y y y

Size: px
Start display at page:

Download "y y y"

Transcription

1 Esimaors Values of α Values of α PRE( i) s MSE( 9)mi

2 THE EFFIIET USE OF SUPPLEMETAR IFORMATIO I FIITE POPULATIO SAMPLIG Rajes Sig Deparme of Saisics, BHU, Varaasi (U.P.), Idia Edior Florei Smaradace Deparme of Maemaics, Uiversi of ew Meico, Gallup, USA Edior 04

3 Educaio Publisig 33 esapeake Aveue olumbus, Oio 43 USA Tel. (64) oprig 04 b Educaioal Publiser ad e auors for eir papers Peer-Reviewers: Dr. A. A. Salama, Facul of Sciece, Por Said Uiversi, Egp. Said Broumi, Uiv. of Hassa II Moammedia, asablaca, Morocco. Pabira Kumar Maji, Ma Deparme, K.. Uiversi, WB, Idia. Mumaz Ali, Deparme of Maemaics, Quaid-i-Azam Uiversi, Islamabad, 44000, Pakisa. EA: ISB:

4 oes Preface: 4. Dual o raio cum produc esimaor i sraified radom samplig: 5. Epoeial raio-produc pe esimaors uder secod order approimaio i sraified radom samplig: 8 3. Two-pase samplig i esimaio of populaio mea i e presece of orespose: 8 4. A famil of media based esimaors i simple radom samplig: 4 5. Differece-pe esimaors for esimaio of mea i e presece of measureme error: 5 3

5 Preface Te purpose of wriig is book is o sugges some improved esimaors usig auiliar iformaio i samplig scemes like simple radom samplig, ssemaic samplig ad sraified radom samplig. Tis volume is a collecio of five papers, wrie b ie co-auors (lised i e order of e papers): Rajes Sig, Mukes Kumar, Maoj Kr. audar, em Kadilar, Praas Sarma, Florei Smaradace, Ail Prajapai, Hema Verma, ad Viplav Kr. Sig. I firs paper dual o raio-cum-produc esimaor is suggesed ad is properies are sudied. I secod paper a epoeial raio-produc pe esimaor i sraified radom samplig is proposed ad is properies are sudied uder secod order approimaio. I ird paper some esimaors are proposed i wo-pase samplig ad eir properies are sudied i e presece of o-respose. I four caper a famil of media based esimaor is proposed i simple radom samplig. I fif paper some differece pe esimaors are suggesed i simple radom samplig ad sraified radom samplig ad eir properies are sudied i presece of measureme error. Te auors ope a book will be elpful for e researcers ad sudes wo are workig i e field of samplig eciques. 4

6 Dual To Raio um Produc Esimaor I Sraified Radom Samplig Rajes Sig, Mukes Kumar ad Maoj K. audar Deparme of Saisics, B.H.U., Varaasi (U.P.), Idia em Kadilar Deparme of Saisics, Haceepe Uiversi, Beepe 06800, Akara, Turke orrespodig auor, rsigsa@aoo.com Absrac Trac e al.[8] ave iroduced a famil of esimaors usig Srivekaaramaa ad Trac ([6],[7]) rasformaio i simple radom samplig. I is aricle, we ave proposed a dual o raio-cum-produc esimaor i sraified radom samplig. Te epressios of e mea square error of e proposed esimaors are derived. Also, e eoreical fidigs are suppored b a umerical eample. Ke words: Auiliar iformaio, dual, raio-cum-produc esimaor, sraified radom samplig, mea square error ad efficiec.. Iroducio I plaig surves, sraified samplig as ofe proved as useful i improvig e precisio of u-sraified samplig sraegies o esimae e fiie populaio mea of e sud variable, L i. Le, ad z respecivel, be e sud ad auiliar variaes i o eac ui U (,,3, ---, ) of e populaio U. Here e size of e sraum U is, ad e size of simple radom sample i sraum U is, were,,---,l. I is sud, 5

7 uder sraified radom samplig wiou replaceme sceme, we sugges esimaors o esimae b cosiderig e esimaors i Plikusas [3] ad i Trac e al. [8]. To obai e bias ad MSE of e proposed esimaors, we use e followig oaios i e res of e aricle: were, w. Suc a, were ad are e sample ad populaio meas of e sud variable i e sraum, respecivel. Similar epressios for ad Z ca also be defied. Usig (), we ca wrie 6

8 were Te combied raio ad e combied produc esimaors are, respecivel, defied as Ad e MSE of ad o e firs degree of approimaio are, respecivel, give b (4) (5) oe a Similar epressios for ad Z ca also be defied.. lassical Esimaors 7

9 Srivekaaramaa ad Trac ([6],[7]) cosidered a simple rasformaio as ( i,,,) were A is a scalar o be cose. Tis rasformaio reders e siuaio suiable for a produc meod isead of raio meod. learl is ubiased for. Usig is rasformaio, a esimaor i e sraified radom samplig is defied as Tis is a produc pe esimaor ( aleraive o combied raio pe esimaor) i sraified radom samplig. Te eac epressio for MSE of is give b (7) I some surve siuaios, iformaio o a secod auiliar variable, Z, correlaed egaivel wi e sud variable,, is readil available. Le be e kow populaio mea of Z. To esimae, Sig[4] cosidered raio-cum-produc esimaor as were Perri[] used α( ) ad z β( Z z) respecivel. Here, α ad β are cosas a make e MSE miimum. z isead of ad z, 8

10 Adapig o e sraified radom samplig, e raio cum produc esimaor usig wo auiliar variables ca be defied as Te approimae MSE of is esimaor is 3. Suggesed Esimaors Trac e al. [8] iroduced a produc esimaor usig wo auiliar variables i e simple radom samplig give b Moivaed b Trac e al. [8], we propose e followig produc esimaor for e sraified radom samplig sceme as Epressig i erms of e s, we ca wrie () as Te MSE o e firs order of approimaio, is give as ad is MSE equaio is miimised for 9

11 oe a e correspodig A is B puig e opimum value of i (), we ca obai e miimum MSE equaio for e firs proposed esimaor,. Remark 3. : Te value of is kow, bu e eac values of V0, V0 ad V00 are rarel available i pracice. However i repeaed surves or sudies based o mulipase samplig, were iformaio is gaered o several occasios i ma be possible o guess e values of V0, V0 ad V00 quie accurael. Eve oug is approac ma reduce e precisio, i ma be saisfacor provided e relaive decrease i precisio is margial, see Trac e al. [8]. as Plikusas[3] defied dual o raio cum produc esimaor i sraified radom samplig were ad g. ( ) osiderig e esimaor i (3) ad moivaed b Sig e al. [5], we propose a famil of dual o raio cum produc esimaor as 0

12 To obai e MSE of e secod proposed esimaor,, we wrie. Epressig (4) i erms of e s, we ave (5) Epadig e rig ad side of (5), o e firs order of approimaio, we ge Squarig bo sides of (6) ad e akig epecaio, we obai e MSE of e secod proposed esimaor,, o e firs order approimaio, as (7) were Tis MSE equaio is miimized for e opimum values of ad give b

13 Puig ese values of ad i MSE ( ), give i (7), we obai e miimum MSE of e secod proposed esimaor,. 4. Teoreical Efficiec omparisos I is secio, we firs compare e efficiec bewee e firs proposed esimaor,, wi e classical combied esimaor, as follows:. Te esimaor is beer a e usual esimaor if ad ol if, B B <, () were, B θ V00 V00 ad B θv0 V0 θv0. If e codiio () is saisfied, e firs proposed esimaor,, performs beer a e classical combied esimaor. We also fid e codiio uder wic e secod proposed esimaor,, performs beer a e classical combied esimaor i eor as follows:,,

14 Te esimaor 9 is beer a e usual esimaor if ad ol if, were, ad 5. umerical Eample I is secio, we use e daa se earlier used i Koucu ad Kadilar[]. Te populaio saisics are give i Table. I is daa se, e sud variable () is e umber of eacers, e firs auiliar variable () is e umber of sudes, ad e secod auiliar variable (Z) is e umber of classes i bo primar ad secodar scools for 93 disrics a 6 regios ( as : Marmara, : Agea, 3: Medierraea, 4: eral Aaolia, 5: Black Sea, 6: Eas ad Sou eas Aaolia) i Turke i 007, see Koucu ad Kadilar[]. Koucu ad Kadilar[] ave used ema allocaio for allocaig e samples o differe sraa. oe a all correlaios bewee e sud ad auiliar variables are posiive. Terefore, we decide o o use produc esimaors for is daa se for efficiec compariso. For is reaso, we appl e classical combied esimaor,, combied raio esimaor,, e raio-cum-produc esimaor,, Plikusas [3] esimaor,, ad e secod proposed esimaor,, o e daa se. For e efficiec compariso, we compue perce relaive efficiecies as 3

15 Table. Daa Saisics of Populaio

16 Table. Perce Relaive Efficiecies (PRE) of esimaors Esimaors Values of PRE( ) MSE( ) mi Table3. Te MSE values accordig o A Value of orrespodig value of A <0.8 - >V(s) (op) 863.6(op) >.40 - >V(s) MSE (mi) a e value A(opimal). 5

17 6. oclusio We we eamie Table, we observe a e secod proposed esimaor,, uder opimum codiio cerail performs quie beer a all oer esimaors discussed ere. Aloug e correlaios are egaive, we also eamie e performace of e firs proposed esimaor,, accordig o e classical combied esimaor. Terefore, for various values of A ad i Table 3, e MSE values of ad are compued. From Table 3, we observe a e firs proposed esimaor,, performs beer a e esimaor,, for a wide rage of as, eve i e egaive correlaios. Refereces [] Koucu,. ad Kadilar,. Famil of Esimaors of Populaio Mea Usig Two Auiliar Variables i Sraified Radom Samplig ommu. i Sais. Teor. ad Me, 38, 009, [] Perri, P.F. Improved raio-cum-produc pe esimaors. Sais. I Tras, 007, [3] Plikusas, A. Some overview of e raio pe esimaors I: Worksop o surve samplig eor ad meodolog, Saisics Esoia, 008. [4] Sig, M. P. Raio-cum-produc meod of esimaio. Merika, 967, [5] Sig, R., Kumar, M., aua, P., Sawa,. ad Smaradace, F. A geeral famil of dual o raio-cum-produc esimaor i sample surves. Sais. I Tras- ew series. IJSA, 0, (), [6] Srivekaaramaa, T. ad Trac, D.S. A aleraive o raio meod i sample surves. A. Is. Sais. Ma.3 A, 980, -0. 6

18 [7] Srivekaaramaa, T. ad Trac, D.S. Eedig produc meod of esimaio o posiive correlaio case i surves. Ausral. J. Sais. 3, 98, [8] Trac, D.S., Sig, H.P. ad Sig, R. A aleraive o e raio-cum-produc esimaor i sample surves. Jour. of Sais. Pla. ad Ifere. 53, 996,

19 Epoeial Raio-Produc Tpe Esimaors Uder Secod Order Approimaio I Sraified Radom Samplig Rajes Sig, Praas Sarma ad Florei Smaradace Deparme of Saisics, Baaras Hidu Uiversi Varaasi-005, Idia Deparme of Maemaics, Uiversi of ew Meico, Gallup, USA orrespodig auor, rsigsa@aoo.com Absrac Sig e al. (0009) iroduced a famil of epoeial raio ad produc pe esimaors i sraified radom samplig. Uder sraified radom samplig wiou replaceme sceme, e epressios of bias ad mea square error (MSE) of Sig e al. (009) ad some oer esimaors, up o e firs- ad secod-order approimaios are derived. Also, e eoreical fidigs are suppored b a umerical eample. Kewords: Sraified Radom Samplig, populaio mea, sud variable, auiliar variable, epoeial raio pe esimaor, epoeial produc esimaor, Bias ad MSE.. ITRODUTIO I surve samplig, i is well esablised a e use of auiliar iformaio resuls i subsaial gai i efficiec over e esimaors wic do o use suc iformaio. However, i plaig surves, e sraified samplig as ofe proved eedful i improvig e precisio of esimaes over simple radom samplig. Assume a e populaio U cosis of L sraa as UU, U,,UL. Here e size of e sraum U is, ad e size of simple radom sample i sraum U is, were,,---,l. We e populaio mea of e auiliar variable,, is kow, Sig e al. (009) suggesed a combied epoeial raio-pe esimaor for esimaig e populaio mea of e sud variable ( ) : 8

20 s S ep (.) s were, i,, i i i L L s w, s w, ad w. L Te epoeial produc-pe esimaor uder sraified radom samplig is give b s S ep (.) s Followig Srivasava (967) a esimaor 3s i sraified radom samplig is defied as : α s 3 S ep (.3) s were α is a cosa suiabl cose b miimizig MSE of 3S. For α, 3S is same as coveioal epoeial raio-pe esimaor wereas for α -, i becomes coveioal epoeial produc pe esimaor. Sig e al. (008) iroduced a esimaor wic is liear combiaio of epoeial raiope ad epoeial produc-pe esimaor for esimaig e populaio mea of e sud variable ( ) i simple radom samplig. Adapig Sig e al. (008) esimaor i sraified radom samplig we propose a esimaor 4s as : s s 4 S θep ( θ)ep (.4) s s 9

21 were θ is e cosa ad suiabl cose b miimizig mea square error of e esimaor 4S. I is observed a e esimaors cosidered ere are equall efficie we erms up o firs order of approimaio are ake. Hossai e al. (006) ad Sig ad Smaradace (03) sudied some esimaors i SRSWOR uder secod order approimaio. Koucu ad Kadilar (009, 00) ), ave sudied some esimaors i sraified radom samplig uder secod order approimaio. To ave more clear picure abou e bes esimaor, i is sud we ave derived e epressios of MSE s of e esimaors cosidered i is paper up o secod order of approimaio i sraified radom samplig. 3. oaios used Le us defie, e suc a 0 s ad e s, V rs L W r s E r [( ) ( ) ] s To obai e bias ad MSE of e proposed esimaors, we use e followig oaios i e res of e aricle: were ad are e sample ad populaio meas of e sud variable i e sraum, respecivel. Similar epressios for ad Z ca also be defied. Also, we ave 0

22 were f γ, f, w. Some addiioal oaios for secod order approimaio: V rs L W r s r s E s [( ) ( ) ] r [ ] s r were, ( ) ( ) rs(), i L 3 () () V W, k k L L 3 () () V W, 30 k() 3 30() V W, 3 L 3 () 03() V 03 W, 3 3 k L k () 3() 3k 4 3() 0() 0() V W, 3

23 L k () 04() 3k 3() 4 0() V 04 W, 4 ( ) L k () () k 4 3() 0() 0() () V W, were k () ( )( ), ( )( ) k () ( )( ) 6 ( ), 3 ( )( )( 3) k 3() ( ) ( )( ). 3 ( )( )( 3) 4. Firs Order Biases ad Mea Squared Errors uder sraified radom samplig Te epressios for biases ad MSE,s of e esimaors S, S ad 3S respecivel, are : 3 Bias ( S ) V0 V 8 (4.) MSE ( S ) V0 V0 V (4.) Bias ( S ) V V0 8 (4.3) MSE ( S ) V0 V0 V 4 (4.4) Bias ( 3S ) α V0 α V0 αv 4 8 (4.5)

24 MSE ( 3S ) V0 α V0 αv 4 (4.6) V B miimizig MSE (3s), e opimum value of α is obaied as α o. B puig is V0 opimum value of α i equaio (4.5) ad (4.6), we ge e miimum value for bias ad MSE of e esimaor 3S. Te epressio for e bias ad MSE of 4s o e firs order of approimaio are give respecivel, as 3 Bias ( 4s) θ V0 V ( θ) V V0 (4.7) 8 8 MSE ( 4S ) V0 θ V0 θv (4.8) V B miimizig MSE ( 4S), e opimum value of θ is obaied as θ o. B puig is V0 opimum value of α i equaio (4.7) ad (4.8) we ge e miimum value for bias ad MSE of e esimaor 3S. We observe a for e opimum cases e biases of e esimaors 3S ad 4S are differe bu e MSE of 3S ad 4S are same. I is also observed a e MSE s of e esimaors 3S ad 4S are alwas less a e MSE s of e esimaors S ad S. Tis promped us o sud e esimaors 3S ad 4S uder secod order approimaio. 5. Secod Order Biases ad Mea Squared Errors i sraified radom samplig Epressig esimaor i s(i,,3,4) i erms of e i s (i0,), we ge s e ( e ) ep 0 e Or 3

25 e s e 0 e0e e e0e e e0e e (5.) Takig epecaios, we ge e bias of e esimaor approimaio as s up o e secod order of Bias ) V V0 V V03 V (s V (5.) Squarig equaio (5.) ad akig epecaios ad usig lemmas we ge MSE of order of approimaio as s up o secod MSE( Or, e S ) E e0 e e0e e0e e 3 8 MSE ( Ee e 4 3 e 8 5 e 4 5 e s) 0 e0e e0 e e0 e 0e 0e e Or, (5.3) MSE ( ) V V V V V V V s V Similarl we ge e biases ad MSE s of e esimaors S, 3S ad 4S up o secod order of approimaio respecivel, as (5.4) 5 5 Bias ( s ) V V0 V V3 V04 V (5.5) MSE ( ) V V V V V V V V ) (5.6) S

26 Bias α 8 α 4 α 8 α 4 α 8 α 48 α 8 α ( 3S ) V0 V V V 03 V3 α 3 4 α α α V (5.7) MSE α 4 α α V ( 3S ) V0 V0 αv V αv V α α α 3α 4 α 4 α 8 V 3α 4 7α 4 V α α 7α V (5.8) Bias ( 4S ) E( 4S ) αv α{ V0 V} α V04 48 ( α 5){ V 03 V } 3 (5.9) MSE ( 4θ ) ( 4θ ) ( 4S ) V0 θ V0 θ V θ V ( 4θ ) θ( θ 5) V 04 θv θ( 4θ ) V 03 4 ( θ 5) θ ( 4θ ) V 3 (5.0) Te opimum value of α we ge b miimizig MSE ( 3S ). Bu eoreicall e deermiaio of e opimum value of α is ver difficul, we ave calculaed e opimum value b usig umerical eciques. Similarl e opimum value of θ wic miimizes e MSE of e esimaor 4s is obaied b usig umerical eciques. 6. umerical Illusraio 5

27 For e oe aural populaio daa, we sall calculae e bias ad e mea square error of e esimaor ad compare Bias ad MSE for e firs ad secod order of approimaio. Daa Se- To illusrae e performace of above esimaors, we ave cosidered e aural daa give i Sig ad audar (986, p.6). Te daa were colleced i a pilo surve for esimaig e ee of culivaio ad producio of fres fruis i ree disrics of Uar- Prades i e ear Table 6.: Bias ad MSE of esimaors Esimaor Bias MSE Firs order Secod order Firs order Secod order s s 3s s OLUSIO I e Table 6. e bias ad MSE of e esimaors S, S, 3S ad 4S are wrie uder firs order ad secod order of approimaio. Te esimaor S is epoeial produc-pe esimaor ad i is cosidered i case of egaive correlaio. So e bias ad mea squared error for is esimaor is more a e oer esimaors cosidered ere. For e classical epoeial raio-pe esimaor, i is observed a e biases ad e mea squared errors icreased for secod order. Te esimaor 3S ad 4S ave e same mea squared error for e firs order bu e mea squared error of 3S is less a 4S for e secod order. So, o 6

28 e basis of e give daa se we coclude a e esimaor 3S is bes followed b e esimaor 4S amog e esimaors cosidered ere. REFEREES Koucu,. ad Kadilar,. (009) : Famil of esimaors of populaio mea usig wo auiliar variables i sraified radom samplig. ommu. i Sais. Teor. ad Me, 38, Koucu,. ad Kadilar,. (00) : O e famil of esimaors of populaio mea i sraified radom samplig. Pak. Jour. Sa., 6(), Sig, D. ad udar, F.S. (986): Teor ad aalsis of sample surve desigs. Wile Easer Limied, ew Deli. Sig, R., aua, P. ad Sawa,.(008): O liear combiaio of Raio-produc pe epoeial esimaor for esimaig fiie populaio mea. Saisics i Trasiio,9(),05-5. Sig, R., Kumar, M., audar, M. K., Kadilar,. (009) : Improved Epoeial Esimaor i Sraified Radom Samplig. Pak. J. Sa. Oper. Res. 5(), pp Sig, R. ad Smaradace, F. (03): O improveme i esimaig populaio parameer(s) usig auiliar iformaio. Educaioal Publisig & Joural of Maer Regulari (Beijig) pg

29 TWO-PHASE SAMPLIG I ESTIMATIO OF POPULATIO MEA I THE PRESEE OF O-RESPOSE Maoj Kr. audar, Ail Prajapai, Rajes Sig ad Florei Smaradace Deparme of Saisics, Baaras Hidu Uiversi, Varaasi-005 Deparme of Maemaics, Uiversi of ew Meico, Gallup, USA orrespodig auor, rsigsa@aoo.com Absrac Te prese paper preses e deail discussio o esimaio of populaio mea i simple radom samplig i e presece of o-respose. Moivaed b Gupa ad Sabbir (008), we ave suggesed e class of esimaors of populaio mea usig a auiliar variable uder o-respose. A eoreical sud is carried ou usig wo-pase samplig sceme we e populaio mea of auiliar variable is o kow. A empirical sud as also bee doe i e suppor of eoreical resuls. Kewords: Two-pase samplig, class of esimaors, opimum esimaor, o-respose, umerical illusraios.. Iroducio Te auiliar iformaio is geerall used o improve e efficiec of e esimaors. ocra (940) proposed e raio esimaor for esimaig e populaio mea weever sud variable is posiivel correlaed wi auiliar variable. orar o e siuaio of raio esimaor, if e sud ad auiliar variables are egaivel correlaed, Mur (964) suggesed e produc esimaor o esimae e populaio mea. Hase e al. (953) proposed e differece esimaor wic was subsequel modified o provide e liear regressio esimaor for e populaio mea or oal. Moa (967) suggesed a esimaor b combiig e raio ad regressio meods for esimaig e populaio parameers. I order o esimae e populaio mea or populaio oal of e sud caracer uilizig auiliar iformaio, several oer auors icludig Srivasava ( 97), Redd (974), Ra ad Saai (980), Srivekaaramaa (980), Srivasava ad Jajj (98) 8

30 ad Sig ad Kumar (008, 0) ave proposed esimaors wic lead improvemes over usual per ui esimaor. I is observed a e o-respose is a commo problem i a pe of surve. Hase ad Hurwiz (946) were e firs o corac e problem of o-respose wile coducig mail surves. Te suggesed a ecique, kow as sub-samplig of orespodes, o deal wi e problem of o-respose ad is adjusmes. I fac e developed a ubiased esimaor for populaio mea i e presece of o-respose b dividig e populaio io wo groups, viz. respose group ad o-respose group. To avoid bias due o o-respose, e suggesed for akig a sub-sample of e o-respodig uis. Le us cosider a populaio cosiss of uis ad a sample of size is seleced from e populaio usig simple radom samplig wiou replaceme (SRSWOR) sceme. Le us assume a ad be e sud ad auiliar variables wi respecive populaio meas ad. Le us cosider e siuaio i wic sud variable is subjeced o orespose ad auiliar variable is free from e o-respose. I is observed a ere are respode ad o-respode uis i e sample of uis for e sud variable. Usig e ecique of sub samplig of o-respodes suggesed b Hase ad Hurwiz (946), we selec a sub-sample of o-respode uis from uis suc a k,k ad collec e iformaio o sub-sample b persoal ierview meod. Te usual sample mea, raio ad regressio esimaors for esimaig e populaio mea uder o-respose are respecivel represeed b (.) 9

31 R (.) lr ( ) b (.3) were ad are e meas based o respode ad o-respode uis respecivel. is e sample mea esimaor of populaio mea, based o sample of size ad b is e sample regressio coefficie of o. Te variace ad mea square errors (MSE) of e above esimaors, are respecivel give b R ad lr were ( ) ( k ) S WS V MSE MSE S ad (.4) ( ) ( ) ( k ) R ρ WS (.5) ( ) ( ) ( k ) lr ρ WS (.6) S are respecivel e mea squares of ad i e populaio. ( S ) ad ( S ) are e coefficies of variaio of ad respecivel. S ad W are respecivel e mea square ad o-respose rae of e o-respose group i e populaio for e sud variable. ρ is e populaio correlaio coefficie bewee ad. We e iformaio o populaio mea of auiliar variable is o available, oe ca use e wo-pase samplig sceme i obaiig e improved esimaor raer a e previous oes. ema (938) was e firs wo gave cocep of wo-pase samplig i esimaig e populaio parameers. Two-pase samplig is cos effecive as well as easier. Tis samplig sceme is used o obai e iformaio abou auiliar variable ceapl from 30

32 a bigger sample a firs pase ad relaivel small sample a e secod sage. Sukame (96) used wo-pase samplig sceme o propose a geeral raio-pe esimaor. Rao (973) used wo-pase samplig o sraificaio, o-respose problems ad ivesigaive comparisos. ocra (977) supplied some basic iformaio for wo-pase samplig. Saoo e al. (993) provided regressio approac i esimaio b usig wo auiliar variables for wo-pase samplig. I e sequece of improvig e efficiec of e esimaors, Sig ad Upadaa (995) suggesed a geeralized esimaor o esimae populaio mea usig wo auiliar variables i wo-pase samplig. I esimaig e populaio mea, if is ukow, firs, we obai e esimae of i usig wo-pase samplig sceme ad e esimae. Uder wo-pase samplig sceme, firs we selec a larger sample of ' uis from e populaio of size wi e elp of SRSWOR sceme. Secodl, we selec a small sample of size from ' uis. Le us agai assume a e siuaio i wic e o-respose is observed o sud variable ol ad auiliar variable is free from e o-respose. Te usual raio ad regressio esimaors of populaio mea uder wo-pase samplig i e presece of o-respose are respecivel give b ' R (.7) ' ad lr b( ) were (.8) ' is e mea based o ' uis for e auiliar variable. Te MSE s of e esimaors followig epressios R ad lr are respecivel represeed b e MSE ( ) ( ) ( k ) R ρ WS ' ' (.9) 3

33 ad MSE ( ) ( ) ( k ) lr ρ WS ' ' (.0) I e prese paper, we ave discussed e sud of o-respose of a geeral class of esimaors usig a auiliar variable. We ave suggesed e class of esimaors i wopase samplig we e populaio mea of auiliar variable is ukow. Te opimum proper of e class is also discussed ad i is compared o raio ad regressio esimaors uder o-respose. Te eoreical sud is also suppored wi e umerical illusraios.. Suggesed lass of Esimaors Le us assume a e o-respose is observed o e sud variable ad auiliar variable provides complee respose o e uis. Moivaed b Gupa ad Sabbir (008), we sugges a class of esimaors of populaio mea uder o-respose as [ ( )] η λ α α η λ (.) were α ad α are e cosas ad wose values are o be deermied. λ ad η( 0) eier cosas or fucios of e kow parameers. are I order o obai e bias ad MSE of, we use e large sample approimaio. Le us assume a ( e ), ( ) suc a ( e ) E( e ) 0 E e, V ( ) ( ) ( k ) e S E W, E V ( ) ( ) e 3

34 ov ad ( ) (, ) E e e ge. ρ Puig e values of ad form e above assumpios i e equaio (.), we ( α ) α ( e τe τe e τ e ) α ( e τe ) (.) O akig epecaio of e equaio (.), e bias of o e firs order of approimaio is give b B ( ) E( ) ( α ) α( τ τρ ) [ α τ ] (.3) Squarig bo e sides of e equaio (.) ad akig epecaio, we ca obai e MSE of o e firs order of approimaio as MSE [ α ( ) ( α ) α ( τ τρ ) ( ρ )] α τ α ( k ) α WS (.4) I e sequece of obaiig e bes esimaor wii e suggesed class wi respec o α ad α, we obai e opimum values of α ad wi respec o α ad α ad equaig e derivaives o zero, we ave α. O differeiaig MSE ( ) MSE α ( ) ( α ) [ α( τ τρ ) α ( ρ τ )] ( ) k α WS 0 (.5) MSE α ( ) [ α α ( ρ τ )] 0 (.6) Solvig e equaios (.4) ad (.5), we ge 33

35 α ( op) (.7) ( ) ( k ) S ρ W ad ( op) α ( op) ( ρ τ ) α (.8) Subsiuig e values of α ( op) ad ( op) α from equaios (.7) ad (.8) io e equaio (.4), e MSE of is give b e followig epressio. MSE MSE ( ) ( lr ) mi (.9) ( ) ( k ) S ρ W 3. Suggesed lass i Two-Pase Samplig I is geerall see a e populaio mea of auiliar variable, is o kow. I is siuaio, we ma use e wo-pase samplig sceme o fid ou e esimae of. Usig wo-pase samplig, we ow sugges a class of esimaors of populaio mea i e presece of o-respose we is ukow, as ' ' [ ( )] η λ α α η λ (3.) 3. Bias ad MSE of B applig e large sample approimaio, we ca obai e bias ad mea square error of. Le us assume a ' ( e ), ( ) ad ( e ) e suc a ( e ) E( e ) E( e ) 0 E,

36 35 ( ) ( ) S W k e E, ( ) e E, ( ) ' 3 e E, ( ) e e E ρ, ( ) ' 3 e e E ρ ad ( ) ' 3 e e E. Uder e above assumpio, e equaio (3.) gives ( ) ( ) e e e e e e e e e e τ τ τ τ τ τ α α ( ) e e e e e e e e τ τ τ τ α (3.) Takig epecaio of bo e sides of equaio (3.), we ge e bias of up o e firs order of approimaio as ( ) ( ) ( ) [ ] ' B α ρ τ α α (3.3) Te MSE of up o e firs order of approimaio ca be obaied b e followig epressio ( ) ( ) ( ) E MSE α ( ) ( ) τρ τ α ' S W k ( ) [ ] ' ρ τ α α α (3.4) 3. Opimum Values of α ad α O differeiaig ( ) MSE wi respec o α ad α ad equaig e derivaives o zero, we ge e ormal equaios

37 MSE α ( ) ( ) ( ) ( k ) α α ( τ ρ ) 0 ' τ τρ S W ' α (3.5) MSE( ) ad [ α α( τ ρ )] 0 α ' (3.6) From equaios (3.5) ad (3.6), we ge e opimum values of α ad α as α ( op) (3.7) ( k ) S ' ρ W ad ( op) α ( op) ( ρ τ ) α (3.8) O subsiuig e opimum values of α ad α, e equaio (3.4) provides miimum MSE of MSE MSE ( ) ( lr ) mi 4. Empirical Sud (3.9) ( k ) S ' ρ W I e suppor of eoreical resuls, some umerical illusraios are give below: 4. I is secio, we ave illusraed e relaive efficiec of e esimaors R, lr ad ( op) wi respec o. For is purpose, we ave cosidered e daa used b Kadilar ad igi (006). Te deails of e populaio are give below: 00, 50, 500, 5, 5,, ρ k.5, 4 S S 5 36

38 Table. Perceage Relaive Efficiec (PRE) wi respec o W Esimaor R lr ( op) Te prese secio preses e relaive efficiec of e esimaors, wi respec o. Tere are wo daa ses wic ave bee cosidered o ad ( op) illusrae e eoreical resuls. R lr Daa Se : Te populaio cosidered b Srivasava (993) is used o give e umerical ierpreaio of e prese sud. Te populaio of seve villages i a Tesil of Idia alog wi eir culivaed area (i acres) i 98 is cosidered. Te culivaed area (i acres) is ake as sud variable ad e populaio is assumed o be auiliar variable. Te populaio parameers are give below: 70, ' 40, 5, 98. 9, , S , S 406.3, S 44., ρ , k. 5 37

39 Table : Perceage Relaive Efficiec wi respec o W Esimaor R lr ( op) Daa Se : ow, we ave used aoer populaio cosidered b Kare ad Sia (004). Te daa are based o e psical grow of upper-socio-ecoomic group of 95 scool cildre of Varaasi disric uder a IMR sud, Deparme of Paediarics, Baaras Hidu Uiversi, Idia durig Te deails are give below: 95, ' 70, 35, , , S , S ,.355, ρ , k. 5. S 38

40 Table 3: Perceage Relaive Efficiec wi respec o W Esimaor R lr ( op) oclusio Te sud of a geeral class of esimaors of populaio mea uder o-respose as bee preseed. We ave also suggesed a class of esimaors of populaio mea i e presece of o-respose usig wo-pase samplig we populaio mea of auiliar variable is o kow. Te opimum proper of e suggesed class as bee discussed. We ave compared e opimum esimaor wi some eisig esimaors roug umerical sud. Te Tables, ad 3 represe e perceage relaive efficiec of e opimum esimaor of suggesed class, liear regressio esimaor ad raio esimaor wi respec o sample mea esimaor. I e above ables, we ave observed a e perceage relaive efficiec of e opimum esimaor is iger a e liear regressio ad raio esimaors. I is also observed a e perceage relaive efficiec decreases wi icrease i orespose. Refereces. ocra, W. G. (940) : Te esimaio of e ields of cereal eperimes b 39

41 samplig for e raio of grai i oal produce, Joural of Te Agriculural Scieces, 30, ocra, W. G. (977) : Samplig Teciques, 3rd ed., Jo Wile ad Sos, ew ork. 3. Gupa, S. ad Sabbir, J. (008) : O improveme i esimaig e populaio mea i simple radom samplig, Joural of Applied Saisics, 35(5), Hase, M. H. ad Hurwiz, W.. (946) : Te problem of o-respose i sample surves, Joural of Te America Saisical Associaio, 4, Hase, M. H., Hurwiz, W.. ad Madow,, W. G. (953): Sample Surve Meods ad Teor, Volume I, Jo Wile ad Sos, Ic., ew ork. 6. Kadilar,. ad igi, H. (006) : ew raio esimaors usig correlaio coefficie, Iersa 4,. 7. Kare, B. B. ad Sia, R. R. (004) : Esimaio of fiie populaio raio usig wo pase samplig sceme i e presece of o-respose, Aligar Joural of Saisics 4, Moa, S. (967) : ombiaio of regressio ad raio esimaes, Joural of e Idia Saisical Associaio 5, Mur, M.. (964) : Produc meod of esimaio, Saka, 6A, ema, J. (938). oribuio o e eor of samplig uma populaios, Joural of America Saisical Associaio, 33, Rao, J..K. (973) : O double samplig for sraificaio ad aalic surves, Biomerika, 60, Ra, S. K. ad Saai, A. (980) : Efficie families of raio ad produc-pe esimaors, Biomerika, 67, Redd, V.. (974) : O a rasformed raio meod of esimaio, Saka, 36, Saoo, J., Saoo, L.., Moa, S. (993) : A regressio approac o esimaio i wo pase samplig usig wo auiliar variables. urr. Sci. 65(),

42 5. Sig, G.. ad Upadaa, L.. (995) : A class of modified cai-pe esimaors usig wo auiliar variables i wo-pase samplig, Mero, Vol. LIII, o. 3-4, Sig, R., Kumar, M. ad Smaradace, F. (008): Almos Ubiased Esimaor for Esimaig Populaio Mea Usig Kow Value of Some Populaio Parameer(s). Pak. J. Sa. Oper. Res., 4() pp Sig, R. ad Kumar, M. (0): A oe o rasformaios o auiliar variable i surve samplig. MASA, 6:, 7-9. doi 0.333/MASA Srivasava, S. (993) Some problems o e esimaio of populaio mea usig auiliar caracer i presece of o-respose i sample surves. P. D. Tesis, Baaras Hidu Uiversi, Varaasi, Idia. 9. Srivasava, S.K. (97) : A geeralized esimaor for e mea of a fiie populaio usig muli-auiliar iformaio, Joural of Te America Saisical Associaio, 66 (334), Srivasava, S.K. ad Jajj, H. S. (98) : A class of esimaors of e populaio mea i surve samplig usig auiliar iformaio, Biomerika, 68 (), Srivekaaramaa, T. (980) : A dual o raio esimaor i sample surves, Biomerika, 67 (), Sukame, B. V. (96) : Some raio-pe esimaors i wo-pase samplig, Joural of e America Saisical Associaio, 57,

43 A Famil of Media Based Esimaors i Simple Radom Samplig Hema K. Verma, Rajes Sig ad Florei Smaradace Deparme of Saisics, Baaras Hidu Uiversi Varaasi-005, Idia Deparme of Maemaics, Uiversi of ew Meico, Gallup, USA orrespodig auor, rsigsa@aoo.com Absrac I is paper we ave proposed a media based esimaor usig kow value of some populaio parameer(s) i simple radom samplig. Various eisig esimaors are sow paricular members of e proposed esimaor. Te bias ad mea squared error of e proposed esimaor is obaied up o e firs order of approimaio uder simple radom samplig wiou replaceme. A empirical sud is carried ou o judge e superiori of proposed esimaor over oers. Kewords: Bias, mea squared error, simple radom samplig, media, raio esimaor.. Iroducio osider a fiie populaio U {U, U,..., U } of disic ad ideifiable uis. Le be e sud variable wi value measured o U i, i,,3...,. Te problem is o esimae e i populaio mea i i. Te simples esimaor of a fiie populaio mea is e sample mea obaied from e simple radom samplig wiou replaceme, we ere is o auiliar iformaio available. Someimes ere eiss a auiliar variable wic is posiivel correlaed wi e sud variable. Te iformaio available o e auiliar variable ma be uilized o obai a efficie esimaor of e populaio mea. Te samplig eor describes a wide varie of eciques for usig auiliar iformaio o obai more efficie esimaors. Te raio esimaor ad e regressio esimaor are e wo impora esimaors available i e lieraure wic are usig e auiliar iformaio. To kow more abou e raio ad regressio esimaors ad oer relaed resuls oe ma refer o [-3]. 4

44 We e populaio parameers of e auiliar variable suc as populaio mea, coefficie of variaio, kurosis, skewess ad media are kow, a umber of modified raio esimaors are proposed i e lieraure, b eedig e usual raio ad Epoeial- raio pe esimaors. Before discussig furer abou e modified raio esimaors ad e proposed media based modified raio esimaors e oaios ad formulae o be used i is paper are described below: - Populaio size - Sample size - Sud variable - Auiliar variable μ3 r β Were μr (i ), oefficie of skewess of e auiliar variable 3 μ i ρ - orrelaio o-efficie bewee ad, - Populaio meas, - Sample meas M, - Average of sample medias of m - Sample media of β - Regressio coefficie of o B (.) - Bias of e esimaor V (.) - Variace of e esimaor MSE (.) - Mea squared error of e esimaor MSE(e) PRE (e,p) 00 - Perceage relaive efficiec of e proposed esimaor p MSE(e) wi respec o e eisig esimaor e. Te formulae for compuig various measures icludig e variace ad e covariace of e SRSWOR sample mea ad sample media are as follows: V (), f f (i ) S, V() (i ) S, V(m) (mi M) i i i ov(, ) f (i )(i ) (i )(i ), i i 43

45 ov(, m) V() ', i (m M)( ), V(m) ', M i i ov(, m) ', M ' mm m ov(, ) (i ), S (i ) i i Were f ; S, I e case of simple radom samplig wiou replaceme (SRSWOR), e sample mea is used o esimae e populaio mea. Ta is e esimaor of r wi e variace V( f (.) r ) S Te classical Raio esimaor for esimaig e populaio mea of e sud variable is defied as R. Te bias ad mea squared error of R are give as below: B( R MSE( ' ' { } ) (.) R ' ) V() R V() R ov(, ) were ' R ' (.3). Proposed esimaor Suppose M δ(m m ) 0,, ep were M am b, m am b αm ( α)m M m Suc a,, w, were w deoes e se of all possible raio pe esimaors for esimaig 0 e populaio mea. B defiiio e se w is a liear varie, if w for 0 i 0 w w i w w R i W, g (.) (.) were w i (i0,, ) deoes e saisical cosas ad R deoes e se of real umbers. Also, αm M ( α)m g, δ(m m ) ep M m 44

46 ad M am b, m am b. To obai e bias ad MSE epressios of e esimaor, we wrie ( e0 ), m M( e) suc a E (e0) E(e ) 0, ( ) V( m) ov(,m) V E (e ), E(e ), E(e e ) M M 0 mm 0 m Epressig e esimaor i erms of e s, we ave ( e0 ) w 0 w am were υ. am b ( υαe ) g w υδe ep υe (.3) Epadig e rig ad side of equaio(.3) up o e firs order of approimaio, we ge υwe e0 υ w δ were w αgw w. Takig epecaios of bo sides of (.4) ad e subracig from bo sides, we ge e biases of esimaors,up o e firs order of approimaio as g(g ) B() υ w α αυ(g ) B() gαυ δυ δ υ B( ) 4 8 From (.4), we ave mm g(g ) α δ δ w 4 8 mm m δυ m δ δ w 4 8 mm υw e m υwe 0 e (.4) (.5) (.6) (.7) (.8) e (e0 υwe) (.9) Squarig bo sides of (.9) ad e akig epecaios, we ge e MSE of e esimaor, up o e firs order of approimaio as 45

47 MSE() V were R ( ) υ R w V( m) υrwov(, m). M (.0) MSE() will be miimum, we (, m) ov w k(sa) υr V m ( ) (.) Puig e value of w(k) i (.0), we ge e miimum MSE of e esimaor, as mi. MSE() V ( )( ρ ) (.) Te miimum MSE of e esimaor is same as a of radiioal liear regressio esimaor. From (.5) ad (.), we ave δ αgw w k (.3) From (.) ad (.3), we ave ol wo equaios i ree ukows. I is o possible o fid e uique values of w i s (i0,, ). I order o ge uique values for w i s, we sall impose e liear resricio ( ) w B( ) w B( ) 0 (.4) w B 0 Equaios (.), (.) ad (.4) ca be wrie i mari form as 0 0 αg B( ) w δ w B( ) w 0 k 0 (.5) Usig (.5) we ge e uique value of w i s (i0,, ) as 46

48 w w w 0 Δ 0 Δ r Δ Δ r Δ Δ r were Δ 0 δ Δ r αgb( ) B() δ B( )( αg k) B() k Δ kb( ) Δ kb( ) (.6) Table.: Some members of e proposed esimaor w 0 w w a b α g δ Esimaors q M q m 0 0 β ρ β M ρ - q3 βm ρ 0 0 ρ ρm β β - q 4 ρm β (M m) q 5 ep M m 0 0 β ρ - - q 6 ep β β (M m) ( M m) ρ 0 0 ρ β - - q 7 ep ρ ρ(m m) ( M m) β 0 β ρ q 8 β M ρ ep βm ρ β β (M m) ( M m) ρ 0 ρ β q 9 ρm β ep ρm β ρ ρ(m m) ( M m) β M (M m) 0 0 q 0 ep m M m 47

49 3. Empirical Sud For umerical illusraio we cosider: e populaio ad ake from [4] pageo.77, e populaio 3 is ake from [5] page o.04. Te parameer values ad cosas compued for e above populaios are give i e Table 3.. MSE for e proposed ad eisig esimaors compued for e ree populaios are give i e Table 3. wereas e PRE for e proposed ad eisig esimaors compued for e ree populaios are give i e Table 3.3. Table: 3. Parameer values ad cosas for 3 differe populaios Parameers For sample size 3 For sample size 5 Popl- Popl- Popl-3 Popl- Popl- Popl M β R V () V () V (m) ov (,m) ov (, ) ρ

50 Table: 3.. Variace / Mea squared error of e eisig ad proposed esimaors Esimaors For sample size 3 For sample size 5 Populaio- Populaio- Populaio-3 Populaio- Populaio- Populaio-3 q q q q q q q q q q (op) Table: 3.3. Perceage Relaive Efficiec of esimaors wi respec o Esimaors For sample size 3 For sample size 5 Populaio- Populaio- Populaio-3 Populaio- Populaio- Populaio-3 q q q q q q q q

51 q q (op) oclusio From empirical sud we coclude a e proposed esimaor uder opimum codiios perform beer a oer esimaors cosidered i is paper. Te relaive efficiecies ad MSE of various esimaors are lised i Table 3. ad 3.3. Refereces. Mur M.. (967). Samplig eor ad meods. Saisical Publisig Socie, alcua, Idia.. ocra, W. G. (977): Samplig Teciques. Wile Easer Limied. 3. Kare B.B. ad Srivasava S.R. (98): A geeral regressio raio esimaor for e populaio mea usig wo auiliar variables. Alig. J. Sais.,: Sisodia, B.V.S. ad Dwivedi, V.K. (98): A modified raio esimaor usig co-efficie of variaio of auiliar variable. Joural of e Idia Socie of Agriculural Saisics 33(), Sig G.. (003): O e improveme of produc meod of esimaio i sample surves. Joural of e Idia Socie of Agriculural Saisics 56 (3), Sig H.P. ad Tailor R. (003): Use of kow correlaio co-efficie i esimaig e fiie populaio meas. Saisics i Trasiio 6 (4), Sig H.P., Tailor R., Tailor R. ad Kakra M.S. (004): A improved esimaor of populaio mea usig Power rasformaio. Joural of e Idia Socie of Agriculural Saisics 58(), Sig, H.P. ad Tailor, R. (005): Esimaio of fiie populaio mea wi kow coefficie of variaio of a auiliar. STATISTIA, ao LV,.3, pp Kadilar. ad igi H. (004): Raio esimaors i simple radom samplig. Applied Maemaics ad ompuaio 5, Koucu. ad Kadilar. (009): Efficie Esimaors for e Populaio mea. Haceepe Joural of Maemaics ad Saisics, Volume 38(), Sig R., Kumar M. ad Smaradace F. (008): Almos ubiased esimaor for esimaig populaio mea usig kow value of some populaio parameer(s). Pak.j.sa.oper.res., Vol.IV, o., pp

52 . Sig, R. ad Kumar, M. (0): A oe o rasformaios o auiliar variable i surve samplig. Mod. Assis. Sa. Appl., 6:, 7-9. doi 0.333/MAS Sig R., Malik S., audar M.K., Verma H.K., ad Adewara A.A. (0): A geeral famil of raio-pe esimaors i ssemaic samplig. Jour. Reliab. Sa. Ssci., 5(): Sig, D. ad audar, F. S. (986): Teor ad aalsis of surve desigs. Wile Easer Limied. 5. Mukopada, P. (998): Teor ad meods of surve samplig. Preice Hall. 5

53 DIFFREE-TPE ESTIMATORS FOR ESTIMATIO OF MEA I THE PRESEE OF MEASUREMET ERROR Viplav Kr. Sig, Rajes Sig ad Florei Smaradace Deparme of Saisics, Baaras Hidu Uiversi Varaasi-005, Idia Deparme of Maemaics, Uiversi of ew Meico, Gallup, USA orrespodig auor, rsigsa@aoo.com Absrac I is paper we ave suggesed differece-pe esimaor for esimaio of populaio mea of e sud variable i e presece of measureme error usig auiliar iformaio. Te opimum esimaor i e suggesed esimaor as bee ideified alog wi is mea square error formula. I as bee sow a e suggesed esimaor performs more efficie e oer eisig esimaors. A empirical sud is also carried ou o illusrae e meris of proposed meod over oer radiioal meods. Ke Words: Sud variable, Auiliar variable, Measureme error, Simple radom Samplig, Bias, Mea Square error.. PERFORMAE OF SUGGESTED METHOD USIG SIMPLE RADOM SAMPLIG 5

54 ITRODUTIO Te prese sud deals wi e impac of measureme errors o esimaig populaio mea of sud variable () i simple radom samplig usig auiliar iformaio. I eor of surve samplig, e properies of esimaors based o daa are usuall presupposed a e observaios are e correc measureme o e caracerisic beig sudied. We e measureme errors are egligible small, e saisical iferece based o observed daa coiue o remai valid. A impora source of measureme error i surve daa is e aure of variables (sud ad auiliar). Here aure of variable sigifies a e eac measureme o variables is o available. Tis ma be due o e followig ree reasos:. Te variable is clearl defied bu i is ard o ake correc observaio a leas wi e currel available eciques or because of oer pes of pracical difficulies. Eg: Te level of blood sugar i a uma beig.. Te variable is cocepuall well defied bu observaio ca obai ol o some closel relaed subsiues kow as Surrogaes. Eg: Te measureme of ecoomic saus of a perso. 3. Te variable is full compreesible ad well udersood bu i is o irisicall defied. Eg: Ielligece, aggressiveess ec. Some auors icludig Sig ad Karpe (008, 009), Salab(997), Alle e al. (003), Maisa ad Sig (00, 00), Srivasava ad Salab (00), Kumar e al. (0 a,b), Malik ad Sig (03), Malik e al. (03) ave paid eir aeio owards e esimaio of populaio mea μ of sud variable usig auiliar iformaio i e presece of measureme errors. Fuller (995) eamied e imporace of measureme errors i esimaig parameers i sample surves. His major cocers are esimaio of populaio mea or oal ad is sadard error, quarile esimaio ad esimaio roug regressio model. SMBOLS AD SETUP 53

55 Le, for a SRS sceme ( i, i ) be e observed values isead of rue values, ) o wo caracerisics (, ), respecivel for all i(,, ) ad e observaioal or ( i i measureme errors are defied as u v i i ( ) () i i ( ) () i i were ui ad vi are socasic i aure wi mea 0 ad variace For e sake of coveiece, we assume a u ad v respecivel. u i ' s ad v i ' s are ucorrelaed aloug i ' s ad ' s are correlaed.suc a specificaio ca be, owever, relaed a e i cos of some algebraic complei. Also assume a fiie populaio correcio ca be igored. Furer, le e populaio meas ad variaces of (, ) be ( μ, μ ) ad (, ). ad ρ be e populaio covariace ad e populaio correlaio coefficie bewee ad respecivel. Also le ad μ μ are e populaio coefficie of variaio ad is e populaio coefficies of covariace i ad. LARGE SAMPLE APPROIMATIO Defie: e 0 μ ad μ e μ μ were, e 0 ad e are ver small umbers ad e i < (i 0,). Also, E(e i ) 0(i 0,) u ad, E(e0 ) θ δ 0, 54

56 55 v ) (e E δ θ, 0 ) e (e E θρ, were θ.. EISTIG ESTIMATORS AD THEIR PROPERTIES Usual mea esimaor is give b i i (3) Up o e firs order of approimaio e variace of is give b u Var() θμ (4) Te usual raio esimaor is give b μ R (5) were μ is kow populaio mea of. Te bias ad MSE ( R ), o e firs order of approimaio, are respecivel, give ρ θμ v R ) ( B (6) ρ θμ v u R ) ( MSE (7) Te radiioal differece esimaor is give b ) k( d μ (8) were, k is e cosa wose value is o be deermied. Miimum mea square error of d a opimum value of

57 56 v k μ ρ μ, is give b ρ θ μ v u u d ) ( MSE (9) Srivasava (967) suggesed a esimaor S μ (0) were, is a arbirar cosa. Up o e firs of approimaio, e bias ad miimum mea square error of S a opimum value of v ρ are respecivel, give b θρ θ μ v S ) ( ) ( B () ρ θ μ v u u S ) ( MSE () Wals (970) suggesed a esimaor w μ μ w ) ( (3) were, is a arbirar cosa.

58 57 Up o e firs order of approimaio, e bias ad miimum mea square error of w a opimum value of v ρ, are respecivel, give b ρ θ μ v w ) ( B (4) ρ θ μ v u u w ) ( MSE (5) Ra ad Saai (979) suggesed e followig esimaor μ 3 3 RS ) ( (6) were, 3 is a arbirar cosa. Up o e firs order of approimaio, e bias ad mea square of RS a opimum value of ρ v 3 are respecivel, give b 3 RS ) ( B ρ μ θ (7) ρ θ μ v u u RS ) ( MSE (8) 3. SUGGESTED ESTIMATOR Followig Sig ad Solaki (03), we sugges e followig differece-pe class of esimaors for esimaig populaio mea of sud variable as

59 [ α α ( α α ) μ ] α μ p (9) were α, ) are suiabl cose scalars suc a MSE of e proposed esimaor is ( α miimum, ( η λ), μ ημ λ) wi (, λ) are eier cosas or fucio of some ( kow populaio parameers. Here i is ieresig o oe a some eisig esimaors ave bee sow as e members of proposed class of esimaors p for differe values of ( λ α, α, α, η, ), wic is summarized i Table. Table : Members of suggesed class of esimaors Values of osas Esimaors α α α η λ [Usual ubiased] R [Usual raio] 0 0 d [Usual differece] α 0 - μ S [Srivasava (967)] 0 α 0 DS [Dube ad Sig] α α 0 0 Te properies of suggesed esimaor are derived i e followig eorems. Teorem.: Esimaor p i erms of e i ;i 0, epressed as: p [ μ αaeμ Bμ e α 0 0 { αae Be e μ αaμ e e } α { e α }] ημ Ae 58

60 r s igorig e erms E(ei e j ) for (rs)>,were r,s0,,... ad i 0, ; j (firs order of approimaio). were, ημ α( α ) A, B A ad μ μ. ημ λ Proof p [ α α ( α α ) μ ] μ α Or [ α ( e ) α η μ e ( α ) μ ][ Ae ] α (0) p 0 We assume e <, so a e erm A α ( Ae) is epadable. Epadig e rig ad side (0) ad eglecig e erms of e s avig power greaer a wo, we ave p μ αae μ Bμ e α { αae Be e μ αaμ e e } 0 0 α { e α } ημ Ae Teorem:. Bias of e esimaor p is give b B( p Proof: [ Bμ δ α { Bδ αaμ δ } α ημ Aαδ ] ) () B( p ) E( p μ ) 0 [ 0 0 E μ μ αae μ Bμ e α { αae Be e μ αaμ e e } [ Bμ δ α { Bδ αaμ δ } α ημ Aαδ ] 0 α { e α }] ημ Ae were, δ 0, δ adδ0 are alread defied i secio 3. 59

61 Teorem.3: MSE of e esimaor p, up o e firs order of approimaio is MSE( p ) α { μ δ0 δ( α A B ) 4αAμ δ0} α η μ δ { δ( α A μ Bμ )} α{ δ( B Bμ α A μ ) δ0αaμ ( μ ) } α ημ αaδ ( μ ) α α ημ ( μ δ Aα δ ) () Proof: 0 MSE( p ) E( p μ ) [ 0 0 e E α { Aαe e μ Be αaμ e e } α ημ { e Aα } αae ] μ Bμ e Squarig ad e akig epecaios of bo sides, we ge e MSE of e suggesed esimaor up o e firs order of approimaio as MSE( p ) α { μ δ0 δ( α A B ) 4αAμ δ0} α η μ δ { δ( α A μ Bμ )} α{ δ( B Bμ α A μ ) δ0αaμ ( μ ) } α ημ αaδ ( μ ) α α ημ ( μ δ Aα δ ) 0 Equaio () ca be wrie as: MSE ( ) α ϕ α ϕ α ϕ α ϕ α α ϕ ϕ (3) p Differeiaig (3) wi respec o α, ) ad equaig em o zero, we ge e opimum values of α, ) as ( α ( α ϕ ϕ ϕ ϕ ϕ ϕ ϕ ϕ α(op) ad α (op) ϕϕ ϕ5 ϕϕ ϕ5 were, ϕ μ δ0 δ( α A B ) 4αAμ δ0 ϕ η μ δ 60

62 ( B Bμ α A μ ) δ αaμ ( μ ) ϕ 3 δ 0 ( μ ) ϕ 4 ημ αaδ ϕ ( μ δ Aα ). 5 ημ 0 δ ϕ δ ( α A μ Bμ ) I e Table some esimaors are lised wic are paricular members of e suggesed class of esimaors p for differe values of ( α, η, λ). Table : Paricular members of e suggesed class of esimaors p Esimaors Values of cosas α η λ μ [ α α ( α α ) μ ] - 0 μ [ α α ( ) ( α α )( μ ) ] μ [ α α ( ) ( α α )( μ ) ] - μ ρ [ α α ( ρ) ( α α )( μ ρ) ] - ρ [ α α ( ) ( α α )( μ )] ρ - μ 6

63 μ [ α α ( ) ( α α )( μ )] 6-7 [ α α ( ) ( α α )( μ )] μ EMPIRIAL STUD Daa saisics: Te daa used for empirical sud as bee ake from Gujarai (007) Were, True cosumpio epediure, i i True icome, i Measured cosumpio epediure, i Measured icome. μ μ ρ u v Te perceage relaive efficiecies (PRE) of various esimaors wi respec o e mea per ui esimaor of, a is,ca be obaied as Var() PRE (.) 00 MSE(.) Table 3: MSE ad PRE of esimaors wi respec o Esimaors Mea Square Error Perce Relaive Efficiec R d

64 S DS PERFORMAE OF SUGGESTED ESTIMATOR I STRATIFIED RADOM SAMPLIG SMBOLS AD SETUP osider a fiie populaio U (u, u,...,u ) of size ad le ad respecivel be e auiliar ad sud variables associaed wi eac ui u j (j,,..., ) of populaio. Le e populaio of be sraified i o L sraa wi e sraum coaiig L uis, were,,,3,.,l suc a i. A simple radom size is drow wiou replaceme from e sraum suc a L i. Le, ) of wo ( i i caracerisics (,) o i ui of e sraum, were i,,,,. I addiio le ( i, i ), i i ( s W, s W i i ), 63

65 ( μ i, μ i i L Ad ( μ W μ, μ i i ), W μ ) be e samples meas ad populaio meas of(,) respecivel, were W is e sraum weig. Le e observaioal or measureme errors be u i (4) i i v i (5) i i Were ui ad vi are socasic i aure ad are ucorrelaed wi mea zero ad variaces V ad U respecivel. Furer le ρ be e populaio correlaio coefficie bewee ad i e sraum. I is also assumed a e fiie populaio correcio erms f ) ad ( f ) ca be igored were f ad ( Le, LARGE SAMPLE APPROIMATIO μ ( e ), ad μ ( e ) s 0 suc a, E(e ) E(e ) 0, 0 s f. E(e 0 U ) 0, θ E(e V ), θ E(e. 0e ) ρ 0 were,,, μ U V θ ad θ. μ U 64 V

66 EISTIG ESTIMATORS AD THEIR PROPERTIES s is usual ubiased esimaor i sraified radom samplig sceme. Te usual combied raio esimaor i sraified radom samplig i e presece of measureme error is defied as- T R μ s (6) s Te usual combied produc esimaor i e presece of measureme error is defied as- T PR s s (7) μ ombied differece esimaor i sraified radom samplig is defied i e presece of measureme errors for a populaio mea, as T D d( μ ) (8) s s Te variace ad mea square erm of above esimaors, up o e firs order of approimaio, are respecivel give b U Var ( s ) (9) MSE(T MSE(T W L R ) R θ θ W L P ) R θ θ ( R β θ ) ( R β θ ) (30) (3) L L L W W W MSE (T D ) d d β (3) θ θ 65

67 were, d op L L W β W θ 6. SUUGESTED ESTIMATOR AD ITS PROPERTIES Le B(.) ad M(.) deoe e bias ad mea square error (M.S.E) of a esimaor uder give samplig desig. Esimaor p defied i equaio (9) ca be wrie i sraified radom samplig as [ β β ( β β ) μ ] β μ T P s s (33) s were α, ) are suiabl cose scalars suc a MSE of proposed esimaor is ( α miimum, ( η λ), μ ημ λ) wi (, λ) are eier cosas or fucios of s s ( some kow populaio parameers. Here i is ieresig o oe a some eisig esimaors ave bee foud paricular members of proposed class of esimaors Tp for differe values of α, α, α, η, ), wic are summarized i Table 4. ( λ Table 4: Members of proposed class of esimaors T p Values of osas Esimaors α α α η λ s [Usual ubiased] T R [Usual raio] 0 0 T PR [Usual produc] 0-0 T D [Usual differece] α 0 - μ 66

68 Teorem.: Esimaor r s T i erms of e i ; i 0, b igorig e erms E( e i e ) for P j (rs)>,were r,s0,,... ad i 0, ; j, ca be wrie as T P [ μ βa' eμ B' μ e β 0 0 { ' βa' e B' ' e e μ βa' μ e e } β { e βa' }] ημ e were, ημ β( β ) A ', B' A' ad ' μ μ. ημ λ Proof T P [ β β ( β β ) μ ] μ s s s β [ β e ) β η μ e ( β ) μ ][ A' ] β ( (34) 0 e We assume A ' e <, so a e erm A' e ) ( β is epadable. Tus b epadig e rig ad side (0) ad eglecig e erms of e s avig power greaer a wo, we ave [ 0 0 Tp μ βa' e μ B' μ e β { ' βa' ' e B' ' e e μ βa' μ e e } Teorem:. Bias of T p is give b P [ B' μ β { B' ' βa' μ } β ημ A' β ] 0 β { e βa' }] ημ e B(T ) (35) Proof: B(T ) E(T P P μ ) [ 0 0 E μ μ βa' e μ B' μ e β { ' βa' ' e B' ' e e μ βa' μ e e } β { e βa' }] ημ e 67

69 [ B' μ β { B' ' βa' μ } β βημ A' ] 0 were, 0, ad 0 are alread defied i secio 3. Teorem:.3 Mea square error of Tp, up o e firs order of approimaio is give b MSE(T ) β P { ' μ 0 ( β A' ' B'' ) 4βA'' μ 0} β η μ { ' ( β A' μ B' ' μ )} β{ ' ( B' ' B' ' μ β A' ' μ ) 0βAμ ( μ ' )} β ημ βa ( μ ' ) β β ημ ( μ A' β ) (36) Proof: 0 ' MSE(T MSE(T ) β P ) E(TP μ ) P { ' μ 0 ( β A' ' B'' ) 4βA'' μ 0} β η μ { ' ( β A' μ B'' μ )} β{ ' ( B'' B'' μ β A' ' μ ) 0βAμ ( μ ' )} β ημ βa ( μ ' ) β β ημ ( μ A' β ) 0 ' MSE(Tp) ca also be wrie as MSE (T ) β χ β χ β χ β χ β β χ χ (37) P Differeiaig equaio (37) wi respec o β, ) ad equaig i o zero, we ge e opimum values of β, ) respecivel, as ( β ( β χ χ χ χ χ χ χ β(op) adβ (op) χχ χ 5 χχ χ 5 χ were, χ ' μ 0 ( β A' ' B' ' ) 4βA' ' μ 0 χ η μ ( B B' ' μ β A' ' μ ) βa' μ ( μ ' ) χ 3 ' 0 ( μ ' ) χ 4 ημ βa' 68

70 χ ( μ A' β ' ). 5 ημ 0 χ ' ( β A' μ B' ' μ ) Wi e elp of ese values, we ge e miimum MSE of e suggesed esimaor Tp. 7. DISUSSIO AD OLUSIO I e prese sud, we ave proposed differece-pe class of esimaors of e populaio mea of a sud variable we iformaio o a auiliar variable is kow i advace. Te asmpoic bias ad mea square error formulae of suggesed class of esimaors ave bee obaied. Te asmpoic opimum esimaor i e suggesed class as bee ideified wi is properies. We ave also sudied some radiioal meods of esimaio of populaio mea i e presece of measureme error suc as usual ubiased, raio, usual differece esimaors suggesed b Srivasava(967), dube ad sig( 00), wic are foud o be paricular members of suggesed class of esimaors. I addiio, some ew members of suggesed class of esimaors ave also bee geeraed i simple radom samplig case. A empirical sud is carried o row lig o e performace of suggesed esimaors over oer eisig esimaors usig simple radom samplig sceme. From e Table 3, we observe a suggesed esimaor 3 performs beer a e oer esimaors cosidered i e prese sud ad wic reflecs e usefuless of suggesed meod i pracice. REFEREES Alle, J., Sig, H. P. ad Smaradace, F. (003): A famil of esimaors of populaio mea usig muliauiliar iformaio i presece of measureme errors. Ieraioal Joural of Social Ecoomics 30 (7), A.K. Srivasava ad Salab (00). Effec of measureme errors o e regressio meod of esimaio i surve samplig. Joural of Saisical Researc, Vol. 35, o., pp Bal, S. ad Tueja, R. K. (99): Raio ad produc pe epoeial esimaor. Iformaio ad opimizaio scieces (), adok, P.K., & Ha,.P.(990):O e efficiec of e raio esimaor uder Midzuo sceme wi measureme errors. Joural of e Idia saisical Associaio,8,

71 Dube, V. ad Sig, S.K. (00). A improved regressio esimaor for esimaig populaio mea, J. Id. Soc. Agri. Sais., 54, p Gujarai, D.. ad Sageea (007): Basic ecoomerics. Taa McGraw Hill. Koucu,. ad Kadilar,. (00): O e famil of esimaors of populaio mea i sraified samplig. Pakisa Joural of Saisics. Pak. J. Sa. 00 vol 6 (), Kumar, M., Sig, R., Sig, A.K. ad Smaradace, F. (0 a): Some raio pe esimaors uder measureme errors. WASJ 4() :7-76. Kumar, M., Sig, R., Sawa,. ad aua, P. (0b): Epoeial raio meod of esimaors i e presece of measureme errors. I. J. Agricul. Sa. Sci. 7(): Malik, S. ad Sig, R. (03) : A improved class of epoeial raio- pe esimaor i e presece of measureme errors. OTOGO Maemaical Magazie,,, Malik, S., Sig, J. ad Sig, R. (03) : A famil of esimaors for esimaig e populaio mea i simple radom samplig uder measureme errors. JRSA, (), Maisa ad Sig, R. K. (00): A esimaio of populaio mea i e presece of measureme errors. Joural of Idia Socie of Agriculural Saisics 54(), 3 8. Maisa ad Sig, R. K. (00): Role of regressio esimaor ivolvig measureme errors. Brazilia joural of probabili Saisics 6, Salab (997): Raio meod of esimaio i e presece of measureme errors. Joural of Idia Socie of Agriculural Saisics 50(): Sig, H. P. ad Karpe,. (008): Raio-produc esimaor for populaio mea i presece of measureme errors. Joural of Applied Saisical Scieces 6, Sig, H. P. ad Karpe,. (009): O e esimaio of raio ad produc of wo populaios meas usig supplemear iformaio i presece of measureme errors. Deparme of Saisics, Uiversi of Bologa, 69(), Sig, H. P. ad Viswakarma, G. K. (005): ombied Raio-Produc Esimaor of Fiie Populaio Mea i Sraified Samplig. Meodologia de Ecuesas 8:

72 Sig, H. P., Raour, A., Solaki, R. S.(03): A improveme over differece meod of esimaio of populaio mea. JRSS, 6(): Sig H. P., Raour A., Solaki R.S. (03): a improveme over differece meod of esimaio of populaio mea. JRSS, 6(): Srivasava, S. K. (967): A esimaor usig auiliar iformaio i e sample surves. alcua saisical Associaio Bullei 6,-3. Wals, J.E.(970). Geeralisaio of raio esimae for populaio oal. Saka A.3,

73 Te purpose of wriig is book is o sugges some improved esimaors usig auiliar iformaio i samplig scemes like simple radom samplig, ssemaic samplig ad sraified radom samplig. Tis volume is a collecio of five papers, wrie b ie co-auors (lised i e order of e papers): Rajes Sig, Mukes Kumar, Maoj Kr. audar, em Kadilar, Praas Sarma, Florei Smaradace, Ail Prajapai, Hema Verma, ad Viplav Kr. Sig. I firs paper dual o raio-cum-produc esimaor is suggesed ad is properies are sudied. I secod paper a epoeial raio-produc pe esimaor i sraified radom samplig is proposed ad is properies are sudied uder secod order approimaio. I ird paper some esimaors are proposed i wo-pase samplig ad eir properies are sudied i e presece of o-respose. I four caper a famil of media based esimaor is proposed i simple radom samplig. I fif paper some differece pe esimaors are suggesed i simple radom samplig ad sraified radom samplig ad eir properies are sudied i presece of measureme error.

Effect of Measurement Errors on the Separate and Combined Ratio and Product Estimators in Stratified Random Sampling

Effect of Measurement Errors on the Separate and Combined Ratio and Product Estimators in Stratified Random Sampling Joural of Moder Applied Saiical Meods Volume 9 Issue Aricle 8 --00 Effec of Measureme Errors o e Separae ad ombied Raio ad Produc Eimaors i Sraified Radom Samplig Housila P Sig Vikram Uiversiy Ujjai Idia

More information

Exponential Ratio-Product Type Estimators Under Second Order Approximation In Stratified Random Sampling

Exponential Ratio-Product Type Estimators Under Second Order Approximation In Stratified Random Sampling Rajes Sing Prayas Sarma Deparmen of Saisics Banaras Hindu Universiy aranasi-005 India Florenin Smarandace Universiy of New Mexico Gallup USA Exponenial Raio-Produc Type Esimaors Under Second Order Approximaion

More information

Modified Ratio and Product Estimators for Estimating Population Mean in Two-Phase Sampling

Modified Ratio and Product Estimators for Estimating Population Mean in Two-Phase Sampling America Joural of Operaioal esearch 06, 6(3): 6-68 DOI: 0.593/j.ajor.060603.0 Moifie aio a Prouc Esimaors for Esimaig Populaio Mea i Two-Phase Samplig Subhash Kumar Yaav, Sa Gupa, S. S. Mishra 3,, Alok

More information

A Generalized Class of Estimators for Finite Population Variance in Presence of Measurement Errors

A Generalized Class of Estimators for Finite Population Variance in Presence of Measurement Errors Joural of Moder Applied Statistical Methods Volume Issue Article 3 --03 A Geeralized Class of Estimators for Fiite Populatio Variace i Presece of Measuremet Errors Praas Sharma Baaras Hidu Uiversit, Varaasi,

More information

Inference of the Second Order Autoregressive. Model with Unit Roots

Inference of the Second Order Autoregressive. Model with Unit Roots Ieraioal Mahemaical Forum Vol. 6 0 o. 5 595-604 Iferece of he Secod Order Auoregressive Model wih Ui Roos Ahmed H. Youssef Professor of Applied Saisics ad Ecoomerics Isiue of Saisical Sudies ad Research

More information

Some Ratio and Product Estimators Using Known Value of Population Parameters

Some Ratio and Product Estimators Using Known Value of Population Parameters Rajes Sing Deparmen of Maemaics, SRM Universi Deli NCR, Sonepa- 9, India Sacin Malik Deparmen of Saisics, Banaras Hindu Universi Varanasi-, India Florenin Smarandace Deparmen of Maemaics, Universi of New

More information

Exponential Ratio-Product Type Estimators Under Second Order Approximation In Stratified Random Sampling

Exponential Ratio-Product Type Estimators Under Second Order Approximation In Stratified Random Sampling Exponenial Raio-Produc Type Eimaors Under Second Order Approximaion In Sraified Random Sampling Rajes Sing Prayas Sarma and Florenin Smarandace Deparmen of Saiics Banaras Hindu Universiy aranasi-005 India

More information

Numerical Solution of Parabolic Volterra Integro-Differential Equations via Backward-Euler Scheme

Numerical Solution of Parabolic Volterra Integro-Differential Equations via Backward-Euler Scheme America Joural of Compuaioal ad Applied Maemaics, (6): 77-8 DOI:.59/.acam.6. Numerical Soluio of Parabolic Volerra Iegro-Differeial Equaios via Bacward-Euler Sceme Ali Filiz Deparme of Maemaics, Ada Mederes

More information

Use of Auxiliary Information for Estimating Population Mean in Systematic Sampling under Non- Response

Use of Auxiliary Information for Estimating Population Mean in Systematic Sampling under Non- Response Maoj K. haudhar, Sachi Malik, Rajesh Sigh Departmet of Statistics, Baaras Hidu Uiversit Varaasi-005, Idia Floreti Smaradache Uiversit of New Mexico, Gallup, USA Use of Auxiliar Iformatio for Estimatig

More information

Method of Estimation in the Presence of Nonresponse and Measurement Errors Simultaneously

Method of Estimation in the Presence of Nonresponse and Measurement Errors Simultaneously Joural of Moder Applied Statistical Methods Volume 4 Issue Article 5--05 Method of Estimatio i the Presece of Norespose ad Measuremet Errors Simultaeousl Rajesh Sigh Sigh Baaras Hidu Uiversit, Varaasi,

More information

STK4080/9080 Survival and event history analysis

STK4080/9080 Survival and event history analysis STK48/98 Survival ad eve hisory aalysis Marigales i discree ime Cosider a sochasic process The process M is a marigale if Lecure 3: Marigales ad oher sochasic processes i discree ime (recap) where (formally

More information

Almost Unbiased Estimator for Estimating Population Mean Using Known Value of Some Population Parameter(s)

Almost Unbiased Estimator for Estimating Population Mean Using Known Value of Some Population Parameter(s) Almos Unbiased Esimaor for Esimaing Populaion Mean Using Known Value of Some Populaion Parameers Rajesh Singh Deparmen of Saisics, Banaras Hindu Universi U.P., India rsinghsa@ahoo.com Mukesh Kumar Deparmen

More information

Review Exercises for Chapter 9

Review Exercises for Chapter 9 0_090R.qd //0 : PM Page 88 88 CHAPTER 9 Ifiie Series I Eercises ad, wrie a epressio for he h erm of he sequece..,., 5, 0,,,, 0,... 7,... I Eercises, mach he sequece wih is graph. [The graphs are labeled

More information

Some Exponential Ratio-Product Type Estimators using information on Auxiliary Attributes under Second Order Approximation

Some Exponential Ratio-Product Type Estimators using information on Auxiliary Attributes under Second Order Approximation ; [Formerly kow as the Bulleti of Statistics & Ecoomics (ISSN 097-70)]; ISSN 0975-556X; Year: 0, Volume:, Issue Number: ; It. j. stat. eco.; opyright 0 by ESER Publicatios Some Expoetial Ratio-Product

More information

A Family of Efficient Estimator in Circular Systematic Sampling

A Family of Efficient Estimator in Circular Systematic Sampling olumbia Iteratioal Publishig Joural of dvaced omputig (0) Vol. o. pp. 6-68 doi:0.776/jac.0.00 Research rticle Famil of Efficiet Estimator i ircular Sstematic Samplig Hemat K. Verma ad Rajesh Sigh * Received

More information

Journal of Scientific Research Vol. 62, 2018 : Banaras Hindu University, Varanasi ISSN :

Journal of Scientific Research Vol. 62, 2018 : Banaras Hindu University, Varanasi ISSN : Joural of Scietific Research Vol. 6 8 : 3-34 Baaras Hidu Uiversity Varaasi ISS : 447-9483 Geeralized ad trasformed two phase samplig Ratio ad Product ype stimators for Populatio Mea Usig uiliary haracter

More information

A Family of Unbiased Estimators of Population Mean Using an Auxiliary Variable

A Family of Unbiased Estimators of Population Mean Using an Auxiliary Variable Advaces i Computatioal Scieces ad Techolog ISSN 0973-6107 Volume 10, Number 1 (017 pp. 19-137 Research Idia Publicatios http://www.ripublicatio.com A Famil of Ubiased Estimators of Populatio Mea Usig a

More information

Outline. simplest HMM (1) simple HMMs? simplest HMM (2) Parameter estimation for discrete hidden Markov models

Outline. simplest HMM (1) simple HMMs? simplest HMM (2) Parameter estimation for discrete hidden Markov models Oulie Parameer esimaio for discree idde Markov models Juko Murakami () ad Tomas Taylor (2). Vicoria Uiversiy of Welligo 2. Arizoa Sae Uiversiy Descripio of simple idde Markov models Maximum likeliood esimae

More information

Improved exponential estimator for population variance using two auxiliary variables

Improved exponential estimator for population variance using two auxiliary variables OCTOGON MATHEMATICAL MAGAZINE Vol. 7, No., October 009, pp 667-67 ISSN -5657, ISBN 97-973-55-5-0, www.hetfalu.ro/octogo 667 Improved expoetial estimator for populatio variace usig two auxiliar variables

More information

Comparisons Between RV, ARV and WRV

Comparisons Between RV, ARV and WRV Comparisos Bewee RV, ARV ad WRV Cao Gag,Guo Migyua School of Maageme ad Ecoomics, Tiaji Uiversiy, Tiaji,30007 Absrac: Realized Volailiy (RV) have bee widely used sice i was pu forward by Aderso ad Bollerslev

More information

Improvement Over General And Wider Class of Estimators Using Ranked Set Sampling

Improvement Over General And Wider Class of Estimators Using Ranked Set Sampling ITERATIOAL JOURAL OF SIETIFI & TEOLOG RESEAR VOLUME ISSUE 7 AUGUST ISS 77-866 Iprovee Over Geeral Ad ider lass of Esiaors Usi Raked Se Sapli V L Madoara iu Meha Raka Absrac: I his paper Iprovee over eeral

More information

Varanasi , India. Corresponding author

Varanasi , India. Corresponding author A Geeral Family of Estimators for Estimatig Populatio Mea i Systematic Samplig Usig Auxiliary Iformatio i the Presece of Missig Observatios Maoj K. Chaudhary, Sachi Malik, Jayat Sigh ad Rajesh Sigh Departmet

More information

The analysis of the method on the one variable function s limit Ke Wu

The analysis of the method on the one variable function s limit Ke Wu Ieraioal Coferece o Advaces i Mechaical Egieerig ad Idusrial Iformaics (AMEII 5) The aalysis of he mehod o he oe variable fucio s i Ke Wu Deparme of Mahemaics ad Saisics Zaozhuag Uiversiy Zaozhuag 776

More information

Comparison between Fourier and Corrected Fourier Series Methods

Comparison between Fourier and Corrected Fourier Series Methods Malaysia Joural of Mahemaical Scieces 7(): 73-8 (13) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES Joural homepage: hp://eispem.upm.edu.my/oural Compariso bewee Fourier ad Correced Fourier Series Mehods 1

More information

A General Family of Estimators for Estimating Population Variance Using Known Value of Some Population Parameter(s)

A General Family of Estimators for Estimating Population Variance Using Known Value of Some Population Parameter(s) Rajesh Sigh, Pakaj Chauha, Nirmala Sawa School of Statistics, DAVV, Idore (M.P.), Idia Floreti Smaradache Uiversity of New Meico, USA A Geeral Family of Estimators for Estimatig Populatio Variace Usig

More information

New Class of Estimators of Population Mean. DECISION SCIENCES INSTITUTE New Class of Estimators of Population Mean Utilizing Median of Study Variable

New Class of Estimators of Population Mean. DECISION SCIENCES INSTITUTE New Class of Estimators of Population Mean Utilizing Median of Study Variable New lass of Esiaors of Poulaio Mea DEISION SIENES INSTITUTE New lass of Esiaors of Poulaio Mea Uilizig Media of Sudy Variable S.K. Yadav Dr. RML Avadh Uiversiy drskysas@gail.co Diesh K. Shara Uiversiy

More information

ECE 570 Session 7 IC 752-E Computer Aided Engineering for Integrated Circuits. Transient analysis. Discuss time marching methods used in SPICE

ECE 570 Session 7 IC 752-E Computer Aided Engineering for Integrated Circuits. Transient analysis. Discuss time marching methods used in SPICE ECE 570 Sessio 7 IC 75-E Compuer Aided Egieerig for Iegraed Circuis Trasie aalysis Discuss ime marcig meods used i SPICE. Time marcig meods. Explici ad implici iegraio meods 3. Implici meods used i circui

More information

On the Validity of the Pairs Bootstrap for Lasso Estimators

On the Validity of the Pairs Bootstrap for Lasso Estimators O he Validiy of he Pairs Boosrap for Lasso Esimaors Lorezo Campoovo Uiversiy of S.Galle Ocober 2014 Absrac We sudy he validiy of he pairs boosrap for Lasso esimaors i liear regressio models wih radom covariaes

More information

S n. = n. Sum of first n terms of an A. P is

S n. = n. Sum of first n terms of an A. P is PROGREION I his secio we discuss hree impora series amely ) Arihmeic Progressio (A.P), ) Geomeric Progressio (G.P), ad 3) Harmoic Progressio (H.P) Which are very widely used i biological scieces ad humaiies.

More information

Chain ratio-to-regression estimators in two-phase sampling in the presence of non-response

Chain ratio-to-regression estimators in two-phase sampling in the presence of non-response ProbStat Forum, Volume 08, July 015, Pages 95 10 ISS 0974-335 ProbStat Forum is a e-joural. For details please visit www.probstat.org.i Chai ratio-to-regressio estimators i two-phase samplig i the presece

More information

Page 1. Before-After Control-Impact (BACI) Power Analysis For Several Related Populations. Richard A. Hinrichsen. March 3, 2010

Page 1. Before-After Control-Impact (BACI) Power Analysis For Several Related Populations. Richard A. Hinrichsen. March 3, 2010 Page Before-Afer Corol-Impac BACI Power Aalysis For Several Relaed Populaios Richard A. Hirichse March 3, Cavea: This eperimeal desig ool is for a idealized power aalysis buil upo several simplifyig assumpios

More information

David Randall. ( )e ikx. k = u x,t. u( x,t)e ikx dx L. x L /2. Recall that the proof of (1) and (2) involves use of the orthogonality condition.

David Randall. ( )e ikx. k = u x,t. u( x,t)e ikx dx L. x L /2. Recall that the proof of (1) and (2) involves use of the orthogonality condition. ! Revised April 21, 2010 1:27 P! 1 Fourier Series David Radall Assume ha u( x,) is real ad iegrable If he domai is periodic, wih period L, we ca express u( x,) exacly by a Fourier series expasio: ( ) =

More information

Estimation of Population Mean Using Co-Efficient of Variation and Median of an Auxiliary Variable

Estimation of Population Mean Using Co-Efficient of Variation and Median of an Auxiliary Variable Iteratioal Joural of Probability ad Statistics 01, 1(4: 111-118 DOI: 10.593/j.ijps.010104.04 Estimatio of Populatio Mea Usig Co-Efficiet of Variatio ad Media of a Auxiliary Variable J. Subramai *, G. Kumarapadiya

More information

Modified Ratio Estimators Using Known Median and Co-Efficent of Kurtosis

Modified Ratio Estimators Using Known Median and Co-Efficent of Kurtosis America Joural of Mathematics ad Statistics 01, (4): 95-100 DOI: 10.593/j.ajms.01004.05 Modified Ratio s Usig Kow Media ad Co-Efficet of Kurtosis J.Subramai *, G.Kumarapadiya Departmet of Statistics, Podicherry

More information

12 th Mathematics Objective Test Solutions

12 th Mathematics Objective Test Solutions Maemaics Objecive Tes Soluios Differeiaio & H.O.D A oes idividual is saisfied wi imself as muc as oer are saisfied wi im. Name: Roll. No. Bac [Moda/Tuesda] Maimum Time: 90 Miues [Eac rig aswer carries

More information

Estimation of the Population Mean in Presence of Non-Response

Estimation of the Population Mean in Presence of Non-Response Commuicatios of the Korea Statistical Society 0, Vol. 8, No. 4, 537 548 DOI: 0.535/CKSS.0.8.4.537 Estimatio of the Populatio Mea i Presece of No-Respose Suil Kumar,a, Sadeep Bhougal b a Departmet of Statistics,

More information

y y y

y y y Esimaors Valus of α Valus of α PRE( i) s 0 0 00 0 09.469 5 49.686 8 5.89 MSE( 9)mi 6.98-0.8870 854.549 THE EFFIIET USE OF SUPPLEMETARY IFORMATIO I FIITE POPULATIO SAMPLIG Rajs Sig Dparm of Saisics, BHU,

More information

Compact Finite Difference Schemes for Solving a Class of Weakly- Singular Partial Integro-differential Equations

Compact Finite Difference Schemes for Solving a Class of Weakly- Singular Partial Integro-differential Equations Ma. Sci. Le. Vol. No. 53-0 (0 Maemaical Scieces Leers A Ieraioal Joural @ 0 NSP Naural Scieces Publisig Cor. Compac Fiie Differece Scemes for Solvig a Class of Weakly- Sigular Parial Iegro-differeial Equaios

More information

ALMOST UNBIASED RATIO AND PRODUCT TYPE EXPONENTIAL ESTIMATORS

ALMOST UNBIASED RATIO AND PRODUCT TYPE EXPONENTIAL ESTIMATORS STATISTIS IN TANSITION-new series, December 0 537 STATISTIS IN TANSITION-new series, December 0 Vol. 3, No. 3, pp. 537 550 ALMOST UNBIASED ATIO AND ODUT TYE EXONENTIAL ESTIMATOS ohini Yadav, Lakshmi N.

More information

BEST LINEAR FORECASTS VS. BEST POSSIBLE FORECASTS

BEST LINEAR FORECASTS VS. BEST POSSIBLE FORECASTS BEST LINEAR FORECASTS VS. BEST POSSIBLE FORECASTS Opimal ear Forecasig Alhough we have o meioed hem explicily so far i he course, here are geeral saisical priciples for derivig he bes liear forecas, ad

More information

Advection! Discontinuous! solutions shocks! Shock Speed! ! f. !t + U!f. ! t! x. dx dt = U; t = 0

Advection! Discontinuous! solutions shocks! Shock Speed! ! f. !t + U!f. ! t! x. dx dt = U; t = 0 p://www.d.edu/~gryggva/cfd-course/ Advecio Discoiuous soluios socks Gréar Tryggvaso Sprig Discoiuous Soluios Cosider e liear Advecio Equaio + U = Te aalyic soluio is obaied by caracerisics d d = U; d d

More information

Prakash Chandra Rautaray 1, Ellipse 2

Prakash Chandra Rautaray 1, Ellipse 2 Prakash Chadra Rauara, Ellise / Ieraioal Joural of Egieerig Research ad Alicaios (IJERA) ISSN: 48-96 www.ijera.com Vol. 3, Issue, Jauar -Februar 3,.36-337 Degree Of Aroimaio Of Fucios B Modified Parial

More information

10.3 Autocorrelation Function of Ergodic RP 10.4 Power Spectral Density of Ergodic RP 10.5 Normal RP (Gaussian RP)

10.3 Autocorrelation Function of Ergodic RP 10.4 Power Spectral Density of Ergodic RP 10.5 Normal RP (Gaussian RP) ENGG450 Probabiliy ad Saisics for Egieers Iroducio 3 Probabiliy 4 Probabiliy disribuios 5 Probabiliy Desiies Orgaizaio ad descripio of daa 6 Samplig disribuios 7 Ifereces cocerig a mea 8 Comparig wo reames

More information

New Ratio Estimators Using Correlation Coefficient

New Ratio Estimators Using Correlation Coefficient New atio Estimators Usig Correlatio Coefficiet Cem Kadilar ad Hula Cigi Hacettepe Uiversit, Departmet of tatistics, Betepe, 06800, Akara, Turke. e-mails : kadilar@hacettepe.edu.tr ; hcigi@hacettepe.edu.tr

More information

ANALYSIS OF THE CHAOS DYNAMICS IN (X n,x n+1) PLANE

ANALYSIS OF THE CHAOS DYNAMICS IN (X n,x n+1) PLANE ANALYSIS OF THE CHAOS DYNAMICS IN (X,X ) PLANE Soegiao Soelisioo, The Houw Liog Badug Isiue of Techolog (ITB) Idoesia soegiao@sude.fi.ib.ac.id Absrac I he las decade, sudies of chaoic ssem are more ofe

More information

F D D D D F. smoothed value of the data including Y t the most recent data.

F D D D D F. smoothed value of the data including Y t the most recent data. Module 2 Forecasig 1. Wha is forecasig? Forecasig is defied as esimaig he fuure value ha a parameer will ake. Mos scieific forecasig mehods forecas he fuure value usig pas daa. I Operaios Maageme forecasig

More information

An interesting result about subset sums. Nitu Kitchloo. Lior Pachter. November 27, Abstract

An interesting result about subset sums. Nitu Kitchloo. Lior Pachter. November 27, Abstract A ieresig resul abou subse sums Niu Kichloo Lior Pacher November 27, 1993 Absrac We cosider he problem of deermiig he umber of subses B f1; 2; : : :; g such ha P b2b b k mod, where k is a residue class

More information

A Generalized Cost Malmquist Index to the Productivities of Units with Negative Data in DEA

A Generalized Cost Malmquist Index to the Productivities of Units with Negative Data in DEA Proceedigs of he 202 Ieraioal Coferece o Idusrial Egieerig ad Operaios Maageme Isabul, urey, July 3 6, 202 A eeralized Cos Malmquis Ide o he Produciviies of Uis wih Negaive Daa i DEA Shabam Razavya Deparme

More information

Additional Exercises for Chapter What is the slope-intercept form of the equation of the line given by 3x + 5y + 2 = 0?

Additional Exercises for Chapter What is the slope-intercept form of the equation of the line given by 3x + 5y + 2 = 0? ddiional Eercises for Caper 5 bou Lines, Slopes, and Tangen Lines 39. Find an equaion for e line roug e wo poins (, 7) and (5, ). 4. Wa is e slope-inercep form of e equaion of e line given by 3 + 5y +

More information

Ideal Amplifier/Attenuator. Memoryless. where k is some real constant. Integrator. System with memory

Ideal Amplifier/Attenuator. Memoryless. where k is some real constant. Integrator. System with memory Liear Time-Ivaria Sysems (LTI Sysems) Oulie Basic Sysem Properies Memoryless ad sysems wih memory (saic or dyamic) Causal ad o-causal sysems (Causaliy) Liear ad o-liear sysems (Lieariy) Sable ad o-sable

More information

1. Solve by the method of undetermined coefficients and by the method of variation of parameters. (4)

1. Solve by the method of undetermined coefficients and by the method of variation of parameters. (4) 7 Differeial equaios Review Solve by he mehod of udeermied coefficies ad by he mehod of variaio of parameers (4) y y = si Soluio; we firs solve he homogeeous equaio (4) y y = 4 The correspodig characerisic

More information

Additional Tables of Simulation Results

Additional Tables of Simulation Results Saisica Siica: Suppleme REGULARIZING LASSO: A CONSISTENT VARIABLE SELECTION METHOD Quefeg Li ad Ju Shao Uiversiy of Wiscosi, Madiso, Eas Chia Normal Uiversiy ad Uiversiy of Wiscosi, Madiso Supplemeary

More information

Samuel Sindayigaya 1, Nyongesa L. Kennedy 2, Adu A.M. Wasike 3

Samuel Sindayigaya 1, Nyongesa L. Kennedy 2, Adu A.M. Wasike 3 Ieraioal Joural of Saisics ad Aalysis. ISSN 48-9959 Volume 6, Number (6, pp. -8 Research Idia Publicaios hp://www.ripublicaio.com The Populaio Mea ad is Variace i he Presece of Geocide for a Simple Birh-Deah-

More information

FIXED FUZZY POINT THEOREMS IN FUZZY METRIC SPACE

FIXED FUZZY POINT THEOREMS IN FUZZY METRIC SPACE Mohia & Samaa, Vol. 1, No. II, December, 016, pp 34-49. ORIGINAL RESEARCH ARTICLE OPEN ACCESS FIED FUZZY POINT THEOREMS IN FUZZY METRIC SPACE 1 Mohia S. *, Samaa T. K. 1 Deparme of Mahemaics, Sudhir Memorial

More information

Calculus Limits. Limit of a function.. 1. One-Sided Limits...1. Infinite limits 2. Vertical Asymptotes...3. Calculating Limits Using the Limit Laws.

Calculus Limits. Limit of a function.. 1. One-Sided Limits...1. Infinite limits 2. Vertical Asymptotes...3. Calculating Limits Using the Limit Laws. Limi of a fucio.. Oe-Sided..... Ifiie limis Verical Asympoes... Calculaig Usig he Limi Laws.5 The Squeeze Theorem.6 The Precise Defiiio of a Limi......7 Coiuiy.8 Iermediae Value Theorem..9 Refereces..

More information

SUMMATION OF INFINITE SERIES REVISITED

SUMMATION OF INFINITE SERIES REVISITED SUMMATION OF INFINITE SERIES REVISITED I several aricles over he las decade o his web page we have show how o sum cerai iiie series icludig he geomeric series. We wa here o eed his discussio o he geeral

More information

Big O Notation for Time Complexity of Algorithms

Big O Notation for Time Complexity of Algorithms BRONX COMMUNITY COLLEGE of he Ciy Uiversiy of New York DEPARTMENT OF MATHEMATICS AND COMPUTER SCIENCE CSI 33 Secio E01 Hadou 1 Fall 2014 Sepember 3, 2014 Big O Noaio for Time Complexiy of Algorihms Time

More information

Stationarity and Unit Root tests

Stationarity and Unit Root tests Saioari ad Ui Roo ess Saioari ad Ui Roo ess. Saioar ad Nosaioar Series. Sprios Regressio 3. Ui Roo ad Nosaioari 4. Ui Roo ess Dicke-Fller es Agmeed Dicke-Fller es KPSS es Phillips-Perro Tes 5. Resolvig

More information

N! AND THE GAMMA FUNCTION

N! AND THE GAMMA FUNCTION N! AND THE GAMMA FUNCTION Cosider he produc of he firs posiive iegers- 3 4 5 6 (-) =! Oe calls his produc he facorial ad has ha produc of he firs five iegers equals 5!=0. Direcly relaed o he discree! fucio

More information

CLOSED FORM EVALUATION OF RESTRICTED SUMS CONTAINING SQUARES OF FIBONOMIAL COEFFICIENTS

CLOSED FORM EVALUATION OF RESTRICTED SUMS CONTAINING SQUARES OF FIBONOMIAL COEFFICIENTS PB Sci Bull, Series A, Vol 78, Iss 4, 2016 ISSN 1223-7027 CLOSED FORM EVALATION OF RESTRICTED SMS CONTAINING SQARES OF FIBONOMIAL COEFFICIENTS Emrah Kılıc 1, Helmu Prodiger 2 We give a sysemaic approach

More information

Some Properties of Semi-E-Convex Function and Semi-E-Convex Programming*

Some Properties of Semi-E-Convex Function and Semi-E-Convex Programming* The Eighh Ieraioal Symposium o Operaios esearch ad Is Applicaios (ISOA 9) Zhagjiajie Chia Sepember 2 22 29 Copyrigh 29 OSC & APOC pp 33 39 Some Properies of Semi-E-Covex Fucio ad Semi-E-Covex Programmig*

More information

Chapter 2: Time-Domain Representations of Linear Time-Invariant Systems. Chih-Wei Liu

Chapter 2: Time-Domain Representations of Linear Time-Invariant Systems. Chih-Wei Liu Caper : Time-Domai Represeaios of Liear Time-Ivaria Sysems Ci-Wei Liu Oulie Iroucio Te Covoluio Sum Covoluio Sum Evaluaio Proceure Te Covoluio Iegral Covoluio Iegral Evaluaio Proceure Iercoecios of LTI

More information

1 Notes on Little s Law (l = λw)

1 Notes on Little s Law (l = λw) Copyrigh c 26 by Karl Sigma Noes o Lile s Law (l λw) We cosider here a famous ad very useful law i queueig heory called Lile s Law, also kow as l λw, which assers ha he ime average umber of cusomers i

More information

Some Newton s Type Inequalities for Geometrically Relative Convex Functions ABSTRACT. 1. Introduction

Some Newton s Type Inequalities for Geometrically Relative Convex Functions ABSTRACT. 1. Introduction Malaysia Joural of Mahemaical Scieces 9(): 49-5 (5) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES Joural homepage: hp://eispem.upm.edu.my/joural Some Newo s Type Ieualiies for Geomerically Relaive Covex Fucios

More information

OLS bias for econometric models with errors-in-variables. The Lucas-critique Supplementary note to Lecture 17

OLS bias for econometric models with errors-in-variables. The Lucas-critique Supplementary note to Lecture 17 OLS bias for ecoomeric models wih errors-i-variables. The Lucas-criique Supplemeary oe o Lecure 7 RNy May 6, 03 Properies of OLS i RE models I Lecure 7 we discussed he followig example of a raioal expecaios

More information

Effect of Heat Exchangers Connection on Effectiveness

Effect of Heat Exchangers Connection on Effectiveness Joural of Roboics ad Mechaical Egieerig Research Effec of Hea Exchagers oecio o Effeciveess Voio W Koiaho Maru J Lampie ad M El Haj Assad * Aalo Uiversiy School of Sciece ad echology P O Box 00 FIN-00076

More information

On the convergence, consistence and stability of a standard finite difference scheme

On the convergence, consistence and stability of a standard finite difference scheme AMERICAN JOURNAL OF SCIENTIFIC AND INDUSTRIAL RESEARCH 2, Sciece Huβ, ttp://www.sciub.org/ajsir ISSN: 253-649X, doi:.525/ajsir.2.2.2.74.78 O te covergece, cosistece ad stabilit of a stadard fiite differece

More information

Improved Class of Ratio -Cum- Product Estimators of Finite Population Mean in two Phase Sampling

Improved Class of Ratio -Cum- Product Estimators of Finite Population Mean in two Phase Sampling Global Joural of Sciece Frotier Research: F Mathematics ad Decisio Scieces Volume 4 Issue 2 Versio.0 Year 204 Type : Double Blid Peer Reviewed Iteratioal Research Joural Publisher: Global Jourals Ic. (USA

More information

BRIDGE ESTIMATOR AS AN ALTERNATIVE TO DICKEY- PANTULA UNIT ROOT TEST

BRIDGE ESTIMATOR AS AN ALTERNATIVE TO DICKEY- PANTULA UNIT ROOT TEST The 0 h Ieraioal Days of Saisics ad Ecoomics Prague Sepember 8-0 06 BRIDGE ESTIMATOR AS AN ALTERNATIVE TO DICKEY- PANTULA UNIT ROOT TEST Hüseyi Güler Yeliz Yalҫi Çiğdem Koşar Absrac Ecoomic series may

More information

Developing Efficient Ratio and Product Type Exponential Estimators of Population Mean under Two Phase Sampling for Stratification

Developing Efficient Ratio and Product Type Exponential Estimators of Population Mean under Two Phase Sampling for Stratification America Joural of Operatioal Researc 05 5: -8 DOI: 0.593/j.ajor.05050.0 Developig Efficiet Ratio ad Product Type Epoetial Eimators of Populatio Mea uder Two Pase Samplig for Stratificatio Subas Kumar adav

More information

An Efficient Method to Reduce the Numerical Dispersion in the HIE-FDTD Scheme

An Efficient Method to Reduce the Numerical Dispersion in the HIE-FDTD Scheme Wireless Egieerig ad Techolog, 0,, 30-36 doi:0.436/we.0.005 Published Olie Jauar 0 (hp://www.scirp.org/joural/we) A Efficie Mehod o Reduce he umerical Dispersio i he IE- Scheme Jua Che, Aue Zhag School

More information

FOR 496 / 796 Introduction to Dendrochronology. Lab exercise #4: Tree-ring Reconstruction of Precipitation

FOR 496 / 796 Introduction to Dendrochronology. Lab exercise #4: Tree-ring Reconstruction of Precipitation FOR 496 Iroducio o Dedrochroology Fall 004 FOR 496 / 796 Iroducio o Dedrochroology Lab exercise #4: Tree-rig Recosrucio of Precipiaio Adaped from a exercise developed by M.K. Cleavelad ad David W. Sahle,

More information

Lecture 9: Polynomial Approximations

Lecture 9: Polynomial Approximations CS 70: Complexiy Theory /6/009 Lecure 9: Polyomial Approximaios Isrucor: Dieer va Melkebeek Scribe: Phil Rydzewski & Piramaayagam Arumuga Naiar Las ime, we proved ha o cosa deph circui ca evaluae he pariy

More information

Calculus BC 2015 Scoring Guidelines

Calculus BC 2015 Scoring Guidelines AP Calculus BC 5 Scorig Guidelies 5 The College Board. College Board, Advaced Placeme Program, AP, AP Ceral, ad he acor logo are regisered rademarks of he College Board. AP Ceral is he official olie home

More information

Optimization of Rotating Machines Vibrations Limits by the Spring - Mass System Analysis

Optimization of Rotating Machines Vibrations Limits by the Spring - Mass System Analysis Joural of aerials Sciece ad Egieerig B 5 (7-8 (5 - doi: 765/6-6/57-8 D DAVID PUBLISHING Opimizaio of Roaig achies Vibraios Limis by he Sprig - ass Sysem Aalysis BENDJAIA Belacem sila, Algéria Absrac: The

More information

A note on deviation inequalities on {0, 1} n. by Julio Bernués*

A note on deviation inequalities on {0, 1} n. by Julio Bernués* A oe o deviaio iequaliies o {0, 1}. by Julio Berués* Deparameo de Maemáicas. Faculad de Ciecias Uiversidad de Zaragoza 50009-Zaragoza (Spai) I. Iroducio. Le f: (Ω, Σ, ) IR be a radom variable. Roughly

More information

Extremal graph theory II: K t and K t,t

Extremal graph theory II: K t and K t,t Exremal graph heory II: K ad K, Lecure Graph Theory 06 EPFL Frak de Zeeuw I his lecure, we geeralize he wo mai heorems from he las lecure, from riagles K 3 o complee graphs K, ad from squares K, o complee

More information

UNIT 1: ANALYTICAL METHODS FOR ENGINEERS

UNIT 1: ANALYTICAL METHODS FOR ENGINEERS UNIT : ANALYTICAL METHODS FOR ENGINEERS Ui code: A// QCF Level: Credi vale: OUTCOME TUTORIAL SERIES Ui coe Be able o aalyse ad model egieerig siaios ad solve problems sig algebraic mehods Algebraic mehods:

More information

Extended Laguerre Polynomials

Extended Laguerre Polynomials I J Coemp Mah Scieces, Vol 7, 1, o, 189 194 Exeded Laguerre Polyomials Ada Kha Naioal College of Busiess Admiisraio ad Ecoomics Gulberg-III, Lahore, Pakisa adakhaariq@gmailcom G M Habibullah Naioal College

More information

A Bayesian Approach for Detecting Outliers in ARMA Time Series

A Bayesian Approach for Detecting Outliers in ARMA Time Series WSEAS RASACS o MAEMAICS Guochao Zhag Qigmig Gui A Bayesia Approach for Deecig Ouliers i ARMA ime Series GUOC ZAG Isiue of Sciece Iformaio Egieerig Uiversiy 45 Zhegzhou CIA 94587@qqcom QIGMIG GUI Isiue

More information

State and Parameter Estimation of The Lorenz System In Existence of Colored Noise

State and Parameter Estimation of The Lorenz System In Existence of Colored Noise Sae ad Parameer Esimaio of he Lorez Sysem I Eisece of Colored Noise Mozhga Mombeii a Hamid Khaloozadeh b a Elecrical Corol ad Sysem Egieerig Researcher of Isiue for Research i Fudameal Scieces (IPM ehra

More information

Order Determination for Multivariate Autoregressive Processes Using Resampling Methods

Order Determination for Multivariate Autoregressive Processes Using Resampling Methods joural of mulivariae aalysis 57, 175190 (1996) aricle o. 0028 Order Deermiaio for Mulivariae Auoregressive Processes Usig Resamplig Mehods Chaghua Che ad Richard A. Davis* Colorado Sae Uiversiy ad Peer

More information

Procedia - Social and Behavioral Sciences 230 ( 2016 ) Joint Probability Distribution and the Minimum of a Set of Normalized Random Variables

Procedia - Social and Behavioral Sciences 230 ( 2016 ) Joint Probability Distribution and the Minimum of a Set of Normalized Random Variables Available olie a wwwsciecedireccom ScieceDirec Procedia - Social ad Behavioral Scieces 30 ( 016 ) 35 39 3 rd Ieraioal Coferece o New Challeges i Maageme ad Orgaizaio: Orgaizaio ad Leadership, May 016,

More information

REVISTA INVESTIGACION OPERACIONAL VOL. 36, NO. 3, , 2015

REVISTA INVESTIGACION OPERACIONAL VOL. 36, NO. 3, , 2015 REVITA INVETIGAION OPERAIONAL VOL. 36 NO. 3 68-79 05 A GENERAL PROEDURE FOR ETIMATING THE MEAN OF A ENITIVE VARIABLE UING AUXILIARY INFORMATION Taveer A. Tarra* ad Housila P. ih** * Deparme of Mahemaics

More information

Journal of Applied Science and Agriculture

Journal of Applied Science and Agriculture Joural of Applied Sciece ad Ariculure 9(4) April 4 Paes: 855-864 AENSI Jourals Joural of Applied Sciece ad Ariculure ISSN 86-9 Joural ome pae: www.aesiweb.com/jasa/ide.ml Aalyical Approimae Soluios of

More information

th m m m m central moment : E[( X X) ] ( X X) ( x X) f ( x)

th m m m m central moment : E[( X X) ] ( X X) ( x X) f ( x) 1 Trasform Techiques h m m m m mome : E[ ] x f ( x) dx h m m m m ceral mome : E[( ) ] ( ) ( x) f ( x) dx A coveie wa of fidig he momes of a radom variable is he mome geeraig fucio (MGF). Oher rasform echiques

More information

Local Influence Diagnostics of Replicated Data with Measurement Errors

Local Influence Diagnostics of Replicated Data with Measurement Errors ISSN 76-7659 Eglad UK Joural of Iformaio ad Compuig Sciece Vol. No. 8 pp.7-8 Local Ifluece Diagosics of Replicaed Daa wih Measureme Errors Jigig Lu Hairog Li Chuzheg Cao School of Mahemaics ad Saisics

More information

Homotopy Analysis Method for Solving Fractional Sturm-Liouville Problems

Homotopy Analysis Method for Solving Fractional Sturm-Liouville Problems Ausralia Joural of Basic ad Applied Scieces, 4(1): 518-57, 1 ISSN 1991-8178 Homoopy Aalysis Mehod for Solvig Fracioal Surm-Liouville Problems 1 A Neamay, R Darzi, A Dabbaghia 1 Deparme of Mahemaics, Uiversiy

More information

9. Point mode plotting with more than two images 2 hours

9. Point mode plotting with more than two images 2 hours Lecure 9 - - // Cocep Hell/feiffer Februar 9. oi mode ploig wih more ha wo images hours aim: iersecio of more ha wo ras wih orieaed images Theor: Applicaio co lieari equaio 9.. Spaial Resecio ad Iersecio

More information

B. Maddah INDE 504 Simulation 09/02/17

B. Maddah INDE 504 Simulation 09/02/17 B. Maddah INDE 54 Simulaio 9/2/7 Queueig Primer Wha is a queueig sysem? A queueig sysem cosiss of servers (resources) ha provide service o cusomers (eiies). A Cusomer requesig service will sar service

More information

EFFICIENT CLASSES OF RATIO-TYPE ESTIMATORS OF POPULATION MEAN UNDER STRATIFIED MEDIAN RANKED SET SAMPLING

EFFICIENT CLASSES OF RATIO-TYPE ESTIMATORS OF POPULATION MEAN UNDER STRATIFIED MEDIAN RANKED SET SAMPLING Pak. J. Sais. 016 Vol. 3(6) 475-496 EFFICIENT CASSES OF RATIO-TYPE ESTIMATORS OF POPUATION MEAN UNDER STRATIFIED MEDIAN RANKED SET SAMPING akkar Kan 1 Javid Sabbir and Ce Kadilar 3 1 Higer Eduacaion Deparen

More information

ODEs II, Supplement to Lectures 6 & 7: The Jordan Normal Form: Solving Autonomous, Homogeneous Linear Systems. April 2, 2003

ODEs II, Supplement to Lectures 6 & 7: The Jordan Normal Form: Solving Autonomous, Homogeneous Linear Systems. April 2, 2003 ODEs II, Suppleme o Lecures 6 & 7: The Jorda Normal Form: Solvig Auoomous, Homogeeous Liear Sysems April 2, 23 I his oe, we describe he Jorda ormal form of a marix ad use i o solve a geeral homogeeous

More information

REVISTA INVESTIGACION OPERACIONAL VOL. 35, NO. 1, 49-57, 2014

REVISTA INVESTIGACION OPERACIONAL VOL. 35, NO. 1, 49-57, 2014 EVISTA IVESTIGAIO OPEAIOAL VOL. 35, O., 9-57, 0 O A IMPOVED ATIO TYPE ESTIMATO OF FIITE POPULATIO MEA I SAMPLE SUVEYS A K P Swai Former Professor of Statistics, Utkal Uiversit, Bhubaeswar-7500, Idia ABSTAT

More information

A Two-Level Quantum Analysis of ERP Data for Mock-Interrogation Trials. Michael Schillaci Jennifer Vendemia Robert Buzan Eric Green

A Two-Level Quantum Analysis of ERP Data for Mock-Interrogation Trials. Michael Schillaci Jennifer Vendemia Robert Buzan Eric Green A Two-Level Quaum Aalysis of ERP Daa for Mock-Ierrogaio Trials Michael Schillaci Jeifer Vedemia Rober Buza Eric Gree Oulie Experimeal Paradigm 4 Low Workload; Sigle Sessio; 39 8 High Workload; Muliple

More information

Conditional Probability and Conditional Expectation

Conditional Probability and Conditional Expectation Hadou #8 for B902308 prig 2002 lecure dae: 3/06/2002 Codiioal Probabiliy ad Codiioal Epecaio uppose X ad Y are wo radom variables The codiioal probabiliy of Y y give X is } { }, { } { X P X y Y P X y Y

More information

Electrical Engineering Department Network Lab.

Electrical Engineering Department Network Lab. Par:- Elecrical Egieerig Deparme Nework Lab. Deermiaio of differe parameers of -por eworks ad verificaio of heir ierrelaio ships. Objecive: - To deermie Y, ad ABD parameers of sigle ad cascaded wo Por

More information

International journal of Engineering Research-Online A Peer Reviewed International Journal Articles available online

International journal of Engineering Research-Online A Peer Reviewed International Journal Articles available online Ieraioal joural of Egieerig Research-Olie A Peer Reviewed Ieraioal Joural Aricles available olie hp://www.ijoer.i Vol.., Issue.., 3 RESEARCH ARTICLE INTEGRAL SOLUTION OF 3 G.AKILA, M.A.GOPALAN, S.VIDHYALAKSHMI

More information

Improved Estimation of Rare Sensitive Attribute in a Stratified Sampling Using Poisson Distribution

Improved Estimation of Rare Sensitive Attribute in a Stratified Sampling Using Poisson Distribution Ope Joural of Statistics, 06, 6, 85-95 Publised Olie February 06 i SciRes ttp://wwwscirporg/joural/ojs ttp://dxdoiorg/0436/ojs0660 Improved Estimatio of Rare Sesitive ttribute i a Stratified Samplig Usig

More information

(1) f ( Ω) Keywords: adjoint problem, a posteriori error estimation, global norm of error.

(1) f ( Ω) Keywords: adjoint problem, a posteriori error estimation, global norm of error. O a poseriori esimaio of umerical global error orms usig adjoi equaio A.K. Aleseev a ad I. M. Navo b a Deparme of Aerodyamics ad Hea Trasfer, RSC ENERGIA, Korolev, Moscow Regio, 4070, Russia Federaio b

More information

Using Linnik's Identity to Approximate the Prime Counting Function with the Logarithmic Integral

Using Linnik's Identity to Approximate the Prime Counting Function with the Logarithmic Integral Usig Lii's Ideiy o Approimae he Prime Couig Fucio wih he Logarihmic Iegral Naha McKezie /26/2 aha@icecreambreafas.com Summary:This paper will show ha summig Lii's ideiy from 2 o ad arragig erms i a cerai

More information