Proportional Intensity Model considering Imperfect Repair for Repairable Systems

Size: px
Start display at page:

Download "Proportional Intensity Model considering Imperfect Repair for Repairable Systems"

Transcription

1 Iteratoal Joural of Performablty Egeerg Vol. 9, No. 2, March 203, pp RAMS Cosultats Prted Ida Proportoal Itesty Model cosderg Imperfect Repar for Reparable Systems YUAN FUQING * ad UDAY KUMAR Dvso of Operato ad Mateace Luleå Uversty of Techology, SE-97 87Lulea, SWEDEN (Receved o February 25, 202, revsed o Jauary 07, 203) Abstract: The Proportoal Itesty Model (PIM) exteds the classcal Proportoal Hazard Model (PHM) order to deal wth reparable systems. Ths paper develops a more geeral PIM model whch uses the mperfect model as basele fucto. By usg the mperfect model, the effectveess of repar has bee take to accout, wthout assumg a as-bad-as-old or a as-good-as-ew scheme. Moreover, the effectveess of other factors, such as the evrometal codtos ad the repar hstory, s cosdered as covarat ths PIM. I order to solve the large umber parameters estmato problem, a Bayesa ferece method s proposed. The Markov Cha Mote Carlo (MCMC) method s used to compute the posteror dstrbuto for the Bayesa method. The Bayesa Iformato Crtero (BIC) s employed to perform model selecto, amely, selectg the basele fucto ad remove the usace factors ths paper. I the fal, a umercal example s provded to demostrate the proposed model ad method. Keywords: Proportoal testy model (PIM), mperfect repar model, testy fucto, Markov Cha Mote Carlo (MCMC) method, model selecto.. Itroducto A reparable system ca be defed as a system whch s cotuous operato, ad whch s repared, but ot replaced, after each falure []. Itesve research has bee performed to address the problem of determg the relablty characterstcs of reparable systems, usg models based o the Homogeeous Posso Process (HPP), the No-Homogeeous Posso Process (NHPP), ad the mperfect repar model etc. Such models have bee prove successful egeerg. However, the weakess of such models s also crtczed by some researchers. As Ascher ad Fegold have metoed, most probablstc models the feld of relablty have bee smplfed hghly ad are based o urealstc assumptos. Most models cosder oly oe varable, amely the operatg tme. However, some stuatos, the operatg tme s ot the oly effectve factor fluecg relablty, some factors such as the evromet, repar hstory, load etc., wll also affect relablty greatly [2]. The Proportoal Hazard Model (PHM) s oe mportat model whch ca take the above-metoed factors to accout. The PHM was tally developed for the medcal dustry [3]. Ths model comprses two parts. The frst part s called the parametrc model or basele fucto, where the expoetal dstrbuto or the Webull dstrbuto ca be used. The secod part s called the covarat part. Ths part accommodates all the covarates, such as the evrometal factors, the repar hstory factors, ad so o. Kumar has carred out a thorough survey o the PHM [4, 5]. However, the PHM s sutable for o-reparable systems. Whe oe replace the basele fucto wth a testy fucto, the PHM s exteded to the Proportoal Itesty Model (PIM), by whch the problems of reparable systems ca be addressed [6]. *Correspodg author s emal: yua.fuqg@ltu.se 63

2 64 Yua Fuqg ad Uday Kumar For reparable system, Guo ad Love have developed a seres of PIMs [7, 8]. These models assume that the system udergoes Prevetve Mateace (PM) ad Correctve Operato (CO). After each PM acto, the system s assumed to be restored to a asgood-as-ew state. Hece the system each PM perods ca be cosdered as a ew detcal system. Ths assumpto facltates parameter estmato for covarates. Based o ths assumpto, oe ca use the partal lkelhood method to estmate the covarat parameters, regardless of the basele fucto [9]. Ths s oe of the sgfcat characterstcs of the PHM. However, whe o detcal systems are observed, ths parameter estmate method s ot feasble. I state-of-the-art applcatos, some NHPP models are usually used as the testy fucto PIM [7, 8]. The NHPP assumes that, after repar, the system s restored to a same-as-old state. Guo et al. argue that ths assumpto s rarely satsfed practce [0]. I the preset paper, we employ the mperfect repar model stead of the NHPP model as the basele fucto. I our paper, we assume that the operatg codtos are varat betwee each repar ad that o PM s carred out o the system. As o detcal systems are observed, the partal lkelhood estmate method caot be appled to ths case. We propose a Bayesa method to perform parameter estmato. I the Bayesa method, a MCMC method based o slce samplg s used to approxmate the posteror dstrbuto. I the remag of ths paper, Secto 2 dscusses the model developmet corporatg mperfect model to PIM. Secto 3 dscusses the parameter estmate for the developed model. Secto 4 presets a umercal example. Secto 5 presets the cocluso ad dscusses the lmtato of ths proposed model. Notato V q x λ 0 λ z F R f t α L Vrtual age at falure Repar factor Iter-arrval tme betwee th ad - th falure Itesty fucto wthout covarate Itesty fucto of PIM model Covarat such as repar hstory, repar hstory Coeffcet of covarat Falure probablty Relablty Probablty desty fucto (PDF) The th Falure tme Scale parameter power law model Shape parameter power law model Lkelhood fucto D Observed falure data G, ) Gamma dstrbuto wth parameter k k ( 2 U (...) Uform dstrbuto k ad k 2

3 Proportoal Itesty Model cosderg Imperfect Repar for Reparable Systems 65 N (...) Normal dstrbuto (...) k π Dstrbuto Bayesa ferece PIM PHM PM CO HPP NHPP MCMC BIC OPSK HOILQ SCSK STEMP ENDUS Number of parameters BIC Proportoal Itesty Model Proportoal Hazard Model Prevetve Mateace Correctve Operato Homogeeous Posso Process No-Homogeeous Posso Process Markov Cha Mote Carlo Bayesa Iformato Crtero operator skll hydraulc ol qualty mateace crew skll hydraulc system temperature evrometal codtos 2. Imperfect Repar Model wth Covarates 2. Vrtual Age Model It s assumed that the system s rejuveated after each repar. The effectveess of each repar s represeted by a reducto of the expereced age. Such mperfect repar models are called vrtual age models state-of-the-art research. The Kjma I ad Kjma II models are two mportat represetatves of such models []. The Kjma I model s descrbed as: V = V + qx () where x deotes the ter-arrval tme betwee th ad - th falure, V ad V deotes vrtual age at the respectve th ad -th repar. q s the mportat mperfect repar factor, whch accommodates the degree of repar effectveess. Usually, q s bouded wth a rage [0,]. The correspodg Kjma II model s V ( ) = q V + x (2) I both Kjma models, q = 0 mples the system has bee restored completely. The vrtual age model s hece degeerated to a reewal process model. Whe q =, the vrtual age model s degeerated to a NHPP model. For the sake of smplcty, we descrbe the Kjma models as a fucto: V = f V, x ) (3) ( 2.2 Proportoal Itesty Model wth Covarates Assume the system s experecg mperfect repar. Let the testy fucto of ths system uder mperfect repar represeted by ( t; ), the correspodg PIM model λ 0 q

4 66 Yua Fuqg ad Uday Kumar λ represeted by ( t, z;. Smlar to the classcal Proportoal Hazard Model[3], we propose our PIM as follows: λ t, z; = λ ( t; exp( z + z + z +... ) (4) For smplcty, we rewrte Formula (4) as: t z q t q where f z) = z + z + z... b. ( b λ (, ; ) = λ0 ( ; )exp{ f ( z)} (5) ( I ths paper, we assume the covarat betwee each falure are costat ad the covarat vary from each falure ter-arrval tme. Based o ths assumpto, the orgal testy fucto, wthout mperfect repar ad wth costat operato codto, s shfted horzotally due to mperfect repar. Furthermore, due to the varablty of operatg codtos, the orgal testy fucto would be shfted vertcally. Ths scearo s llustrated Fgure, where the λ ( t, z; s show ot cotuous. λ( t, z; t t+ t j Fgure : Effect of Imperfect Repar ad Operatg Codtos The covarates ca be some evrometal factors such as temperature, humdty, dust etc. Moreover, as Ascher has clamed [2], the repar hstory ca also fluece the repar rate. Thus the covarates ca be some factors regardg repar hstory. Percy et al. has developed a PIM that cosders the repar hstory factor [2]. I ther model, they cosder repar hstory data such as: the tme sce the last PM, CO, the total umber of PM actos ad Cos, as covarates. I ther paper, the factors regardg repar hstory are sgfcat. Therefore, cosderg the fluece of the repar hstory s ecessary some stuato. Moreover, the covarates ca corporate some codto motorg data. 2.3 Cumulatve Dstrbuto Fucto of PIM Based o the prevous falure occurrece, the codtoal probablty of the ext falure ca be obtaed from [3]: It s equvalet to F( x + V ) F( V ) F ( x / V ) = (6) R( V ) R( V ) R( x + V ) R( x + V ) F ( x / V ) = = (7) R( V ) R( V ) Substtutg Formula (5) to (7), the ) = t F x V e t 0 } ( / λ ( t; exp{ f ( z dt The correspodg Probablty Desty Fucto (PDF) s: (8)

5 Proportoal Itesty Model cosderg Imperfect Repar for Reparable Systems 67 f ( t / t t 0 t 0 ) = λ ( t )exp( f ( z ))exp( λ ( t)exp( f ( z )) dt) (9) 2.4 PIM uder Power Law Process I ths paper, we assume the orgal testy fucto as NHPP. As metoed before, the NHPP s wdely used modellg reparable systems. NHPP assumes that the successve falures of a system are depedet of each other. I other words, the accumulatve umber of falures has depedet cremets. The most popular of NHPP models are Power Law Process Models ad Cox-Lews model [4]. The Power Law Process Model defes the testy fucto as a power fucto ad the Cox-Lews model defes t as a log-lear fucto. Ths paper uses the Power Law Process model as orgal testy fucto. The defto of the Power Law Process model s as follows [5, 6]: t λ( α α where α s scale parameter, s shape parameter. t ) = ( ) (0) Based o Power Law Process, whe the Kjma I model s used to accommodate the effectveess of repar, the testy fucto λ ( t, z; s descrbed as: q xl + x l = 0 λ( x, z; = ( ) exp( z + 2z2 + 3z b) α α where we assume x 0. 0 = Whe the Kjma II model s used to accommodate the effectveess of repar, the testy fucto λ ( t, z; s: where V + x (, ; ) ( λ x z q ) exp( z 2z2 3z3... b = ) α α V s defed Equato (2) ad we assume V Parameter Estmato ad Iferece Whe the umber of covarat cosdered s large, estmatg ther correspodg parameter s also dffcult. As there are o detcal systems observed, the popular partal lkelhood method caot be appled [7]. I ths secto, we propose a Bayesa method to estmate parameter. 3. Lkelhood Fucto I ths paper, the parameters of terest are tme s α, q, 0 =, t 2 t, the correspodg covarates are z, z2,..., z t,..., testy fucto Formula () s the: () (2), (=,2, ). Assume the falure. The PDF based o the

6 68 Yua Fuqg ad Uday Kumar f α x + qt α ( qt ) ( x + qt )).exp ( α α ( t / t ) = ( ) exp( f ( z )exp( f ( z The correspodg lkelhood fucto s the rewrtte to: = ) (3) L( α,, q,,...) = f ( t / t ) (4) Whe the Kjma I model s used, the correspodg l s: l L = l( ) + α = = l lα + f f ( z ) + ( ) = ( z) = z + 2z2 + f ( z ) + ( ) x + qt l α L + ( = = x + qt qt l( x + qt ) + ( α) = = e e f ( z ) f ( z ) u ( ) α {( qt )... (5) The correspodg Kjma II model s smlar to above Formula (5), we omt the expresso here. 3.2 Bayesa Estmator Whe the umber of parameters s larger, oe ca employ Bayesa ferece to estmate parameters [9]. The Bayesa estmator cosders the parameter as a varable stead of a costat. The Bayesa lkelhood fucto s: L t) = where f / ) s defed the Formula (3). t t ( Usg the observed tme to falure data D: fucto s f ( t / t ) ( (6) L( D,, q, ) = t t,..., t, 2, the jot pror lkelhood α (7) = f ( t / t ) Oe mport step to perform Bayesa ferece s the selecto of the pror dstrbuto for each parameter. We use o-formatve prors to estmate parameters ths paper. Smlarly to the pror used by Hamada et al. [20], we employ a Gamma dstrbuto as the pror dstrbuto for the scale ad shape parameters. For the mperfect repar factor q, we use the stadard uform dstrbuto. The pror for the coeffcet of the covarate s selected as ormal dstrbuto. I summary, the pror dstrbutos are assumed to be: (, ) (, ~ U (0, α ~ G k a k α 2, ~ G k k 2), q ), ~ N ( µ, ). k, k ) k a, k for scale parameter α. G( a 2 s the Gamma dstrbuto wth parameters 2 α α G ( k, k 2) s that for shape parameter wth parameters k, k 2. N ( µ, ) deotes multomal Normal dstrbuto of covarate coeffcet wth mea vector µ ad covarate matrx. du) )) ( qt + x ) }

7 Proportoal Itesty Model cosderg Imperfect Repar for Reparable Systems 69 The correspodg jot posteror dstrbutos are π ( α,, q, D) L( D α,, q, ) π ( α k π ( k, k 2 a, k α 2 ) π ( q 0,) π ( µ, The posteror dstrbuto s a complex compoud. We employ a MCMC method wth a slce sampler to compute the posteror dstrbuto. Oe ca refer [9] for the theoretcal dscusso of the MCMC method. The result of the MCMC estmato wll be seres of traces. The estmated parameter values of terest are derved from these seres of traces. Oe ca refer [20] for the procedure of obtag the mea, varace ad cofdece terval from the seres of traces. 3.3 Model selecto I Bayesa ferece, model selecto s a broad term. I ths paper, the model selecto covers the selecto of a sutable basele fucto ad the removal of usace factors. Before we dscuss the detaled procedure of model selecto, we troduce a method for assessg the performace of the model. The Bayesa Factor s usually used to measure the goodess of models [9]. Yet the Bayesa Factor (BF) s dffcult to be obtaed practcally. Whe the umber of parameters s kow, usually a approxmate of the BF s used, amely the Bayesa Iformato Crtero (BIC). The defto of the BIC s as follows: α (9) BIC = 2 l L( D,,..) + k l where k s the umber of parameters, s the sze of data sets. The models wth a lower BIC are more preferable. I ths paper, we frstly employ the Bayesa MCMC method to estmate the parameters cosderg all covarates ad the compute the cofdece terval of the estmated parameters. All the covarates whose cofdece terval of ts cover zero wll be removed. After that, we re-estmate the parameters for the reduced covarates aga. Ths procedure s performed teratvely utl o covarate cover zero. 4. A Numercal Example I order to demostrate the methodology proposed above, we troduce a example whch has bee dscussed by Ghodrat ad Kumar [2]. The hydraulc brake pump s a crtcal part of the hydraulc loader. It s kow that the followg factors ca fluece ts relablty: the operator skll (OPSK), mateace crew skll (SCSK), hydraulc ol qualty (HOILQ), hydraulc system temperature (STEMP), ad evrometal codtos (ENDUS). Our paper uses the data Table AI from ther paper [2]. Several PIM models were appled to model the testy fucto cosderg covarates. They dffer at ther basele fucto: models based o the NHPP ad the Webull dstrbuto, ad the Kjma I ad Kjma II models, whch are mperfect repar models. The Webull dstrbuto-based model essetally assumed that q = 0 ad hece assumed that the repar effectveess restored the system to a as-good-as-ew state. The NHPP-based model assumed that the repar effectveess restored the system to a sameas-old state. ) ) (8)

8 70 Yua Fuqg ad Uday Kumar The repar hstory was also take to accout the model. The umber of repars expereced was used as a covarate for the PIM, whch s abbrevated as CO. I summary, 5 covarates were cosdered tally. It was assumed that these covarates were depedet of each other. We developed our model based o Equato (4). Thereafter we employ Bayesa method to estmate parameter,,. The pror dstrbuto was assumed to be: ~ G(3,2) ~ N(0,00). α q, α, ~ G(2,2), ~ U (0,) q, Usg MCMC method, after 2000 bur- teratos, 3000 teratos were a statoary state. The mea, stadard devato, ad cofdece terval for the parameters of terest were derved from the traces whch are statoary state. The parameters wth a cofdece terval coverg zero were cosdered sgfcat. After removg all the sgfcat factors, we re-evaluated the parameter. All the cofdece tervals of the remag covarates excluded zero. The results usg dfferet models are tabulated Table. Table : Results usg Several Models Basele Fucto Model Covarates BIC No covarate / 04 NHPP Full covarates Reduced covarates No covarate / 20 Kjma I Full covarates Reduced covarates No covarate / 95.6 Kjma II Full covarates Webull Dstrbuto 2 4 Reduced covarates 54 No covarate / 292 Full covarates Reduced covarates From Table, t shows that the NHPP-based seres of models ad models wthout covarates are ot sutable for the data, as the BICs are all hgh. Therefore, the assumpto of restorato to a same-as-old state s ot reasoable ad some covarates should be corporated to the model. The Kjma I ad the Webull dstrbuto-based models exhbt a smlar performace ths applcato. The reaso behd s that, whe the Kjma I model s used, q s ear zero. Therefore, the effectveess of q ca be cosdered as restorg the system to a as-good as-ew state. The best model s the Kjma II based PIM model wth the covarates 2, 4 correspodg to BIC=54. The detaled results for ths model are tabulated Table 2 where SD s stadard devato.

9 Proportoal Itesty Model cosderg Imperfect Repar for Reparable Systems 7 Table 2: Evaluated parameter values Lower boud Upper boud Parameter Mea SD (0.025) (0.975) Scale Parameterα Shape Parameter Imperfect Repar Factor q OPSK SCSK STEMP I the optmal PIM model, the mea for q s I order to demostrate the effectveess of repar, we plot ts testy fucto agast tme wth q = 0.099, as show Fgure 2, where the testy fucto s for the 4th to the 7th falure. We ca see from ths fgure that repar s sgfcatly effectve as the system s testy fucto has almost bee restored to zero after each repar. Fgure 2: Effectveess of Repar Moreover, the optmal PIM model, the remag sgfcat factors are: OPSK, SCSK ad STEMP, whch are all sgfcat at level To llustrate the effectveess of these factors, we take the factor STEMP as a example. Fgure 3 plots the 95% cofdece terval of the testy fucto, whe STEMP s ad the other covarates are zero. Both the upper boud ad the lower boud are uder the No Covarate curve. It mples that uder the hgher STEMP, the system has hgher relablty tha the ormal STEMP. Addtoally, order to compare the effectveess of all 3 factors o the system relablty, Fgure 4 s plotted. I Fgure 4, testy fucto OPSK supposes the OPSK to be ad the other factors are 0. The other curves for factor STEMP, SCSK follow ths. Ths fgure shows the effectveess of the 3 factors o relablty follows the order: OPSK> STEMP > SCSK. The factor OPSK flueces the system relablty most sgfcatly.

10 72 Yua Fuqg ad Uday Kumar Fgure 3: 95% Cofdece Iterval for Itesty Fucto Fgure 4: Sestvty of Sgfcat Factors CO, whch represets the repar hstory ths example, s sgfcat ths optmal PIM model. Ths does ot mea that the repar hstory ca be eglected. I some other stuatos, cosderg the repar hstory s stll ecessary. Fally, t s ecessary to meto that Lao has developed a mperfect repar model that cosders the cumulatve umber of falures as a covarate [22]. He argues that hs mperfect repar model ca outperform ay other mperfect repar model. Essetally, the mperfect repar PIM model proposed our paper has geeralzed that preseted Lao s paper. I our model, ot oly the cumulatve umber of falures, but also ay factors relevat to falure ca be accommodated as covarates. 5. Coclusos Ths paper has proposed a model that combes the mperfect repar model ad the proportoal testy model. Usg ths proposed model, the effectveess of repar ad covarates are corporated to the model. The paper essetally provdes a framework for accommodatg all possble factors to a model to aalyze ther effectveess. These factors could be the operatg codtos, the evrometal fluctuato, ad the repar or mateace hstory etc. The troducto of a large umber of factors to the model

11 Proportoal Itesty Model cosderg Imperfect Repar for Reparable Systems 73 complcates the estmato of parameters. I cotrast to some PIMs cosderg several detcal systems exstg, where the partal lkelhood estmator ca be used, the paper employs a Bayesa ferece method based o MCMC estmato. Ths parameter estmator does ot requre detcal systems. Oe lmtato of the preset research s the fact that the factors are assumed to be mutually depedet. I practce, especally whe the repar hstory factor s cosdered, some factors ca be hghly correlated. The teracto betwee factors should therefore be cosdered. Aother lmtato of ths paper s the fact that the covarates are assumed to be tme-depedet. Further research wll exted ths proposed model to cosder tmedepedet factors. Refereces [] Crow, L. H. Relablty Aalyss for Complex, Reparable Systems, ARMY MATERIAL SYSTEMS ANALYSIS ACTIVITY A692020, 975. [2] Ascher, H. ad H. Fegold, Reparable Systems Relablty : Modelg, Iferece, Mscoceptos ad ther Causes. M. Dekker, New York, 984. [3] Cox, D. R. Regresso Models ad Lfe-tables, Joural of the Royal Statstcal Socety, 972; 34(2): [4] Kumar, D. ad B. Klefsjo, Proportoal Hazards Model-A Revew, Relablty Egeerg & System Safety, 994; 44(2): [5] Kumar, D., Proportoal Hazards Modelg of Reparable Systems, Qualty ad Relablty Egeerg Iteratoal, 995; (5): [6] Lugtghed, D. Bajevc ad A.K.S. Jard, Modelg Reparable System Relablty wth Explaatory Varables ad Repar ad Mateace Actos, IMA Joural of Maagemet Mathematcs, 2004; 5(2):89-0. [7] Love, C. E. ad R. Guo, Applcato of Webull Proportoal Hazards Modelg to Badas-Old Falure Data, Qualty ad Relablty Egeerg Iteratoal, 99; 7(3): [8] Love, C. E. ad R. Guo, Usg Proportoal Hazard Modelg Plat Mateace, Qualty ad Relablty Egeerg Iteratoal, 99; 7():7-7. [9] Cox, D. R. ad D. Oakes, Aalyss of Survval Data. Chapma ad Hall, New York, 984. [0] Guo, R., H. ASCHER ad E. Love et al., Geeralzed Models of Reparable Systems: A Survey va Stochastc Processes Formalsm, ORON, 2000; 6(2): [] Kjma, M. ad U. Sumta, A Useful Geeralzato of Reewal Theory: Coutg Processes Govered by No-Negatve Markova Icremets, Joural of Appled Probablty, 986; 23():7-88. [2] Percy, D. F. ad K. A. H. Kobbacy, Usg Proportoal-testes Models to Schedule Prevetve Mateace Itervals, Joural of Mathematcs Appled Busess & Idustry, 998; 9(3): [3] Kjma, M., Some Results for Reparable Systems wth Geeral Repar, Joural of Appled Probablty, 989; 26(): [4] Coetzee, J. L., The Role of NHPP Models the Practcal Aalyss of Mateace Falure Data, Relablty Egeerg & System Safety, 997; 56(2): [5] Klefsjo, B. ad U. Kumar, Goodess-of-Ft Tests for the Power-Law Process Based o the Ttt-Plot,IEEE Trasactos o Relablty, 992; 4(4): [6] Rausad, M. ad A. Høylad, System Relablty Theory : Models, Statstcal Methods, ad Applcatos, Wley-Iterscece,New York, [7] Cox, D. R., Partal Lkelhood,Bometrka, 975; 62(2): [8] Kalbflesch, J. D. ad R. L. Pretce, The Statstcal Aalyss of Falure Tme Data. Wley, New York, 980. [9] Gelma, A., Bayesa Data Aalyss, Chapma ad Hall, Lodo, 2004.

12 74 Yua Fuqg ad Uday Kumar [20] Hamada, M.S., A.G.Wlso, C.S.Reese ad H.F. Martz, Bayesa Relablty, Sprger, [2] Ghodrat, B. ad U. Kumar, Relablty ad Operatg Evromet-based Spare Parts Estmato Approach, Joural of Qualty Mateace Egeerg, 2005, (2): [22] Guo, H.R., H. Lao, W. Zhao ad A. Mettas, A New Stochastc Model for Systems uder Geeral Repars, IEEE Trasactos o Relablty, 2007; 56(): Yua Fuqg obtaed hs M.Tech. System Egeerg at Bejg Uversty of Aeroautcs ad Astroautcs, Cha, the year He joed the Dvso of Operato ad Mateace Egeerg, Luleå Uversty of Techology, Swede, September 2007 to work for the degree of Ph.D. Hs area of research deals wth relablty data aalyss ad statstcal learg theory. Uday Kumar obtaed hs B.Tech. Ida durg the year 979. After workg for 6 years Ida mg compaes, he joed the postgraduate programme of Luleå Uversty of Techology, Luleå, Swede, ad obtaed the degree of PhD the feld of Relablty ad Mateace durg 990. Presetly, he s Professor of Operato ad Mateace Egeerg at Luleå Uversty of Techology, Luleå, Swede. Hs research terests are equpmet mateace, equpmet selecto, relablty ad mataablty aalyss, system aalyss, etc. He has publshed more tha 70 papers teratoal jourals ad coferece proceedgs.

MYUNG HWAN NA, MOON JU KIM, LIN MA

MYUNG HWAN NA, MOON JU KIM, LIN MA BAYESIAN APPROACH TO MEAN TIME BETWEEN FAILURE USING THE MODULATED POWER LAW PROCESS MYUNG HWAN NA, MOON JU KIM, LIN MA Abstract. The Reewal process ad the No-homogeeous Posso process (NHPP) process are

More information

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions Iteratoal Joural of Computatoal Egeerg Research Vol, 0 Issue, Estmato of Stress- Stregth Relablty model usg fte mxture of expoetal dstrbutos K.Sadhya, T.S.Umamaheswar Departmet of Mathematcs, Lal Bhadur

More information

Bayes Estimator for Exponential Distribution with Extension of Jeffery Prior Information

Bayes Estimator for Exponential Distribution with Extension of Jeffery Prior Information Malaysa Joural of Mathematcal Sceces (): 97- (9) Bayes Estmator for Expoetal Dstrbuto wth Exteso of Jeffery Pror Iformato Hadeel Salm Al-Kutub ad Noor Akma Ibrahm Isttute for Mathematcal Research, Uverst

More information

Functions of Random Variables

Functions of Random Variables Fuctos of Radom Varables Chapter Fve Fuctos of Radom Varables 5. Itroducto A geeral egeerg aalyss model s show Fg. 5.. The model output (respose) cotas the performaces of a system or product, such as weght,

More information

A New Family of Transformations for Lifetime Data

A New Family of Transformations for Lifetime Data Proceedgs of the World Cogress o Egeerg 4 Vol I, WCE 4, July - 4, 4, Lodo, U.K. A New Famly of Trasformatos for Lfetme Data Lakhaa Watthaacheewakul Abstract A famly of trasformatos s the oe of several

More information

Comparing Different Estimators of three Parameters for Transmuted Weibull Distribution

Comparing Different Estimators of three Parameters for Transmuted Weibull Distribution Global Joural of Pure ad Appled Mathematcs. ISSN 0973-768 Volume 3, Number 9 (207), pp. 55-528 Research Ida Publcatos http://www.rpublcato.com Comparg Dfferet Estmators of three Parameters for Trasmuted

More information

Lecture 2 - What are component and system reliability and how it can be improved?

Lecture 2 - What are component and system reliability and how it can be improved? Lecture 2 - What are compoet ad system relablty ad how t ca be mproved? Relablty s a measure of the qualty of the product over the log ru. The cocept of relablty s a exteded tme perod over whch the expected

More information

Bayes Interval Estimation for binomial proportion and difference of two binomial proportions with Simulation Study

Bayes Interval Estimation for binomial proportion and difference of two binomial proportions with Simulation Study IJIEST Iteratoal Joural of Iovatve Scece, Egeerg & Techology, Vol. Issue 5, July 04. Bayes Iterval Estmato for bomal proporto ad dfferece of two bomal proportos wth Smulato Study Masoud Gaj, Solmaz hlmad

More information

Ordinary Least Squares Regression. Simple Regression. Algebra and Assumptions.

Ordinary Least Squares Regression. Simple Regression. Algebra and Assumptions. Ordary Least Squares egresso. Smple egresso. Algebra ad Assumptos. I ths part of the course we are gog to study a techque for aalysg the lear relatoshp betwee two varables Y ad X. We have pars of observatos

More information

Analyzing Fuzzy System Reliability Using Vague Set Theory

Analyzing Fuzzy System Reliability Using Vague Set Theory Iteratoal Joural of Appled Scece ad Egeerg 2003., : 82-88 Aalyzg Fuzzy System Relablty sg Vague Set Theory Shy-Mg Che Departmet of Computer Scece ad Iformato Egeerg, Natoal Tawa versty of Scece ad Techology,

More information

VOL. 3, NO. 11, November 2013 ISSN ARPN Journal of Science and Technology All rights reserved.

VOL. 3, NO. 11, November 2013 ISSN ARPN Journal of Science and Technology All rights reserved. VOL., NO., November 0 ISSN 5-77 ARPN Joural of Scece ad Techology 0-0. All rghts reserved. http://www.ejouralofscece.org Usg Square-Root Iverted Gamma Dstrbuto as Pror to Draw Iferece o the Raylegh Dstrbuto

More information

CHAPTER VI Statistical Analysis of Experimental Data

CHAPTER VI Statistical Analysis of Experimental Data Chapter VI Statstcal Aalyss of Expermetal Data CHAPTER VI Statstcal Aalyss of Expermetal Data Measuremets do ot lead to a uque value. Ths s a result of the multtude of errors (maly radom errors) that ca

More information

Summary of the lecture in Biostatistics

Summary of the lecture in Biostatistics Summary of the lecture Bostatstcs Probablty Desty Fucto For a cotuos radom varable, a probablty desty fucto s a fucto such that: 0 dx a b) b a dx A probablty desty fucto provdes a smple descrpto of the

More information

Chapter 5 Properties of a Random Sample

Chapter 5 Properties of a Random Sample Lecture 6 o BST 63: Statstcal Theory I Ku Zhag, /0/008 Revew for the prevous lecture Cocepts: t-dstrbuto, F-dstrbuto Theorems: Dstrbutos of sample mea ad sample varace, relatoshp betwee sample mea ad sample

More information

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS Exam: ECON430 Statstcs Date of exam: Frday, December 8, 07 Grades are gve: Jauary 4, 08 Tme for exam: 0900 am 00 oo The problem set covers 5 pages Resources allowed:

More information

Unimodality Tests for Global Optimization of Single Variable Functions Using Statistical Methods

Unimodality Tests for Global Optimization of Single Variable Functions Using Statistical Methods Malaysa Umodalty Joural Tests of Mathematcal for Global Optmzato Sceces (): of 05 Sgle - 5 Varable (007) Fuctos Usg Statstcal Methods Umodalty Tests for Global Optmzato of Sgle Varable Fuctos Usg Statstcal

More information

BAYESIAN ESTIMATOR OF A CHANGE POINT IN THE HAZARD FUNCTION

BAYESIAN ESTIMATOR OF A CHANGE POINT IN THE HAZARD FUNCTION Mathematcal ad Computatoal Applcatos, Vol. 7, No., pp. 29-38, 202 BAYESIAN ESTIMATOR OF A CHANGE POINT IN THE HAZARD FUNCTION Durdu Karasoy Departmet of Statstcs, Hacettepe Uversty, 06800 Beytepe, Akara,

More information

Module 7: Probability and Statistics

Module 7: Probability and Statistics Lecture 4: Goodess of ft tests. Itroducto Module 7: Probablty ad Statstcs I the prevous two lectures, the cocepts, steps ad applcatos of Hypotheses testg were dscussed. Hypotheses testg may be used to

More information

Analysis of Variance with Weibull Data

Analysis of Variance with Weibull Data Aalyss of Varace wth Webull Data Lahaa Watthaacheewaul Abstract I statstcal data aalyss by aalyss of varace, the usual basc assumptos are that the model s addtve ad the errors are radomly, depedetly, ad

More information

Point Estimation: definition of estimators

Point Estimation: definition of estimators Pot Estmato: defto of estmators Pot estmator: ay fucto W (X,..., X ) of a data sample. The exercse of pot estmato s to use partcular fuctos of the data order to estmate certa ukow populato parameters.

More information

STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS. x, where. = y - ˆ " 1

STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS. x, where. = y - ˆ  1 STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS Recall Assumpto E(Y x) η 0 + η x (lear codtoal mea fucto) Data (x, y ), (x 2, y 2 ),, (x, y ) Least squares estmator ˆ E (Y x) ˆ " 0 + ˆ " x, where ˆ

More information

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS Postpoed exam: ECON430 Statstcs Date of exam: Jauary 0, 0 Tme for exam: 09:00 a.m. :00 oo The problem set covers 5 pages Resources allowed: All wrtte ad prted

More information

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model Lecture 7. Cofdece Itervals ad Hypothess Tests the Smple CLR Model I lecture 6 we troduced the Classcal Lear Regresso (CLR) model that s the radom expermet of whch the data Y,,, K, are the outcomes. The

More information

Lecture 3. Sampling, sampling distributions, and parameter estimation

Lecture 3. Sampling, sampling distributions, and parameter estimation Lecture 3 Samplg, samplg dstrbutos, ad parameter estmato Samplg Defto Populato s defed as the collecto of all the possble observatos of terest. The collecto of observatos we take from the populato s called

More information

Bayesian Inferences for Two Parameter Weibull Distribution Kipkoech W. Cheruiyot 1, Abel Ouko 2, Emily Kirimi 3

Bayesian Inferences for Two Parameter Weibull Distribution Kipkoech W. Cheruiyot 1, Abel Ouko 2, Emily Kirimi 3 IOSR Joural of Mathematcs IOSR-JM e-issn: 78-578, p-issn: 9-765X. Volume, Issue Ver. II Ja - Feb. 05, PP 4- www.osrjourals.org Bayesa Ifereces for Two Parameter Webull Dstrbuto Kpkoech W. Cheruyot, Abel

More information

Chapter 14 Logistic Regression Models

Chapter 14 Logistic Regression Models Chapter 4 Logstc Regresso Models I the lear regresso model X β + ε, there are two types of varables explaatory varables X, X,, X k ad study varable y These varables ca be measured o a cotuous scale as

More information

TESTS BASED ON MAXIMUM LIKELIHOOD

TESTS BASED ON MAXIMUM LIKELIHOOD ESE 5 Toy E. Smth. The Basc Example. TESTS BASED ON MAXIMUM LIKELIHOOD To llustrate the propertes of maxmum lkelhood estmates ad tests, we cosder the smplest possble case of estmatg the mea of the ormal

More information

Comparison of Parameters of Lognormal Distribution Based On the Classical and Posterior Estimates

Comparison of Parameters of Lognormal Distribution Based On the Classical and Posterior Estimates Joural of Moder Appled Statstcal Methods Volume Issue Artcle 8 --03 Comparso of Parameters of Logormal Dstrbuto Based O the Classcal ad Posteror Estmates Raja Sulta Uversty of Kashmr, Sragar, Ida, hamzasulta8@yahoo.com

More information

Introduction to local (nonparametric) density estimation. methods

Introduction to local (nonparametric) density estimation. methods Itroducto to local (oparametrc) desty estmato methods A slecture by Yu Lu for ECE 66 Sprg 014 1. Itroducto Ths slecture troduces two local desty estmato methods whch are Parze desty estmato ad k-earest

More information

Some Statistical Inferences on the Records Weibull Distribution Using Shannon Entropy and Renyi Entropy

Some Statistical Inferences on the Records Weibull Distribution Using Shannon Entropy and Renyi Entropy OPEN ACCESS Coferece Proceedgs Paper Etropy www.scforum.et/coferece/ecea- Some Statstcal Ifereces o the Records Webull Dstrbuto Usg Shao Etropy ad Rey Etropy Gholamhosse Yar, Rezva Rezae * School of Mathematcs,

More information

Bootstrap Method for Testing of Equality of Several Coefficients of Variation

Bootstrap Method for Testing of Equality of Several Coefficients of Variation Cloud Publcatos Iteratoal Joural of Advaced Mathematcs ad Statstcs Volume, pp. -6, Artcle ID Sc- Research Artcle Ope Access Bootstrap Method for Testg of Equalty of Several Coeffcets of Varato Dr. Navee

More information

Bounds on the expected entropy and KL-divergence of sampled multinomial distributions. Brandon C. Roy

Bounds on the expected entropy and KL-divergence of sampled multinomial distributions. Brandon C. Roy Bouds o the expected etropy ad KL-dvergece of sampled multomal dstrbutos Brado C. Roy bcroy@meda.mt.edu Orgal: May 18, 2011 Revsed: Jue 6, 2011 Abstract Iformato theoretc quattes calculated from a sampled

More information

Analysis of a Repairable (n-1)-out-of-n: G System with Failure and Repair Times Arbitrarily Distributed

Analysis of a Repairable (n-1)-out-of-n: G System with Failure and Repair Times Arbitrarily Distributed Amerca Joural of Mathematcs ad Statstcs. ; (: -8 DOI:.593/j.ajms.. Aalyss of a Reparable (--out-of-: G System wth Falure ad Repar Tmes Arbtrarly Dstrbuted M. Gherda, M. Boushaba, Departmet of Mathematcs,

More information

Lecture 3 Probability review (cont d)

Lecture 3 Probability review (cont d) STATS 00: Itroducto to Statstcal Iferece Autum 06 Lecture 3 Probablty revew (cot d) 3. Jot dstrbutos If radom varables X,..., X k are depedet, the ther dstrbuto may be specfed by specfyg the dvdual dstrbuto

More information

Estimation of the Loss and Risk Functions of Parameter of Maxwell Distribution

Estimation of the Loss and Risk Functions of Parameter of Maxwell Distribution Scece Joural of Appled Mathematcs ad Statstcs 06; 4(4): 9- http://www.scecepublshggroup.com/j/sjams do: 0.648/j.sjams.060404. ISSN: 76-949 (Prt); ISSN: 76-95 (Ole) Estmato of the Loss ad Rsk Fuctos of

More information

BAYESIAN INFERENCES FOR TWO PARAMETER WEIBULL DISTRIBUTION

BAYESIAN INFERENCES FOR TWO PARAMETER WEIBULL DISTRIBUTION Iteratoal Joural of Mathematcs ad Statstcs Studes Vol.4, No.3, pp.5-39, Jue 06 Publshed by Europea Cetre for Research Trag ad Developmet UK (www.eajourals.org BAYESIAN INFERENCES FOR TWO PARAMETER WEIBULL

More information

Solving Constrained Flow-Shop Scheduling. Problems with Three Machines

Solving Constrained Flow-Shop Scheduling. Problems with Three Machines It J Cotemp Math Sceces, Vol 5, 2010, o 19, 921-929 Solvg Costraed Flow-Shop Schedulg Problems wth Three Maches P Pada ad P Rajedra Departmet of Mathematcs, School of Advaced Sceces, VIT Uversty, Vellore-632

More information

Simple Linear Regression

Simple Linear Regression Statstcal Methods I (EST 75) Page 139 Smple Lear Regresso Smple regresso applcatos are used to ft a model descrbg a lear relatoshp betwee two varables. The aspects of least squares regresso ad correlato

More information

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution:

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution: Chapter 4 Exercses Samplg Theory Exercse (Smple radom samplg: Let there be two correlated radom varables X ad A sample of sze s draw from a populato by smple radom samplg wthout replacemet The observed

More information

Chapter 3 Sampling For Proportions and Percentages

Chapter 3 Sampling For Proportions and Percentages Chapter 3 Samplg For Proportos ad Percetages I may stuatos, the characterstc uder study o whch the observatos are collected are qualtatve ature For example, the resposes of customers may marketg surveys

More information

Third handout: On the Gini Index

Third handout: On the Gini Index Thrd hadout: O the dex Corrado, a tala statstca, proposed (, 9, 96) to measure absolute equalt va the mea dfferece whch s defed as ( / ) where refers to the total umber of dvduals socet. Assume that. The

More information

ENGI 4421 Joint Probability Distributions Page Joint Probability Distributions [Navidi sections 2.5 and 2.6; Devore sections

ENGI 4421 Joint Probability Distributions Page Joint Probability Distributions [Navidi sections 2.5 and 2.6; Devore sections ENGI 441 Jot Probablty Dstrbutos Page 7-01 Jot Probablty Dstrbutos [Navd sectos.5 ad.6; Devore sectos 5.1-5.] The jot probablty mass fucto of two dscrete radom quattes, s, P ad p x y x y The margal probablty

More information

STK4011 and STK9011 Autumn 2016

STK4011 and STK9011 Autumn 2016 STK4 ad STK9 Autum 6 Pot estmato Covers (most of the followg materal from chapter 7: Secto 7.: pages 3-3 Secto 7..: pages 3-33 Secto 7..: pages 35-3 Secto 7..3: pages 34-35 Secto 7.3.: pages 33-33 Secto

More information

Derivation of 3-Point Block Method Formula for Solving First Order Stiff Ordinary Differential Equations

Derivation of 3-Point Block Method Formula for Solving First Order Stiff Ordinary Differential Equations Dervato of -Pot Block Method Formula for Solvg Frst Order Stff Ordary Dfferetal Equatos Kharul Hamd Kharul Auar, Kharl Iskadar Othma, Zara Bb Ibrahm Abstract Dervato of pot block method formula wth costat

More information

Econometric Methods. Review of Estimation

Econometric Methods. Review of Estimation Ecoometrc Methods Revew of Estmato Estmatg the populato mea Radom samplg Pot ad terval estmators Lear estmators Ubased estmators Lear Ubased Estmators (LUEs) Effcecy (mmum varace) ad Best Lear Ubased Estmators

More information

X ε ) = 0, or equivalently, lim

X ε ) = 0, or equivalently, lim Revew for the prevous lecture Cocepts: order statstcs Theorems: Dstrbutos of order statstcs Examples: How to get the dstrbuto of order statstcs Chapter 5 Propertes of a Radom Sample Secto 55 Covergece

More information

Comparison of Dual to Ratio-Cum-Product Estimators of Population Mean

Comparison of Dual to Ratio-Cum-Product Estimators of Population Mean Research Joural of Mathematcal ad Statstcal Sceces ISS 30 6047 Vol. 1(), 5-1, ovember (013) Res. J. Mathematcal ad Statstcal Sc. Comparso of Dual to Rato-Cum-Product Estmators of Populato Mea Abstract

More information

Multiple Regression. More than 2 variables! Grade on Final. Multiple Regression 11/21/2012. Exam 2 Grades. Exam 2 Re-grades

Multiple Regression. More than 2 variables! Grade on Final. Multiple Regression 11/21/2012. Exam 2 Grades. Exam 2 Re-grades STAT 101 Dr. Kar Lock Morga 11/20/12 Exam 2 Grades Multple Regresso SECTIONS 9.2, 10.1, 10.2 Multple explaatory varables (10.1) Parttog varablty R 2, ANOVA (9.2) Codtos resdual plot (10.2) Trasformatos

More information

Application of Calibration Approach for Regression Coefficient Estimation under Two-stage Sampling Design

Application of Calibration Approach for Regression Coefficient Estimation under Two-stage Sampling Design Authors: Pradp Basak, Kaustav Adtya, Hukum Chadra ad U.C. Sud Applcato of Calbrato Approach for Regresso Coeffcet Estmato uder Two-stage Samplg Desg Pradp Basak, Kaustav Adtya, Hukum Chadra ad U.C. Sud

More information

Cubic Nonpolynomial Spline Approach to the Solution of a Second Order Two-Point Boundary Value Problem

Cubic Nonpolynomial Spline Approach to the Solution of a Second Order Two-Point Boundary Value Problem Joural of Amerca Scece ;6( Cubc Nopolyomal Sple Approach to the Soluto of a Secod Order Two-Pot Boudary Value Problem W.K. Zahra, F.A. Abd El-Salam, A.A. El-Sabbagh ad Z.A. ZAk * Departmet of Egeerg athematcs

More information

Chapter 8. Inferences about More Than Two Population Central Values

Chapter 8. Inferences about More Than Two Population Central Values Chapter 8. Ifereces about More Tha Two Populato Cetral Values Case tudy: Effect of Tmg of the Treatmet of Port-We tas wth Lasers ) To vestgate whether treatmet at a youg age would yeld better results tha

More information

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA THE ROYAL STATISTICAL SOCIETY 3 EXAMINATIONS SOLUTIONS GRADUATE DIPLOMA PAPER I STATISTICAL THEORY & METHODS The Socety provdes these solutos to assst caddates preparg for the examatos future years ad

More information

ESS Line Fitting

ESS Line Fitting ESS 5 014 17. Le Fttg A very commo problem data aalyss s lookg for relatoshpetwee dfferet parameters ad fttg les or surfaces to data. The smplest example s fttg a straght le ad we wll dscuss that here

More information

Chapter 8: Statistical Analysis of Simulated Data

Chapter 8: Statistical Analysis of Simulated Data Marquette Uversty MSCS600 Chapter 8: Statstcal Aalyss of Smulated Data Dael B. Rowe, Ph.D. Departmet of Mathematcs, Statstcs, ad Computer Scece Copyrght 08 by Marquette Uversty MSCS600 Ageda 8. The Sample

More information

A Study of the Reproducibility of Measurements with HUR Leg Extension/Curl Research Line

A Study of the Reproducibility of Measurements with HUR Leg Extension/Curl Research Line HUR Techcal Report 000--9 verso.05 / Frak Borg (borgbros@ett.f) A Study of the Reproducblty of Measuremets wth HUR Leg Eteso/Curl Research Le A mportat property of measuremets s that the results should

More information

Part 4b Asymptotic Results for MRR2 using PRESS. Recall that the PRESS statistic is a special type of cross validation procedure (see Allen (1971))

Part 4b Asymptotic Results for MRR2 using PRESS. Recall that the PRESS statistic is a special type of cross validation procedure (see Allen (1971)) art 4b Asymptotc Results for MRR usg RESS Recall that the RESS statstc s a specal type of cross valdato procedure (see Alle (97)) partcular to the regresso problem ad volves fdg Y $,, the estmate at the

More information

Confidence Intervals for Double Exponential Distribution: A Simulation Approach

Confidence Intervals for Double Exponential Distribution: A Simulation Approach World Academy of Scece, Egeerg ad Techology Iteratoal Joural of Physcal ad Mathematcal Sceces Vol:6, No:, 0 Cofdece Itervals for Double Expoetal Dstrbuto: A Smulato Approach M. Alrasheed * Iteratoal Scece

More information

Simulation Output Analysis

Simulation Output Analysis Smulato Output Aalyss Summary Examples Parameter Estmato Sample Mea ad Varace Pot ad Iterval Estmato ermatg ad o-ermatg Smulato Mea Square Errors Example: Sgle Server Queueg System x(t) S 4 S 4 S 3 S 5

More information

A Combination of Adaptive and Line Intercept Sampling Applicable in Agricultural and Environmental Studies

A Combination of Adaptive and Line Intercept Sampling Applicable in Agricultural and Environmental Studies ISSN 1684-8403 Joural of Statstcs Volume 15, 008, pp. 44-53 Abstract A Combato of Adaptve ad Le Itercept Samplg Applcable Agrcultural ad Evrometal Studes Azmer Kha 1 A adaptve procedure s descrbed for

More information

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best Error Aalyss Preamble Wheever a measuremet s made, the result followg from that measuremet s always subject to ucertaty The ucertaty ca be reduced by makg several measuremets of the same quatty or by mprovg

More information

( ) = ( ) ( ) Chapter 13 Asymptotic Theory and Stochastic Regressors. Stochastic regressors model

( ) = ( ) ( ) Chapter 13 Asymptotic Theory and Stochastic Regressors. Stochastic regressors model Chapter 3 Asmptotc Theor ad Stochastc Regressors The ature of eplaator varable s assumed to be o-stochastc or fed repeated samples a regresso aalss Such a assumpto s approprate for those epermets whch

More information

Multivariate Transformation of Variables and Maximum Likelihood Estimation

Multivariate Transformation of Variables and Maximum Likelihood Estimation Marquette Uversty Multvarate Trasformato of Varables ad Maxmum Lkelhood Estmato Dael B. Rowe, Ph.D. Assocate Professor Departmet of Mathematcs, Statstcs, ad Computer Scece Copyrght 03 by Marquette Uversty

More information

Class 13,14 June 17, 19, 2015

Class 13,14 June 17, 19, 2015 Class 3,4 Jue 7, 9, 05 Pla for Class3,4:. Samplg dstrbuto of sample mea. The Cetral Lmt Theorem (CLT). Cofdece terval for ukow mea.. Samplg Dstrbuto for Sample mea. Methods used are based o CLT ( Cetral

More information

A new Family of Distributions Using the pdf of the. rth Order Statistic from Independent Non- Identically Distributed Random Variables

A new Family of Distributions Using the pdf of the. rth Order Statistic from Independent Non- Identically Distributed Random Variables Iteratoal Joural of Cotemporary Mathematcal Sceces Vol. 07 o. 8 9-05 HIKARI Ltd www.m-hkar.com https://do.org/0.988/jcms.07.799 A ew Famly of Dstrbutos Usg the pdf of the rth Order Statstc from Idepedet

More information

IJOART. Copyright 2014 SciResPub.

IJOART. Copyright 2014 SciResPub. Iteratoal Joural of Advacemets Research & Techology, Volume 3, Issue 10, October -014 58 Usg webull dstrbuto the forecastg by applyg o real data of the umber of traffc accdets sulama durg the perod (010-013)

More information

ECONOMETRIC THEORY. MODULE VIII Lecture - 26 Heteroskedasticity

ECONOMETRIC THEORY. MODULE VIII Lecture - 26 Heteroskedasticity ECONOMETRIC THEORY MODULE VIII Lecture - 6 Heteroskedastcty Dr. Shalabh Departmet of Mathematcs ad Statstcs Ida Isttute of Techology Kapur . Breusch Paga test Ths test ca be appled whe the replcated data

More information

Study of Correlation using Bayes Approach under bivariate Distributions

Study of Correlation using Bayes Approach under bivariate Distributions Iteratoal Joural of Scece Egeerg ad Techolog Research IJSETR Volume Issue Februar 4 Stud of Correlato usg Baes Approach uder bvarate Dstrbutos N.S.Padharkar* ad. M.N.Deshpade** *Govt.Vdarbha Isttute of

More information

Chapter -2 Simple Random Sampling

Chapter -2 Simple Random Sampling Chapter - Smple Radom Samplg Smple radom samplg (SRS) s a method of selecto of a sample comprsg of umber of samplg uts out of the populato havg umber of samplg uts such that every samplg ut has a equal

More information

Chapter -2 Simple Random Sampling

Chapter -2 Simple Random Sampling Chapter - Smple Radom Samplg Smple radom samplg (SRS) s a method of selecto of a sample comprsg of umber of samplg uts out of the populato havg umber of samplg uts such that every samplg ut has a equal

More information

Continuous Distributions

Continuous Distributions 7//3 Cotuous Dstrbutos Radom Varables of the Cotuous Type Desty Curve Percet Desty fucto, f (x) A smooth curve that ft the dstrbuto 3 4 5 6 7 8 9 Test scores Desty Curve Percet Probablty Desty Fucto, f

More information

Generating Multivariate Nonnormal Distribution Random Numbers Based on Copula Function

Generating Multivariate Nonnormal Distribution Random Numbers Based on Copula Function 7659, Eglad, UK Joural of Iformato ad Computg Scece Vol. 2, No. 3, 2007, pp. 9-96 Geeratg Multvarate Noormal Dstrbuto Radom Numbers Based o Copula Fucto Xaopg Hu +, Jam He ad Hogsheg Ly School of Ecoomcs

More information

Objectives of Multiple Regression

Objectives of Multiple Regression Obectves of Multple Regresso Establsh the lear equato that best predcts values of a depedet varable Y usg more tha oe eplaator varable from a large set of potetal predctors {,,... k }. Fd that subset of

More information

Block-Based Compact Thermal Modeling of Semiconductor Integrated Circuits

Block-Based Compact Thermal Modeling of Semiconductor Integrated Circuits Block-Based Compact hermal Modelg of Semcoductor Itegrated Crcuts Master s hess Defese Caddate: Jg Ba Commttee Members: Dr. Mg-Cheg Cheg Dr. Daqg Hou Dr. Robert Schllg July 27, 2009 Outle Itroducto Backgroud

More information

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA THE ROYAL STATISTICAL SOCIETY EXAMINATIONS SOLUTIONS GRADUATE DIPLOMA PAPER II STATISTICAL THEORY & METHODS The Socety provdes these solutos to assst caddates preparg for the examatos future years ad for

More information

Chapter 4 Multiple Random Variables

Chapter 4 Multiple Random Variables Revew for the prevous lecture: Theorems ad Examples: How to obta the pmf (pdf) of U = g (, Y) ad V = g (, Y) Chapter 4 Multple Radom Varables Chapter 44 Herarchcal Models ad Mxture Dstrbutos Examples:

More information

Multiple Linear Regression Analysis

Multiple Linear Regression Analysis LINEA EGESSION ANALYSIS MODULE III Lecture - 4 Multple Lear egresso Aalyss Dr. Shalabh Departmet of Mathematcs ad Statstcs Ida Isttute of Techology Kapur Cofdece terval estmato The cofdece tervals multple

More information

4. Standard Regression Model and Spatial Dependence Tests

4. Standard Regression Model and Spatial Dependence Tests 4. Stadard Regresso Model ad Spatal Depedece Tests Stadard regresso aalss fals the presece of spatal effects. I case of spatal depedeces ad/or spatal heterogeet a stadard regresso model wll be msspecfed.

More information

Chapter 4 (Part 1): Non-Parametric Classification (Sections ) Pattern Classification 4.3) Announcements

Chapter 4 (Part 1): Non-Parametric Classification (Sections ) Pattern Classification 4.3) Announcements Aoucemets No-Parametrc Desty Estmato Techques HW assged Most of ths lecture was o the blacboard. These sldes cover the same materal as preseted DHS Bometrcs CSE 90-a Lecture 7 CSE90a Fall 06 CSE90a Fall

More information

Special Instructions / Useful Data

Special Instructions / Useful Data JAM 6 Set of all real umbers P A..d. B, p Posso Specal Istructos / Useful Data x,, :,,, x x Probablty of a evet A Idepedetly ad detcally dstrbuted Bomal dstrbuto wth parameters ad p Posso dstrbuto wth

More information

ρ < 1 be five real numbers. The

ρ < 1 be five real numbers. The Lecture o BST 63: Statstcal Theory I Ku Zhag, /0/006 Revew for the prevous lecture Deftos: covarace, correlato Examples: How to calculate covarace ad correlato Theorems: propertes of correlato ad covarace

More information

BAYESIAN ESTIMATION OF GUMBEL TYPE-II DISTRIBUTION

BAYESIAN ESTIMATION OF GUMBEL TYPE-II DISTRIBUTION Data Scece Joural, Volume, 0 August 03 BAYESIAN ESTIMATION OF GUMBEL TYPE-II DISTRIBUTION Kamra Abbas,*, Jayu Fu, Yca Tag School of Face ad Statstcs, East Cha Normal Uversty, Shagha 004, Cha Emal-addresses:*

More information

Evaluation of uncertainty in measurements

Evaluation of uncertainty in measurements Evaluato of ucertaty measuremets Laboratory of Physcs I Faculty of Physcs Warsaw Uversty of Techology Warszawa, 05 Itroducto The am of the measuremet s to determe the measured value. Thus, the measuremet

More information

9.1 Introduction to the probit and logit models

9.1 Introduction to the probit and logit models EC3000 Ecoometrcs Lecture 9 Probt & Logt Aalss 9. Itroducto to the probt ad logt models 9. The logt model 9.3 The probt model Appedx 9. Itroducto to the probt ad logt models These models are used regressos

More information

Chapter 13 Student Lecture Notes 13-1

Chapter 13 Student Lecture Notes 13-1 Chapter 3 Studet Lecture Notes 3- Basc Busess Statstcs (9 th Edto) Chapter 3 Smple Lear Regresso 4 Pretce-Hall, Ic. Chap 3- Chapter Topcs Types of Regresso Models Determg the Smple Lear Regresso Equato

More information

Simple Linear Regression

Simple Linear Regression Correlato ad Smple Lear Regresso Berl Che Departmet of Computer Scece & Iformato Egeerg Natoal Tawa Normal Uversty Referece:. W. Navd. Statstcs for Egeerg ad Scetsts. Chapter 7 (7.-7.3) & Teachg Materal

More information

A Review on Trend Tests for Failure Data Analysis

A Review on Trend Tests for Failure Data Analysis A.H.C. Tsag: A Revew o Tred Tests for Falure Data Aalyss 4 ISSN 5-578 The West Ida Joural of Egeerg Vol.35, No., July, pp.4-9 A Revew o Tred Tests for Falure Data Aalyss Albert H.C. Tsag Departmet of Idustral

More information

Analysis of System Performance IN2072 Chapter 5 Analysis of Non Markov Systems

Analysis of System Performance IN2072 Chapter 5 Analysis of Non Markov Systems Char for Network Archtectures ad Servces Prof. Carle Departmet of Computer Scece U Müche Aalyss of System Performace IN2072 Chapter 5 Aalyss of No Markov Systems Dr. Alexader Kle Prof. Dr.-Ig. Georg Carle

More information

Bayes (Naïve or not) Classifiers: Generative Approach

Bayes (Naïve or not) Classifiers: Generative Approach Logstc regresso Bayes (Naïve or ot) Classfers: Geeratve Approach What do we mea by Geeratve approach: Lear p(y), p(x y) ad the apply bayes rule to compute p(y x) for makg predctos Ths s essetally makg

More information

MEASURES OF DISPERSION

MEASURES OF DISPERSION MEASURES OF DISPERSION Measure of Cetral Tedecy: Measures of Cetral Tedecy ad Dsperso ) Mathematcal Average: a) Arthmetc mea (A.M.) b) Geometrc mea (G.M.) c) Harmoc mea (H.M.) ) Averages of Posto: a) Meda

More information

STRONG CONSISTENCY FOR SIMPLE LINEAR EV MODEL WITH v/ -MIXING

STRONG CONSISTENCY FOR SIMPLE LINEAR EV MODEL WITH v/ -MIXING Joural of tatstcs: Advaces Theory ad Alcatos Volume 5, Number, 6, Pages 3- Avalable at htt://scetfcadvaces.co. DOI: htt://d.do.org/.864/jsata_7678 TRONG CONITENCY FOR IMPLE LINEAR EV MODEL WITH v/ -MIXING

More information

Beam Warming Second-Order Upwind Method

Beam Warming Second-Order Upwind Method Beam Warmg Secod-Order Upwd Method Petr Valeta Jauary 6, 015 Ths documet s a part of the assessmet work for the subject 1DRP Dfferetal Equatos o Computer lectured o FNSPE CTU Prague. Abstract Ths documet

More information

CHAPTER 3 POSTERIOR DISTRIBUTIONS

CHAPTER 3 POSTERIOR DISTRIBUTIONS CHAPTER 3 POSTERIOR DISTRIBUTIONS If scece caot measure the degree of probablt volved, so much the worse for scece. The practcal ma wll stck to hs apprecatve methods utl t does, or wll accept the results

More information

GENERALIZED METHOD OF MOMENTS CHARACTERISTICS AND ITS APPLICATION ON PANELDATA

GENERALIZED METHOD OF MOMENTS CHARACTERISTICS AND ITS APPLICATION ON PANELDATA Sc.It.(Lahore),26(3),985-990,2014 ISSN 1013-5316; CODEN: SINTE 8 GENERALIZED METHOD OF MOMENTS CHARACTERISTICS AND ITS APPLICATION ON PANELDATA Beradhta H. S. Utam 1, Warsoo 1, Da Kurasar 1, Mustofa Usma

More information

arxiv: v1 [math.st] 24 Oct 2016

arxiv: v1 [math.st] 24 Oct 2016 arxv:60.07554v [math.st] 24 Oct 206 Some Relatoshps ad Propertes of the Hypergeometrc Dstrbuto Peter H. Pesku, Departmet of Mathematcs ad Statstcs York Uversty, Toroto, Otaro M3J P3, Caada E-mal: pesku@pascal.math.yorku.ca

More information

Module 7. Lecture 7: Statistical parameter estimation

Module 7. Lecture 7: Statistical parameter estimation Lecture 7: Statstcal parameter estmato Parameter Estmato Methods of Parameter Estmato 1) Method of Matchg Pots ) Method of Momets 3) Mamum Lkelhood method Populato Parameter Sample Parameter Ubased estmato

More information

X X X E[ ] E X E X. is the ()m n where the ( i,)th. j element is the mean of the ( i,)th., then

X X X E[ ] E X E X. is the ()m n where the ( i,)th. j element is the mean of the ( i,)th., then Secto 5 Vectors of Radom Varables Whe workg wth several radom varables,,..., to arrage them vector form x, t s ofte coveet We ca the make use of matrx algebra to help us orgaze ad mapulate large umbers

More information

Bayesian Classification. CS690L Data Mining: Classification(2) Bayesian Theorem: Basics. Bayesian Theorem. Training dataset. Naïve Bayes Classifier

Bayesian Classification. CS690L Data Mining: Classification(2) Bayesian Theorem: Basics. Bayesian Theorem. Training dataset. Naïve Bayes Classifier Baa Classfcato CS6L Data Mg: Classfcato() Referece: J. Ha ad M. Kamber, Data Mg: Cocepts ad Techques robablstc learg: Calculate explct probabltes for hypothess, amog the most practcal approaches to certa

More information

A NEW MODIFIED GENERALIZED ODD LOG-LOGISTIC DISTRIBUTION WITH THREE PARAMETERS

A NEW MODIFIED GENERALIZED ODD LOG-LOGISTIC DISTRIBUTION WITH THREE PARAMETERS A NEW MODIFIED GENERALIZED ODD LOG-LOGISTIC DISTRIBUTION WITH THREE PARAMETERS Arbër Qoshja 1 & Markela Muça 1. Departmet of Appled Mathematcs, Faculty of Natural Scece, Traa, Albaa. Departmet of Appled

More information

Interval Estimation of a P(X 1 < X 2 ) Model for Variables having General Inverse Exponential Form Distributions with Unknown Parameters

Interval Estimation of a P(X 1 < X 2 ) Model for Variables having General Inverse Exponential Form Distributions with Unknown Parameters Amerca Joural of Theoretcal ad Appled Statstcs 08; 7(4): 3-38 http://www.scecepublshggroup.com/j/ajtas do: 0.648/j.ajtas.080704. ISSN: 36-8999 (Prt); ISSN: 36-9006 (Ole) Iterval Estmato of a P(X < X )

More information

The Necessarily Efficient Point Method for Interval Molp Problems

The Necessarily Efficient Point Method for Interval Molp Problems ISS 6-69 Eglad K Joural of Iformato ad omputg Scece Vol. o. 9 pp. - The ecessarly Effcet Pot Method for Iterval Molp Problems Hassa Mshmast eh ad Marzeh Alezhad + Mathematcs Departmet versty of Ssta ad

More information