Exploring Human Mobility Patterns Based on Location Information of US Flights. Bin Jiang and Tao Jia

Size: px
Start display at page:

Download "Exploring Human Mobility Patterns Based on Location Information of US Flights. Bin Jiang and Tao Jia"

Transcription

1 Eplorg Huma Moblty Pattrs Basd o Locato Iformato of US Flghts B Jag ad Tao Ja Dpartmt of Tchology ad Bult Evromt, Dvso of Gomatcs Uvrsty of Gävl, SE Gävl, Swd Emal: b.jag@hg.s, jatao8@6.com (Draft: Aprl 0, Rvso: August 0) Abstract A rag of arly studs hav b coductd to llustrat huma moblty pattrs usg dffrt trackg data, such as dollar ots, cll phos ad tacabs. Hr, w plor huma moblty pattrs basd o massv trackg data of US flghts. Both topologcal ad gomtrc proprts ar ad dtal. W foud that topologcal proprts, such as traffc volum (btw arports) ad dgr of coctvty (of dvdual arports), cludg both - ad outdgrs, follow a powr law dstrbuto but ot a gomtrc proprty lk travl lgths. Th travl lgths hbt a potal dstrbuto rathr tha a powr law wth a potal cutoff as prvous studs llustratd. W furthr smulatd huma moblty o th stablshd topologs of arports wth varous movg bhavors ad foud that th moblty pattrs ar maly attrbutd to th udrlyg bary topology of arports ad hav lttl to do wth othr factors, such as movg bhavors ad gomtrc dstacs. Apart from th abov fdgs, ths study adopts th had/tal dvso rul, whch s rgularty bhd ay havy-tald dstrbuto for tractg dvdual arports. Th adopto of ths rul for data procssg costtuts aothr major cotrbuto of ths papr. Kywords: scalg of gographc spac, had/tal dvso rul, powr law, gographc formato, agt-basd smulatos Itroducto Huma moblty s a rsarch topc of prmary trst to may dscpls, such as gography, urba plag, pdmology ad v tlcommucato (Hägrstrad 970, Hllr t al. 99, Hufagl, Brockma ad Gsl 00, L t al. 009). Rctly, wth th avalablty of massv amouts of varous trackg data, rsarchrs hav attmptd to vstgat th udrlyg rgularts ad mchasms of huma movmt pattrs (Brockma, Hufag ad Gsl 006, Gozalz, Hdalgo ad Barabás 008, Jag, Y ad Zhao 009, Sog t al. 00, Roth t al. 0). It was foud that huma moblty hbts a scalg proprty wth a hgh probablty of prdctg dvdual ad collctv movmt pattrs. Th trackg data rlatd to US dollar ots (Brockma, Hufag ad Gsl 006), cll phos (Gozalz, Hdalgo ad Barabás 008, Sog t al. 00), ad tacabs (Jag, Y ad Zhao 009) hav b usd. Th scalg proprty dcats that huma actvts gographc spac ar thr radom or v but dmostrat a vry hgh dgr of htrogty trms of dstacs ad prfrrd placs. I ths papr, w adopt locato formato of US flghts, capturd vry 5 uts by GPS rcvrs whl th plas ar srvc. I total, ovr 7 mllo locatos of varous US flghts wr usd to tract formato rlatd to both gomtrc ad topologcal proprts, such as travl lgths, traffc volum, ad arport dgrs of coctvty (by routs or by flghts) for furthr vstgato of huma moblty pattrs. W charactrz huma movmt pattrs by fv havy-tald dstrbutos,.., powr law, powr law wth cutoff, potal, strtchd potal ad logormal dstrbutos (Claust, Shalz ad Nwma 009). I cotrast to arlr studs that sought powr law-lk dstrbutos oly, w blv that all th fv modls ca charactrz huma movmt pattrs. Thus, w mak a par-ws comparso amog th fv modls ad choos o bst ft to charactrz huma movmt pattrs. Aothr dstgushd fatur of ths study s that w placd cosdrabl ffort to data procssg to tract th gomtrc ad topologcal proprts for plorg huma moblty pattrs. Th basc

2 prcpl of th data procssg s th had/tal dvso rul that was formulatd for mprcal data that hav a havy-tald dstrbuto (Jag ad Lu 0). W procssd ovr mllo capturd locatos of US domstc flghts wth a -day tm prod. From th massv amout of locatos or pots (, y, z, t), w tractd ovr,000 routs ad 00,000 flghts ad stablshd a topologcal rlatoshp for ovr 700 arports across th coutry ad wth th spcfd tm prod (s th t scto o data ad data procssg). W dsgatd th flght movmt as a proy for huma movmt at th coutry lvl ad ad th pattrs from both gomtrc ad topologcal prspctvs. To furthr plor huma moblty pattrs, w stup varous agt-basd smulatos to ucovr th udrlyg mchasms.. Data ad data procssg W obtad, total, 7,685,98 flght locatos or pots wth days btw 8 ad 8 August 00,.., (, y, z, t ) whr 7,685, 98. Th startg tm o th 8 th was :6AM, whl th dg tm o th 8 th was 8:9AM. Th locatos or pots ar rfrcd to th World Godtc Systm, 98. Apart from th locato formato, thr ar som othr attrbuts, such as arl cod, ad flght umbr ad spd; s Tabl for a small sampl. Tabl : A sampl of orgal flght data capturd by GPS rcvrs Arl Flght Spd Alttud Lattud Logtud Tmstamp MES 9 NULL NULL :0:9 COM :9:6 MES 9 NULL NULL :0:9 COM :5:6 MES NULL NULL :0: COM :59:6 W had to procss th data, tally a massv st of pots (500MB), to dtr th dvdual arports ad how th arports ar lkd or rlatd by flghts or routs. W tractd two typs of graphs: rout graphs ad flght graphs. Th dffrc btw a rout graph ad a flght graph s that th formr bars a bary rlatoshp whl th lattr s wghtd by th umbr of flghts. I othr words, a rout has at last o flght; thr would b o rout wthout a sgl flght. To buld up th two graphs, frst w tractd th dvdual flghts. Ths procss s show Fgur ad s dscrbd dtals as follows. Fgur : Flowchart of th data procssg to tract 05,66 vald flghts from 7,685,98 flght locatos

3 Bcaus w wr trstd US domstc flghts, w kpt,999,57 domstc pots wth th tag 0 ad fltrd out tratoal flghts wth th tag. Thr wr thus 75,599,999,57,8, 658 vald pots. A pot s vald f thr s th sam pot at th sam stat tm or f o of th four dmsos s st to NULL. Th,8,659 vald pots blog to,0 vald routs that ca b dtrd by a uqu combato of arl cod ad flght umbr. Th,0 routs ar furthr dvdd to two typs: rgular ad rrgular =.58 L (Pr(X )) 0 - =.56 Tragl sz Powr law ft Powr law ft L () Fgur : (Color ol) Bpartt powr law dstrbuto of tragl szs of th TIN To dstgush btw rgular ad rrgular routs, w plord th tm dffrc t t btw two coscutv tms ( t, t ). For ay rrgular rout that appars oly oc wth th days, dos ot chag much. It fluctuats at appromatly 5 uts, whch s th tm trval to captur flght locatos. Bcaus all th pots wr capturd whl th flghts wr srvc, for ay rgular rout, fluctuatd appromatly 5 uts whl srvc but aroud a largr valu (.g., s hours btw ths flght ad th t o) whl ot srvc. Gv th dffrc, th arthmtc ma of for ay rrgular rout ( ) s gratr tha th stadard dvato ( ),.,, whl th arthmtc ma of for ay rgular rout ( ) s far lss tha th stadard dvato ( ),..,. Usg ths statstcal proprty,.., th dffrc btw th arthmtc ma ad stadard dvato, w obtad 7,7 rgular routs ad,60 rrgular routs. Cosqutly, th 7,7 rgular routs cotad,70,55 rgular pots, whl th,60 rrgular routs cotad 8,0 rrgular pots. Thus, th prctags of rgular pots, rgular routs ad rgular flghts ar prtty hgh rspctvly 98%, 86% ad 98% as dcatd Fgur. Not that o rrgular rout s cosdrd to b o rrgular flght,.., th,60 rrgular routs qual th sam umbr of flghts. Howvr, o rgular rout cotas multpl flghts (Fgur a).th procss of drvg multpl flghts from a rout s achvd through th arthmtc ma of ad th stadard dvato wth ach rout. Thos pots wth lss tha th sum of th ma ad th stadard dvato blog to a complt flght wth th startg pot as th org ad dg pot as th dstato (c.f., Fgur b for a llustrato). Th 7,7 rgular routs fact cotad 0,0 rpatd flghts. Evtually, w obtad 05,66 vald flghts by addg th,60 rrgular flghts to th 0,0 rgular flghts.

4 0 0 L ( ) 0 Rgular rout Irrgular rout μ μ :59 08 : 08 : 5 08 : : Dat (a) Day Day Flght Flght (b) Fgur : Drvato of multpl flghts from o rout: (a) O rrgular rout (rd) ad o rgular rout cludg 9 rgular flghts (blu), ad (b) a fctv ampl of daly flghts wth th tm trvals bg prcsly 5 uts whl srvc (Not: W adopt a fctv ampl to llustrat how to drv multpl flghts from a rgular rout,., how to drv thos flght locatos as complt flghts btw th org ad th dstato. For th sak of smplcty, w assum a daly flght btw two arports lastg o hour. Evry day thr would b tm trvals (, whr,,... ), 5 for, but 60 for whch prod a flght s ot srvc. Th arthmtc ma of all tm trvals s ( 5 60) / 0.8 uts, ad th stadard dvato s 8.. Gv th fact that th tm trvals ar ot prcsly 5 uts, w ca us th sum of th arthmtc ma ad th stadard dvato ( ) = 9. to obta th cosctv pots as a complt flght joury.) Wth th 05,66 vald flghts (or mor spcfcally, th corrspodg rgular ad rrgular pots as show Fgur ), w could tract th dvdual arports for sttg up th rout graphs ad flght graphs. Evry flght cotas a org (O) ad a dstato (D), so thory thr ar, 05,66 O/D locatos. Howvr, w rtrvd oly 0,56 O/D locatos, slghtly lss tha th thortcal stmat, bcaus som O/D locatos ar shard. From th 0,56 pots, w gratd four tragulatd rrgular tworks (TIN) for four aras: th Malad, Alaska, Hawa, ad Purto Rco ad th Vrg slads. Th TIN tragl szs follow a bpartt powr law dstrbuto (Fgur ). Cosqutly, accordg to th had/tal dvso rul (Jag ad Lu 0) ad usg th arthmtc ma of th TIN tragl szs, w placd th tragls to two catgors: thos smallr tha th ma ad thos gratr tha th ma. W dsgatd thos smallr tha th ma as th arports, sc arports ar hghly crowdd wth O/D pots. Evtually, w gratd 7 arports ad dtrd th arport topologs trms of both flghts ad routs for furthr aalyss (Fgur ).

5 Fgur : (Color ol) Illustrato of data procssg from a pot cloud to 7 atural arports. Mathmatcal charactrzato of flghts or huma moblty pattrs Th ctral thm of our study s to dtr whch havy tald dstrbuto charactrzs huma moblty pattrs. Th havy tald dstrbutos rfr oft to thr basc olar rlatoshps btw quatty ad ts probablty: powr law, logormal ad potal, ad thr dgrat vrsos: powr law wth a potal cutoff ad strtchd potal (Claust, Shalz ad Nwma 009). Th focus of th work by Claust ad hs collagus was to dtct a powr law 5

6 dstrbuto ad dffrtat t from th four altratvs basd o som statstcal tsts. Thr mthods ca b summarzd by thr stps: () comput ad for a powr law ft, () coduct Kolmogorov-Smrov (KS) tst ad calculat th p valu to assss th goodss of ft, ad () comput th lklhood rato (LR) valus to compar wth altratvs cas th ft caot pass th KS tst. I ths papr, w adopt smlar mthods but do so to dtr ay havy tald dstrbuto ad dffrtat t from th altratvs (s Appd A). Lt us frst troduc th fv dstrbutos. Th powr law dstrbuto dcats a olar rlatoshp btw a quatty () ad ts probablty (y), gv by y ts smplst form, whr s usually btw ad. Ths s a dalzd prsso. I ral world data, th powr law rlatoshp appars oly for th tal whl s gratr tha a mum. Th powr law s prssd as follows: y C, [] whr C s ( ) [] Th powr law has a dgrat form,.., a powr law wth a potal cutoff. I othr words, th tal s ot a prfct powr law dstrbuto but rathr a mtur of powr law ad potal. y C, [] whr C s (, ) [] I ts smplst format, a potal rlatoshp btw ad y s prssd by y. Takg th logarthm of both sds of th prsso, w obta l y, whch mpls that th rlatoshp btw ad l y s lar. Mor grally, a potal dstrbuto s prssd as follows: y C, [5] whr C s [6] A dgrat vrso of th potal fucto s th strtchd potal,.., y C, [7] whr C s [8] Th last havy tald dstrbuto s logormal. Ltrally, logormal mpls that th logarthm of a quatty follows a ormal or Gaussa dstrbuto,.., (l ) 5 y C, [9] whr C 5 s l rfc [0] 6

7 As show th abov formulas, vry o of th havy tald dstrbutos cossts of two parts: th ma fucto that charactrzs th dstrbuto ad th costat C. Thr s a srs of paramtrs that dscrb th fuctos ad costats,..,,,,,,. Th objctv of Claust, Shalz ad Nwma (009) was to dtct a powr law dstrbuto th form of quato [] ad to dtr how to dffrtat t from altratvs th form of quatos [], [5], [7] ad [9]. Ths papr, howvr, sks a bst ft fucto for charactrzg varous proprts of huma moblty pattrs. Th mthods for dtfyg th powr law dstrbutos ca b tdd for dtfyg ay havy tald dstrbuto. Th mthods ca b usd ot oly () to fd th bst ft modls but also () to valuat how good th ft s. For task (), all of th paramtrs for th abov modls ca b computd (s Appd A). For task (), thr ar two typs of mthods for th goodss-of-ft tst. Th frst mthod s th KS tst. For a ral world datast, thr s a hypothszd modl for. Th mamum dffrc (δ) btw th cumulatv dstrbuto fucto (CDF) of th datast ad th CDF of th hypothszd modl dcats th goodss-of-ft or how clos th modl fts th ral world datast: ma f ( ) g( ), [] whr f () s th CDF of th datast wth a valu of at last ad g() s th CDF for th hypothszd modl that bst fts th datast for. Howvr, to quatfy th ft, w gratd 000 sythtc datasts accordg to th hypothszd modl. Th 000 sythszd datasts had 000 corrspodg hypothszd modls for. Followg th sam da of th mamum dffrc btw th modl ad th data, w would hav 000, dcatg th dffrcs btw th hypothszd modls ad th sythtc data. Evtually a goodss-of-ft d p was dfd as a rato of th umbr of whos valus ar gratr tha δ to 000. If th p valu s gratr tha a gv thrshold (.g., 0.0), th th hypothszd modl s accptabl, mplyg that 0 amog th 000 hav a mamum dstac gratr tha δ. For modls that could ot pass th abov KS tst, w dd altratv mthods to compar th two comptg modls. O of th most frqutly usd mthods s to calculat th lklhood rato of two modls. Bcaus ths study, th KS tst was suffct to dtty th pottal modls, w wll ot troduc th mthods; trstd radrs ca rfr to Claust, Shalz ad Nwma (009) for mor dtals.. Smulatos of huma moblty comparso wth th obsrvd W smulatd huma movmt usg movg bhavors as show Fgur 5 to ucovr th udrlyg mchasm of huma moblty pattrs. O of th mchasms s basd o gomtrc dstac (G), thr of th mchasms ar basd o topologcal proprts (T, T, ad T), ad a fal o s a prfrtal rtur (PR) suggstd by Sog t al. (00). For ach scaro or mchasm, w stup 500 movg agts, movg a rout graph or flght graph from od to aothr for about 000 tms utl th vstd tms ar hghly corrlatd to th dgr of od coctvty (.g. R squar > 0.9). To ths pot, w thk th smulato s saturatd. Through th smulatos, w obtad th smulatd travl lgths (stad of traffc flow) ad compard thm wth th obsrvd os. Not that th smulatos ar basd o th topology of th 7 arports, both th rout graphs ad th flght graphs. Th smulatd travl lgths wr was compard to th obsrvd os btw th 7 arports. Th comparso was basd o a smlar da to th o llustratd quato [],.., th 7

8 mamum dstac btw two CDF of th smulatd ad obsrvd travl lgths. W ra ach scaro 00 tms ad avragd th travl lgths for comparso to th obsrvd os. L L L L L L L L L L L L L L L (a) G (b) T (c) T 5 (d) T 7 P P 6 0 P 6 P 0 P 6 () PR Fgur 5: (Color ol) Fv scaros of smulatos dcatd by (a) G = gomtry (rout graph), (b) T = topology (rout graph), (c) T = topology (flght graph), (d) T = topology (rout graph), ad () PR = prfrtal rtur (rout graph) (NOTE: A movg agt s currtly at th blu od, ad th agt wats to mak th t mov wth a dffrt probablty as dcatd. Th gomtrc scaro s basd o gomtrc dstac,.., th closr, th bttr th probablty (pal a). Th t thr bhavors ar basd o som topologcal proprts: T s smply basd o lkag (ys/o whthr or ot thr s a flght) (pal b), T cosdrs th actual wght (how may actual flghts) (pal c), whl T cosdr how attractv ts ghbors ar (pal d). Prfrtal rtur s basd o Barabas s prfrtal attachmt (Sog t al. 00),.., thr s a hghr chac to rtur to th ods that wr prvously vstd. I pal (), all th lkd ods ar placd to catgors: th vstd ods to th rght (th tms ar dcatd by th umbrs), ad th uvstd ods to th lft (gray ods). Th frst probablty (P) s accordg to th prctag of th two catgory ods, whl th scod probablty (P) rlats to a prfrc to rtur to thos prvously vstd ods.) 5. Rsults ad dscusso W foud that huma moblty pattrs ar maly shapd by th udrlg topology of arports ad hav lttl to do wth huma movmt bhavors ad dstacs. Ths fdg s cosstt wth th rct studs (.g., Jag ad Ja 0, Ha t al. 0), but th prmtal sttgs wr rathr dffrt. For ampl, th two prvous studs dalt wth smulatos: th formr for strtcostrad movmt, th lattr work for smulatg movmt som dalzd topology or tworks. Th currt study s cosdrd to b comprhsv bcaus t covrs () massv data procssg, () mathmatcal charactrzato of th obsrvd moblty pattrs, ad () agt-basd smulatos of dffrt movmt to compar wth th obsrvd flow or pattrs. I what follows, w rport th rsults rlatd to thos thr ma topcs. 8

9 Th dtald data procssg s dscrbd dtals th abov Scto. A ot-worthy rsult of th data procssg s that th had/tal dvso rul (Jag ad Lu 0) s applcabl for dlatg arports. Th had/tal dvso rul stats that for gv a varabl X, f ts valus follow a havytald dstrbuto, th th ma (m) of th valus ca dvd all th valus to two parts: a hgh prctag th tal ad a low prctag th had. It should b otd that th havy-tald dstrbuto s obtad by plottg rakg a dcrasg ordr as th -as, ad th corrspodg valus as th y-as, so-calld rak-sz plot or Zpf plot. Th two parts, or both th had ad th tal, corrspod wll to huma cogto about ral world phoma, such as rch ad poor, rcsso ad prosprty, urba ad rural, just to am a fw ampls. Ths rul was tally usd to dlat cty boudars wh t was frst formulatd. Hr, th applcato of th rul provds furthr vdc for ts usfulss. Not that th arports ar aturally dtfd dpdg o th dsty of O/D pots so-calld atural arports. Th atural arport boudars may dvat from th ral os, but th boudars ar suffctly accurat to st up arport rlatoshps or topology L (Pr(X )) Traffc volum Powr law ft L () Fgur 6: (Color ol) Powr law dstrbuto of traffc volum W foud that topologcal proprts, cludg traffc volum (flght umbrs btw arports) ad dgr of coctvty (umbr of flghts arrvg or dpartg from th dvdual arports), show a powr law dstrbuto. Fgur 6 llustrats th powr law dstrbuto a doubl logarthm plot:.56 y 8* ( 9) wth th KS tst d p = 0.. To furthr llustrat th hrarchy of traffc volum, w rducd t to dffrt lvls of dtal accordg to th had/tal dvso rul (c.f., Fgur 7). Both th dgr ad outdgr hbt a strkg powr law dstrbuto wth slghtly dffrt.7 paramtr sttgs: y 0.68* ( 06) wth th KS tst d p = 0.0, ad.67 y.0* ( 8) wth th KS tst d p = 0.05 (Fgur 8). 9

10 Fgur 7: (Color ol) Four lvls of hrarchy of traffc volum (NOTE: Th frst lvl rprsts th most dtald lvl, whch all th routs wth at last o flght ar show togthr wth th rlatd arports or ods. Th scod lvl s obtad from th frst lvl by slctg thos lks wth mor tha th ma umbr (9) of flghts. Ths sam procdur cotus rcursvly for drvg th thrd ad fourth lvls. Th szs of th ods dcat th magtud of dgr, whch s hghly corrlatd wth that of th outdgr.) 0

11 0 0 L (Pr(X )) Idgr Powr law ft Outdgr Powr law ft L () Fgur 8: (Color ol) Powr law dstrbutos of arport dgrs W foud that huma travl lgths dmostrat a potal dstrbuto wth a powr law cutoff,.., ( 9000 km) p 0. y ( 9000 km) p 0.5 Ths rsult dcats that th dstrbuto s potal for travl lgths lss tha 9000 km, whras t s a powr law for travl lgths gratr tha 9000 km (Fgur 9). It should b otd that th powr law part cotas oly 8 flghts (whch ca b gord du to suffct statstcs), whl th potal part cotas 05,5 flghts. Ths rsult s vry dffrt from th arly fdg, whch clams that huma travl lgths dmostrat a powr law wth a potal cutoff (Brockma, Hufag ad Gsl 006, Gozalz, Hdalgo ad Barabás 008, Jag, Y ad Zhao 009). I othr words, for thos short lgths lss tha th thrshold, thr s a powr law dstrbuto, whl for log os, thr s a potal dstrbuto. Ths cocluso s oppost from our fdg. 0 0 L (Pr(X )) L (Pr(X )) L (Pr(X )) Flght lgth 9000Km Epotal ft Flght lgth 9000Km Powr law ft L () L () Fgur 9: (Color ol) Epotal dstrbuto wth a powr law cutoff for travl lgth

12 Not that th abov fdgs ar basd o a flght graph whos lks ar wghtd by th umbr of flghts. Howvr, arlr studs ar maly basd o a rout graph that s a bary graph th rlato btw arports s thr or 0 (.g., Gumrà ad Amaral 00, Gumrà t al. 005). I othr words, thr was o traffc volum formato volvd th arlr studs. Th arport topology usd th prvous studs s purly topologcal,.., ay two arports wth a lk as log as thr s o flght rgardlss of th umbr of flghts. Our arport topology s wghtd,.., th lk s wghtd by th umbr of flghts. A bary rout graph caot fully charactrz huma movmt pattrs or flght pattrs. Nvrthlss, w rducd th flght graph to a rout graph ad ad both th topologcal ad gomtrc proprts. W foud that wth th bary rout graph both dgr ad btwss ctralts hbt a powr law dstrbuto wth a potal cutoff. Ths rsult rgardg th bary rout graph s cosstt wth arlr studs (.g., Gumrà ad Amaral 00, Gumrà t al. 005). Th rout lgths dmostrat a potal dstrbuto,.., 0.00 y 0.00 ( 768) wth th KS tst d p = 0.8 (Fgur 0). If w tak th rout lgths as a proy for travl lgths, th th rsult s also dffrt from what was rportd th ltratur that clams a powr law or powr law wth a potal cutoff (Brockma, Hufag ad Gsl 006, Gozalz, Hdalgo ad Barabás 008, Jag, Y ad Zhao 009). Aothr trstg fdg s th rch club phomo obsrvd wth th bary rout graph,.., th top 50 arports costtut a arly complt graph wth at last routs to othr arports L (Pr(X )) Rout lgth Epotal ft Fgur 0: (Color ol) Epotal dstrbuto of rout lgths Through agt-basd smulatos of huma moblty (c.f., Scto ad Fgur 5), w foud that th travl lgths wth scaro T, basd o th rout graph ad radom movg bhavor, bst match th obsrvd travl lgths. T s squtally followd by T, PR, T ad G trms of matchg dgr. Ths rsult s coutr-tutv bcaus w avly td to blv that th othr two topologcally basd scaros T ad T would hav a bttr ffct rplcatg th obsrvd travl lgths. Scaro T s basd o th d facto flght graph, whl scaro T cosdrs how attractv th ghbors ar. Th scaro basd o prfrtal rtur s good but ot th bst. Ths fdg llustrats th udrlyg topologcal structur (th bary o rathr tha th wghtd o), ad radom moto ca dscrb th movmt pattrs wll. I othr words, huma movmt pattrs hav lttl to do wth gomtrc factors or movg bhavor. 6. Cocluso Massv trackg data of flghts provd a w mas of studyg huma moblty pattrs. I ths papr, w assum US flghts to b a proy for huma movmt at th coutry lvl. From th massv locato formato of US flghts wth a -day prod, w tractd dvdual routs, flghts ad arports ad stup both flght graphs ad rout graphs for plorg th moblty pattrs. Th rsultg data ar publshd togthr wth th papr. It s foud that topologcal proprts, such as

13 traffc volum ad arport dgrs, ar dd powr-law dstrbutd. Travl lgths hbt a potal dstrbuto wth a powr law cutoff rathr tha a powr law dstrbuto wth a potal cutoff as prvous studs llustratd. To ucovr th udrlyg mchasms, w costructd varous smulato scaros basd o both flght graphs ad rout graphs ad foud that rout graphs wth a radom-moto bhavor rplcat th obsrvd travl lgths pattr. Ths fdg dcats that huma movmt pattrs at a collctv lvl ar maly shapd by th udrlyg structur th smplst topology rprstd by th bary rout graph. Ackowldgmts Th flght data was collctd by Flytcomm Ic., ad w ar gratful for thr prmsso to us t ths papr. Rfrcs: Brockma D., Hufag L., ad Gsl T. (006), Th scalg laws of huma travl, Natur, 9, Claust A., Shalz C. R., ad Nwma M. E. J. (009), Powr-law dstrbutos mprcal data, SIAM Rvw, 5, Gozalz M., Hdalgo C. A., ad Barabás A.-L. (008), Udrstadg dvdual huma moblty pattrs, Natur, 5, Gumrà R. ad Amaral L. A. N. (00), Modlg th world-wd arport twork, Th Europa Physcal Joural B, 8(), Gumrà R., Mossa S., Turtsch A. ad Amaral L. A. N. (005), Th worldwd ar trasportato twork: Aomalous ctralty, commuty structur, ad cts' global rols, Procdgs of th Natoal Acadmy of Sccs of th Utd Stats of Amrca, 0(), Hägrstrad T. (970), What about popl rgoal scc? Paprs of th Rgoal Scc Assocato,, 7. Ha X., Hao Q., Wag B. ad Zhou T. (0), Org of th scalg law huma moblty: Hrarchy of traffc systms, Physcal Rvw E, 8, 067. Hllr B., P A., Haso J., Grajwsk T. ad Xu J. (99), Natural movmt: cofgurato ad attracto urba pdstra movmt, Evromt ad Plag B: Plag ad Dsg, 0, Hufagl L., Brockma D. ad Gsl T. (00), Forcast ad cotrol of pdmcs a globalzd world, Procdgs of th Natoal Acadmy of Sccs, 0(), Jag B. ad Ja T. (0), Agt-basd smulato of huma movmt shapd by th udrlyg strt structur, Itratoal Joural of Gographcal Iformato Scc, 5(), 5 6. Jag B. ad Lu X. (0), Scalg of gographc spac from th prspctv of cty ad fld blocks ad usg volutrd gographc formato, Itratoal Joural of Gographcal Iformato Scc,, -, Prprt, arv.org/abs/ Jag B., Y J. ad Zhao S. (009), Charactrzg huma moblty pattrs a larg strt twork, Physcal Rvw E, 80, 06. L K., Hog S., Km S. J., Rh I. ad Chog S. (009), SLAW: A moblty modl for huma walks, IEEE INFOCOM 009, IEEE. Roth C., Kag S. M., Batty M, ad Barthélmy M. (0), Structur of urba movmts: Polyctrc actvty ad tagld hrarchcal flows, PLoS ONE, 6(), 59. Sog C., Kor T., Wag P. ad Barabás A. (00), Modllg th scalg proprts of huma moblty, Natur Physcs, DOI: 0.08/NPHYS760. Ypma T. J. (995), Hstorcal dvlopmt of th Nwto-Raphso mthod, SIAM Rvw, 7(), 5 55.

14 Appd A: Estmato of th paramtrs for som havy tald dstrbutos basd o th mamum lklhood mthod Basd o th mthods suggstd by Claust, Shalz ad Nwma (009) for dtctg a powr law dstrbuto, ths appd, w prst varous procdurs for stmatg th paramtrs of th othr four havy tald, cotuous dstrbutos. Th prmary mthod usd s th mamum lklhood mthod.. Mamum lklhood stmato for th cotuous potal dstrbuto. Th gral form of th cotuous potal dstrbuto ca b dscrbd by y C [.] whr λ s th rat paramtr ( 0 ) ad C s th ormalzg costat.. Calculatg th ormalzg costat C It s obvous that y dvrgs as 0 ; thus, th abov quato dos ot hold for all valus of. Thr must b a lowr boud for th potal dstrbuto. Supposg that ad λ ar kow, w ca asly drv th ormalzg costat C. To fd th ormalzg costat, w us th fact that Thus, Fally, C d [.] C C C C d( ) [.] [.] [.5] [.6]. Estmatg th rat paramtr Now suppos, gv a mprcal datast cotag obsrvatos (,,..., ), w wat to kow th probablty that ths datast s draw from th cotuous potal dstrbuto modl. Ths probablty s also kow as th lklhood, ad t s dscrbd by Thus, ths cas, L y ( ) ( ) [.7] L. [.8] W ow wsh to fd th valu of that mamzs L (). Mathmatcally, ths valu ca b obtad by sttg th drvatv dl ( ) d qual to 0 ad solvg for. Howvr, t s tdous to fd th drvatv of L () bcaus t s a product of fuctos. Hc, w adopt th atural logarthm form of L () bcaus t s asr to fd th valu of that mamzs L [ L( )]. W hav

15 L[ L( )] L. [.9] Th drvatv of L [ L( )] wth rspct to s dl[ L( )] d. [.0] Thus, th valu of that mamzs L [ L( )] s th soluto of th quato 0. [.] Solvg, w obta th stmats ˆ as ˆ. [.]. Mamum lklhood stmato for th cotuous strtchd potal dstrbuto. Th gral form of th cotuous strtchd potal dstrbuto ca b dscrbd as: y C [.] whr s th rat paramtr ( 0 ), s th strtchg pot ( 0 ) ad C s th ormalzg costat. For, t dgrats to a potal dstrbuto as dscussd abov.. Calculat th ormalzg costat C To calculat th ormalzg costat C, w mpos a lowr boud for th strtchd potal dstrbuto. Lt us assum that, ad ar kow; w ca asly drv th ormalzg costat C. To fd th ormalzg costat, w us th fact that Thus, Fally, C C C C d d( ), [.] [.] [.], [.5] C, [.6]. Estmatg th rat paramtr ad strtchg pot 5

16 Now suppos, gv a mprcal datast cotag obsrvatos (,,..., ), w wat to kow th lklhood that ths datast s draw from th cotuous strtchd potal dstrbuto modl. I ths cas, th lklhood s gv by Furthrmor, ( ) L(, ), [.7] L L[ L(, )] L L ( ). [.8] Th mamum lklhood stmators of ad ar th valus that mamz L [ L(, )]. Takg drvatvs wth rspct to both ad, w obta ad L( L(, ))) ( L( L(, ))) ( L L L [.9]. [.0] Sttg th abov two drvatvs qual to 0, w obta th followg systm of quatos, L 0 L L 0. [.] Solvg th frst quato, w obta ˆ ˆ ˆ [ ]. [.] Substtutg ˆ for th scod quato, w obta ˆ ˆ ˆ ˆ L [ ] ( ) 0 L L ˆ. [.] Notc that th lft sd of th abov quato s kow as f (ˆ ), ad our goal s to fd th valu of ˆ that maks ths fucto qual to 0. Howvr, t s dffcult to solv t drctly to obta th valu of ˆ bcaus t s dffcult to drv th vrs fucto of f (ˆ ) as ˆ f (, ). Hc, w us th smpl Nwto Raphso mthod (Ypma, 995) to drv th soluto to f (ˆ ). Oc th valu of ˆ s dtrd, th valu of ˆ s also dtrd. Th Nwto Raphso mthod s usd for fdg succssvly bttr appromatos to th roots of a fucto f. Itally, w gv a stmato of th root 0 that s rasoably clos to th tru root. Th, w draw a tagt l of th fucto f at ths stmato pot, ad th trscto pot btw ths tagt l ad th -as s dtrd as th scod stmato of th root, whch s cosdrd to b a bttr appromato. Aftr svral tratos, f th currt stmato satsfs our accuracy rqurmt, th ths procss s tratd; othrws, ths procss s rpatd utl a 6

17 rasoabl accuracy s accptd. Not that th drvatv of th fucto f should b calculatd drctly bcaus th tagt l must b costructd at th stmato pot. Th followg fgur llustrats ths mthod. Fgur A: (Color ol) Illustrato of th Nwto Raphso mthod Basd o ths mthod, frstly, w st th tal valu of ˆ as th pot valu of a pur powr law dstrbuto fttd by th obsrvd datast. Th, w obta th drvatv of ths fucto, ' [ f ( ˆ) ˆ ˆ L ˆ L ]( ˆ ( ˆ ˆ ) ) [ ˆ L [.] Nt, followg th stps of Nwto Raphso mthod, w ca calculat th t bttr stmato valu of ˆ wth th formula ˆ ˆ f ( ˆ). [.5] ' f ( ˆ) Fally, ths procdur wll b tratd f f ˆ ), [.6] ( whr s th accptabl rror. Othrws, ths procdur must b tratd utl ths codto s satsfd. ˆ L ]. Mamum lklhood stmato for th cotuous logormal dstrbuto. Th gral form of th cotuous logormal dstrbuto ca b dscrbd by y ( C /( ))p( ( L ) / ), [.] 5 whr s th ma valu, s th stadard dvato valu ad C 5 s th ormalzg costat. 7

18 . Calculatg th ormalzg costat C 5 To calculat th ormalzg costat C 5, w mpos a lowr boud o th logormal dstrbuto. Lt us assum that, ad ar kow. Th, w ca asly drv th ormalzg costat C 5. To fd th ormalzg costat, w us th fact that ( C /( ))p( ( L ) / ) d. [.] 5 Thus, C 5 p( ( ) / ) ( ) L L d C5 L rfc( ) C5 L rfc( ) [.] [.]. [.5] Fally, L 5 [ ( )] C rfc, [.6] whr rfc( ) t dt. [.7]. Estmatg th ma paramtr ad th stadard dvato paramtr pot Suppos that, gv a mprcal datast cotag obsrvatos (,,..., ), w wat to kow th lklhood that ths datast s draw from th cotuous logormal dstrbuto modl. I ths cas, th lklhood s gv by L ( L ) t, ) p( )[ L dt], [.8] ( Furthrmor, L [ L(, )] ( L ) L L L( L t dt) Th mamum lklhood stmators of ad ar th valus that mamz L [ L(, )]. Hr, w adopt th tchqu provdd by th R packag to obta th stmato valu of ad bcaus t s ot covt to us th sam stratgy as th cas of th strtchd potal dstrbuto to hadl th abov complcatd log lklhood fucto. [.9] 8

19 R s a collcto of powrful packags that s usd for data mapulato, calculato ad graphcal dsplay. It ca b usd as a statstcal systm that mplmts a rch st of classcal ad modr statstcal tchqus. Th problm hr of obtag a stmat for th valu of ad to mamz L [ L(, )] ca b tratd as a problm of olar optmzato. I R, th fucto lm() s usd to carry out a mzato of th objctv fucto f basd o a Nwto-typ algorthm. Thrfor, our problm ca b solvd as a mzato of th gatv L [ L(, )], ad th procdur s dmostratd wth th followg psudo-cod. Fucto LogormalFt (, thrshold) St = ( thrshold) Guss th tal valu of both ad usg Ma( L( )) St stmato = lm ( f L[ L(, )], p (, )) Rtur stmato Ed Fucto ad Std( L( )) whr th varabl stmato rturs th bst stmato valu for both ad.. Mamum lklhood stmato for th cotuous powr law dstrbuto wth potal cutoff. Th gral form of th cotuous logormal dstrbuto ca b dscrbd by y C, [.] whr s th powr law pot paramtr, s th potal rat paramtr ad C s th ormalzg costat.. Calculatg th ormalzg costat C To calculat th ormalzg costat C, w mpos a lowr boud o th powr law dstrbuto wth a potal cutoff. Lt us assum that, ad ar kow. Th, w ca asly drv th costat C. To fd th ormalzg costat, w us th fact that Thus, C d C ( ) p( ) d( ). [.]. [.] Substtutg t for, Substtutg C t p( t) dt. [.] for a, a a C t p( t) dt. [.5] Th, a C ( a) ( a) ( a, )]. [.6] [ 9

20 Aga, substtutg a for, ad fally, whr c ( )[ (, )], [.7] t t 0 ( ) dt, [.8] ad t t dt 0 (, ). [.9] ( ). Estmatg th powr law pot paramtr ad th potal rat paramtr Suppos that, gv a mprcal datast cotag obsrvatos (,,..., ), w wat to kow th lklhood that ths datast s draw from th cotuous powr law dstrbuto wth a potal cutoff modl. I ths cas, th lklhood s gv by Furthrmor, L(, ). [.0] ( )[ (, )] L L [ L (, )] ( ) L L [ ( )[ (, )]] [.] Th mamum lklhood stmators of ad ar th valus that mamz L [ L(, )]. Howvr, bcaus of th complty of th abov log lklhood fucto, w adopt th sam stratgy as th cas of th logormal dstrbuto. O small dffrc s that hr w us th fucto CostrOptm() R to carry out a mzato of th objctv fucto f wth th costrats o th rag of paramtrs. Thrfor, our problm ca b solvd as a mzato of th gatv L [ L(, )] wth paramtr costrats, ad th procdur s dmostratd wth th followg psudo-cod. Fucto PowrlawEpFt (, thrshold) St = ( thrshold) Guss th tal valu of by fttg to a pur powr law dstrbuto Guss th tal valu of by fttg to a pur potal dstrbuto St th costrats as ad 0 St stmato = CostrOpt m( f L[ L(, )], p (, ), costrats) Rtur stmato Ed Fucto Whr varabl stmato rturs th bst stmato valu for both ad. 0

Introduction to logistic regression

Introduction to logistic regression Itroducto to logstc rgrsso Gv: datast D { 2 2... } whr s a k-dmsoal vctor of ral-valud faturs or attrbuts ad s a bar class labl or targt. hus w ca sa that R k ad {0 }. For ampl f k 4 a datast of 3 data

More information

On Estimation of Unknown Parameters of Exponential- Logarithmic Distribution by Censored Data

On Estimation of Unknown Parameters of Exponential- Logarithmic Distribution by Censored Data saqartvlos mcrbata rovul akadms moamb, t 9, #2, 2015 BULLETIN OF THE GEORGIAN NATIONAL ACADEMY OF SCIENCES, vol 9, o 2, 2015 Mathmatcs O Estmato of Ukow Paramtrs of Epotal- Logarthmc Dstrbuto by Csord

More information

Reliability of time dependent stress-strength system for various distributions

Reliability of time dependent stress-strength system for various distributions IOS Joural of Mathmatcs (IOS-JM ISSN: 78-578. Volum 3, Issu 6 (Sp-Oct., PP -7 www.osrjourals.org lablty of tm dpdt strss-strgth systm for varous dstrbutos N.Swath, T.S.Uma Mahswar,, Dpartmt of Mathmatcs,

More information

3.4 Properties of the Stress Tensor

3.4 Properties of the Stress Tensor cto.4.4 Proprts of th trss sor.4. trss rasformato Lt th compots of th Cauchy strss tsor a coordat systm wth bas vctors b. h compots a scod coordat systm wth bas vctors j,, ar gv by th tsor trasformato

More information

Introduction to logistic regression

Introduction to logistic regression Itroducto to logstc rgrsso Gv: datast D {... } whr s a k-dmsoal vctor of ral-valud faturs or attrbuts ad s a bar class labl or targt. hus w ca sa that R k ad {0 }. For ampl f k 4 a datast of 3 data pots

More information

Unbalanced Panel Data Models

Unbalanced Panel Data Models Ubalacd Pal Data odls Chaptr 9 from Baltag: Ecoomtrc Aalyss of Pal Data 5 by Adrás alascs 4448 troducto balacd or complt pals: a pal data st whr data/obsrvatos ar avalabl for all crosssctoal uts th tr

More information

Second Handout: The Measurement of Income Inequality: Basic Concepts

Second Handout: The Measurement of Income Inequality: Basic Concepts Scod Hadout: Th Masurmt of Icom Iqualty: Basc Cocpts O th ormatv approach to qualty masurmt ad th cocpt of "qually dstrbutd quvalt lvl of com" Suppos that that thr ar oly two dvduals socty, Rachl ad Mart

More information

Suzan Mahmoud Mohammed Faculty of science, Helwan University

Suzan Mahmoud Mohammed Faculty of science, Helwan University Europa Joural of Statstcs ad Probablty Vol.3, No., pp.4-37, Ju 015 Publshd by Europa Ctr for Rsarch Trag ad Dvlopmt UK (www.ajourals.org ESTIMATION OF PARAMETERS OF THE MARSHALL-OLKIN WEIBULL DISTRIBUTION

More information

Binary Choice. Multiple Choice. LPM logit logistic regresion probit. Multinomial Logit

Binary Choice. Multiple Choice. LPM logit logistic regresion probit. Multinomial Logit (c Pogsa Porchawssul, Faculty of Ecoomcs, Chulalogor Uvrsty (c Pogsa Porchawssul, Faculty of Ecoomcs, Chulalogor Uvrsty 3 Bary Choc LPM logt logstc rgrso probt Multpl Choc Multomal Logt (c Pogsa Porchawssul,

More information

Lecture 1: Empirical economic relations

Lecture 1: Empirical economic relations Ecoomcs 53 Lctur : Emprcal coomc rlatos What s coomtrcs? Ecoomtrcs s masurmt of coomc rlatos. W d to kow What s a coomc rlato? How do w masur such a rlato? Dfto: A coomc rlato s a rlato btw coomc varabls.

More information

Department of Mathematics and Statistics Indian Institute of Technology Kanpur MSO202A/MSO202 Assignment 3 Solutions Introduction To Complex Analysis

Department of Mathematics and Statistics Indian Institute of Technology Kanpur MSO202A/MSO202 Assignment 3 Solutions Introduction To Complex Analysis Dpartmt of Mathmatcs ad Statstcs Ida Isttut of Tchology Kapur MSOA/MSO Assgmt 3 Solutos Itroducto To omplx Aalyss Th problms markd (T) d a xplct dscusso th tutoral class. Othr problms ar for hacd practc..

More information

Total Prime Graph. Abstract: We introduce a new type of labeling known as Total Prime Labeling. Graphs which admit a Total Prime labeling are

Total Prime Graph. Abstract: We introduce a new type of labeling known as Total Prime Labeling. Graphs which admit a Total Prime labeling are Itratoal Joural Of Computatoal Egrg Rsarch (crol.com) Vol. Issu. 5 Total Prm Graph M.Rav (a) Ramasubramaa 1, R.Kala 1 Dpt.of Mathmatcs, Sr Shakth Isttut of Egrg & Tchology, Combator 641 06. Dpt. of Mathmatcs,

More information

Bayesian Shrinkage Estimator for the Scale Parameter of Exponential Distribution under Improper Prior Distribution

Bayesian Shrinkage Estimator for the Scale Parameter of Exponential Distribution under Improper Prior Distribution Itratoal Joural of Statstcs ad Applcatos, (3): 35-3 DOI:.593/j.statstcs.3. Baysa Shrkag Estmator for th Scal Paramtr of Expotal Dstrbuto udr Impropr Pror Dstrbuto Abbas Najm Salma *, Rada Al Sharf Dpartmt

More information

Numerical Method: Finite difference scheme

Numerical Method: Finite difference scheme Numrcal Mthod: Ft dffrc schm Taylor s srs f(x 3 f(x f '(x f ''(x f '''(x...(1! 3! f(x 3 f(x f '(x f ''(x f '''(x...(! 3! whr > 0 from (1, f(x f(x f '(x R Droppg R, f(x f(x f '(x Forward dffrcg O ( x from

More information

MODEL QUESTION. Statistics (Theory) (New Syllabus) dx OR, If M is the mode of a discrete probability distribution with mass function f

MODEL QUESTION. Statistics (Theory) (New Syllabus) dx OR, If M is the mode of a discrete probability distribution with mass function f MODEL QUESTION Statstcs (Thory) (Nw Syllabus) GROUP A d θ. ) Wrt dow th rsult of ( ) ) d OR, If M s th mod of a dscrt robablty dstrbuto wth mass fucto f th f().. at M. d d ( θ ) θ θ OR, f() mamum valu

More information

LECTURE 6 TRANSFORMATION OF RANDOM VARIABLES

LECTURE 6 TRANSFORMATION OF RANDOM VARIABLES LECTURE 6 TRANSFORMATION OF RANDOM VARIABLES TRANSFORMATION OF FUNCTION OF A RANDOM VARIABLE UNIVARIATE TRANSFORMATIONS TRANSFORMATION OF RANDOM VARIABLES If s a rv wth cdf F th Y=g s also a rv. If w wrt

More information

Weights Interpreting W and lnw What is β? Some Endnotes = n!ω if we neglect the zero point energy then ( )

Weights Interpreting W and lnw What is β? Some Endnotes = n!ω if we neglect the zero point energy then ( ) Sprg Ch 35: Statstcal chacs ad Chcal Ktcs Wghts... 9 Itrprtg W ad lw... 3 What s?... 33 Lt s loo at... 34 So Edots... 35 Chaptr 3: Fudatal Prcpls of Stat ch fro a spl odl (drvato of oltza dstrbuto, also

More information

Almost all Cayley Graphs Are Hamiltonian

Almost all Cayley Graphs Are Hamiltonian Acta Mathmatca Sca, Nw Srs 199, Vol1, No, pp 151 155 Almost all Cayly Graphs Ar Hamltoa Mg Jxag & Huag Qogxag Abstract It has b cocturd that thr s a hamltoa cycl vry ft coctd Cayly graph I spt of th dffculty

More information

A COMPARISON OF SEVERAL TESTS FOR EQUALITY OF COEFFICIENTS IN QUADRATIC REGRESSION MODELS UNDER HETEROSCEDASTICITY

A COMPARISON OF SEVERAL TESTS FOR EQUALITY OF COEFFICIENTS IN QUADRATIC REGRESSION MODELS UNDER HETEROSCEDASTICITY Colloquum Bomtrcum 44 04 09 7 COMPISON OF SEVEL ESS FO EQULIY OF COEFFICIENS IN QUDIC EGESSION MODELS UNDE HEEOSCEDSICIY Małgorzata Szczpa Dorota Domagała Dpartmt of ppld Mathmatcs ad Computr Scc Uvrsty

More information

Independent Domination in Line Graphs

Independent Domination in Line Graphs Itratoal Joural of Sctfc & Egrg Rsarch Volum 3 Issu 6 Ju-1 1 ISSN 9-5518 Iddt Domato L Grahs M H Muddbhal ad D Basavarajaa Abstract - For ay grah G th l grah L G H s th trscto grah Thus th vrtcs of LG

More information

COMPLEX NUMBERS AND ELEMENTARY FUNCTIONS OF COMPLEX VARIABLES

COMPLEX NUMBERS AND ELEMENTARY FUNCTIONS OF COMPLEX VARIABLES COMPLEX NUMBERS AND ELEMENTARY FUNCTIONS OF COMPLEX VARIABLES DEFINITION OF A COMPLEX NUMBER: A umbr of th form, whr = (, ad & ar ral umbrs s calld a compl umbr Th ral umbr, s calld ral part of whl s calld

More information

Math Tricks. Basic Probability. x k. (Combination - number of ways to group r of n objects, order not important) (a is constant, 0 < r < 1)

Math Tricks. Basic Probability. x k. (Combination - number of ways to group r of n objects, order not important) (a is constant, 0 < r < 1) Math Trcks r! Combato - umbr o was to group r o objcts, ordr ot mportat r! r! ar 0 a r a s costat, 0 < r < k k! k 0 EX E[XX-] + EX Basc Probablt 0 or d Pr[X > ] - Pr[X ] Pr[ X ] Pr[X ] - Pr[X ] Proprts

More information

Counting the compositions of a positive integer n using Generating Functions Start with, 1. x = 3 ), the number of compositions of 4.

Counting the compositions of a positive integer n using Generating Functions Start with, 1. x = 3 ), the number of compositions of 4. Coutg th compostos of a postv tgr usg Gratg Fuctos Start wth,... - Whr, for ampl, th co-ff of s, for o summad composto of aml,. To obta umbr of compostos of, w d th co-ff of (...) ( ) ( ) Hr for stac w

More information

The R Package PK for Basic Pharmacokinetics

The R Package PK for Basic Pharmacokinetics Wolfsggr, h R Pacag PK St 6 h R Pacag PK for Basc Pharmacotcs Mart J. Wolfsggr Dpartmt of Bostatstcs, Baxtr AG, Va, Austra Addrss of th author: Mart J. Wolfsggr Dpartmt of Bostatstcs Baxtr AG Wagramr Straß

More information

A Stochastic Approximation Iterative Least Squares Estimation Procedure

A Stochastic Approximation Iterative Least Squares Estimation Procedure Joural of Al Azhar Uvrst-Gaza Natural Sccs, 00, : 35-54 A Stochastc Appromato Itratv Last Squars Estmato Procdur Shahaz Ezald Abu- Qamar Dpartmt of Appld Statstcs Facult of Ecoomcs ad Admstrato Sccs Al-Azhar

More information

Aotomorphic Functions And Fermat s Last Theorem(4)

Aotomorphic Functions And Fermat s Last Theorem(4) otomorphc Fuctos d Frmat s Last Thorm(4) Chu-Xua Jag P. O. Box 94 Bg 00854 P. R. Cha agchuxua@sohu.com bsract 67 Frmat wrot: It s mpossbl to sparat a cub to two cubs or a bquadrat to two bquadrats or gral

More information

A Measure of Inaccuracy between Two Fuzzy Sets

A Measure of Inaccuracy between Two Fuzzy Sets LGRN DEMY OF SENES YERNETS ND NFORMTON TEHNOLOGES Volum No 2 Sofa 20 Masur of accuracy btw Two Fuzzy Sts Rajkumar Vrma hu Dv Sharma Dpartmt of Mathmatcs Jayp sttut of formato Tchoy (Dmd vrsty) Noda (.P.)

More information

Correlation in tree The (ferromagnetic) Ising model

Correlation in tree The (ferromagnetic) Ising model 5/3/00 :\ jh\slf\nots.oc\7 Chaptr 7 Blf propagato corrlato tr Corrlato tr Th (frromagtc) Isg mol Th Isg mol s a graphcal mol or par ws raom Markov fl cosstg of a urct graph wth varabls assocat wth th vrtcs.

More information

Tolerance Interval for Exponentiated Exponential Distribution Based on Grouped Data

Tolerance Interval for Exponentiated Exponential Distribution Based on Grouped Data Itratoal Rfrd Joural of Egrg ad Scc (IRJES) ISSN (Ol) 319-183X, (Prt) 319-181 Volum, Issu 10 (Octobr 013), PP. 6-30 Tolrac Itrval for Expotatd Expotal Dstrbuto Basd o Groupd Data C. S. Kaad 1, D. T. Shr

More information

Repeated Trials: We perform both experiments. Our space now is: Hence: We now can define a Cartesian Product Space.

Repeated Trials: We perform both experiments. Our space now is: Hence: We now can define a Cartesian Product Space. Rpatd Trals: As w hav lood at t, th thory of probablty dals wth outcoms of sgl xprmts. I th applcatos o s usually trstd two or mor xprmts or rpatd prformac or th sam xprmt. I ordr to aalyz such problms

More information

The real E-k diagram of Si is more complicated (indirect semiconductor). The bottom of E C and top of E V appear for different values of k.

The real E-k diagram of Si is more complicated (indirect semiconductor). The bottom of E C and top of E V appear for different values of k. Modr Smcoductor Dvcs for Itgratd rcuts haptr. lctros ad Hols Smcoductors or a bad ctrd at k=0, th -k rlatoshp ar th mmum s usually parabolc: m = k * m* d / dk d / dk gatv gatv ffctv mass Wdr small d /

More information

Consistency of the Maximum Likelihood Estimator in Logistic Regression Model: A Different Approach

Consistency of the Maximum Likelihood Estimator in Logistic Regression Model: A Different Approach ISSN 168-8 Joural of Statstcs Volum 16, 9,. 1-11 Cosstcy of th Mamum Lklhood Estmator Logstc Rgrsso Modl: A Dffrt Aroach Abstract Mamuur Rashd 1 ad Nama Shfa hs artcl vstgats th cosstcy of mamum lklhood

More information

ASYMPTOTIC AND TOLERANCE 2D-MODELLING IN ELASTODYNAMICS OF CERTAIN THIN-WALLED STRUCTURES

ASYMPTOTIC AND TOLERANCE 2D-MODELLING IN ELASTODYNAMICS OF CERTAIN THIN-WALLED STRUCTURES AYMPTOTIC AD TOLERACE D-MODELLIG I ELATODYAMIC OF CERTAI THI-WALLED TRUCTURE B. MICHALAK Cz. WOŹIAK Dpartmt of tructural Mchacs Lodz Uvrsty of Tchology Al. Poltrchk 6 90-94 Łódź Polad Th objct of aalyss

More information

Chiang Mai J. Sci. 2014; 41(2) 457 ( 2) ( ) ( ) forms a simply periodic Proof. Let q be a positive integer. Since

Chiang Mai J. Sci. 2014; 41(2) 457 ( 2) ( ) ( ) forms a simply periodic Proof. Let q be a positive integer. Since 56 Chag Ma J Sc 0; () Chag Ma J Sc 0; () : 56-6 http://pgscccmuacth/joural/ Cotrbutd Papr Th Padova Sucs Ft Groups Sat Taș* ad Erdal Karaduma Dpartmt of Mathmatcs, Faculty of Scc, Atatürk Uvrsty, 50 Erzurum,

More information

Machine Learning. Principle Component Analysis. Prof. Dr. Volker Sperschneider

Machine Learning. Principle Component Analysis. Prof. Dr. Volker Sperschneider Mach Larg Prcpl Compot Aalyss Prof. Dr. Volkr Sprschdr AG Maschlls Lr ud Natürlchsprachlch Systm Isttut für Iformatk chsch Fakultät Albrt-Ludgs-Uvrstät Frburg sprschdr@formatk.u-frburg.d I. Archtctur II.

More information

Odd Generalized Exponential Flexible Weibull Extension Distribution

Odd Generalized Exponential Flexible Weibull Extension Distribution Odd Gralzd Epotal Flbl Wbull Etso Dstrbuto Abdlfattah Mustafa Mathmatcs Dpartmt Faculty of Scc Masoura Uvrsty Masoura Egypt abdlfatah mustafa@yahoo.com Bh S. El-Dsouy Mathmatcs Dpartmt Faculty of Scc Masoura

More information

On the Possible Coding Principles of DNA & I Ching

On the Possible Coding Principles of DNA & I Ching Sctfc GOD Joural May 015 Volum 6 Issu 4 pp. 161-166 Hu, H. & Wu, M., O th Possbl Codg Prcpls of DNA & I Chg 161 O th Possbl Codg Prcpls of DNA & I Chg Hupg Hu * & Maox Wu Rvw Artcl ABSTRACT I ths rvw artcl,

More information

Channel Capacity Course - Information Theory - Tetsuo Asano and Tad matsumoto {t-asano,

Channel Capacity Course - Information Theory - Tetsuo Asano and Tad matsumoto   {t-asano, School of Iformato Scc Chal Capacty 009 - Cours - Iformato Thory - Ttsuo Asao ad Tad matsumoto Emal: {t-asao matumoto}@jast.ac.jp Japa Advacd Isttut of Scc ad Tchology Asahda - Nom Ishkawa 93-9 Japa http://www.jast.ac.jp

More information

Different types of Domination in Intuitionistic Fuzzy Graph

Different types of Domination in Intuitionistic Fuzzy Graph Aals of Pur ad Appld Mathmatcs Vol, No, 07, 87-0 ISSN: 79-087X P, 79-0888ol Publshd o July 07 wwwrsarchmathscorg DOI: http://dxdoorg/057/apama Aals of Dffrt typs of Domato Itutostc Fuzzy Graph MGaruambga,

More information

The probability of Riemann's hypothesis being true is. equal to 1. Yuyang Zhu 1

The probability of Riemann's hypothesis being true is. equal to 1. Yuyang Zhu 1 Th robablty of Ra's hyothss bg tru s ual to Yuyag Zhu Abstract Lt P b th st of all r ubrs P b th -th ( ) lt of P ascdg ordr of sz b ostv tgrs ad s a rutato of wth Th followg rsults ar gv ths ar: () Th

More information

Chapter 6. pn-junction diode: I-V characteristics

Chapter 6. pn-junction diode: I-V characteristics Chatr 6. -jucto dod: -V charactrstcs Tocs: stady stat rsos of th jucto dod udr ald d.c. voltag. ucto udr bas qualtatv dscusso dal dod quato Dvatos from th dal dod Charg-cotrol aroach Prof. Yo-S M Elctroc

More information

Complex Numbers. Prepared by: Prof. Sunil Department of Mathematics NIT Hamirpur (HP)

Complex Numbers. Prepared by: Prof. Sunil Department of Mathematics NIT Hamirpur (HP) th Topc Compl Nmbrs Hyprbolc fctos ad Ivrs hyprbolc fctos, Rlato btw hyprbolc ad crclar fctos, Formla of hyprbolc fctos, Ivrs hyprbolc fctos Prpard by: Prof Sl Dpartmt of Mathmatcs NIT Hamrpr (HP) Hyprbolc

More information

In 1991 Fermat s Last Theorem Has Been Proved

In 1991 Fermat s Last Theorem Has Been Proved I 99 Frmat s Last Thorm Has B Provd Chu-Xua Jag P.O.Box 94Bg 00854Cha Jcxua00@s.com;cxxxx@6.com bstract I 67 Frmat wrot: It s mpossbl to sparat a cub to two cubs or a bquadrat to two bquadrats or gral

More information

On Approximation Lower Bounds for TSP with Bounded Metrics

On Approximation Lower Bounds for TSP with Bounded Metrics O Approxmato Lowr Bouds for TSP wth Boudd Mtrcs Mark Karpsk Rchard Schmd Abstract W dvlop a w mthod for provg xplct approxmato lowr bouds for TSP problms wth boudd mtrcs mprovg o th bst up to ow kow bouds.

More information

pn Junction Under Reverse-Bias Conditions 3.3 Physical Operation of Diodes

pn Junction Under Reverse-Bias Conditions 3.3 Physical Operation of Diodes 3.3 Physcal Orato of os Jucto Ur vrs-bas Cotos rft Currt S : ato to th ffuso Currt comot u to majorty carrr ffuso, caus by thrmally grat morty carrrs, thr ar two currt comots lctros mov by rft from to

More information

Note on the Computation of Sample Size for Ratio Sampling

Note on the Computation of Sample Size for Ratio Sampling Not o th Computato of Sampl Sz for ato Samplg alr LMa, Ph.D., PF Forst sourcs Maagmt Uvrst of B.C. acouvr, BC, CANADA Sptmbr, 999 Backgroud ato samplg s commol usd to rduc cofdc trvals for a varabl of

More information

On the Beta Mekaham Distribution and Its Applications. Chukwu A. U., Ogunde A. A. *

On the Beta Mekaham Distribution and Its Applications. Chukwu A. U., Ogunde A. A. * Amrca Joural of Mathmatcs ad Statstcs 25, 5(3: 37-43 DOI:.5923/j.ajms.2553.5 O th Bta Mkaham Dstruto ad Its Applcatos Chukwu A. U., Ogud A. A. * Dpartmt of Statstcs, Uvrsty Of Iada, Dpartmt of Mathmatcs

More information

This is a repository copy of Estimation of generalised frequency response functions.

This is a repository copy of Estimation of generalised frequency response functions. hs s a rpostory copy of Estmato of gralsd frqucy rspos fuctos. Wht Ros Rsarch Ol URL for ths papr: http://prts.whtros.ac.uk/74654/ Moograph: L, L.M. ad Bllgs, S.A. 9 Estmato of gralsd frqucy rspos fuctos.

More information

Estimation Theory. Chapter 4

Estimation Theory. Chapter 4 Estmato ory aptr 4 LIEAR MOELS W - I matrx form Estmat slop B ad trcpt A,,.. - WG W B A l fttg Rcall W W W B A W ~ calld vctor I gral, ormal or Gaussa ata obsrvato paramtr Ma, ovarac KOW p matrx to b stmatd,

More information

Estimation of the Present Values of Life Annuities for the Different Actuarial Models

Estimation of the Present Values of Life Annuities for the Different Actuarial Models h Scod Itratoal Symposum o Stochastc Modls Rlablty Egrg, Lf Scc ad Opratos Maagmt Estmato of th Prst Valus of Lf Auts for th Dffrt Actuaral Modls Gady M Koshk, Oaa V Guba omsk Stat Uvrsty Dpartmt of Appld

More information

Bayesian Test for Lifetime Performance Index of Ailamujia Distribution Under Squared Error Loss Function

Bayesian Test for Lifetime Performance Index of Ailamujia Distribution Under Squared Error Loss Function Pur ad Appld Mathmatcs Joural 6; 5(6): 8-85 http://www.sccpublshggroup.com/j/pamj do:.648/j.pamj.656. ISSN: 36-979 (Prt); ISSN: 36-98 (Ol) Baysa Tst for ftm Prformac Idx of Alamuja Dstrbuto Udr Squard

More information

ERDOS-SMARANDACHE NUMBERS. Sabin Tabirca* Tatiana Tabirca**

ERDOS-SMARANDACHE NUMBERS. Sabin Tabirca* Tatiana Tabirca** ERDO-MARANDACHE NUMBER b Tbrc* Tt Tbrc** *Trslv Uvrsty of Brsov, Computr cc Dprtmt **Uvrsty of Mchstr, Computr cc Dprtmt Th strtg pot of ths rtcl s rprstd by rct work of Fch []. Bsd o two symptotc rsults

More information

' 1.00, has the form of a rhomb with

' 1.00, has the form of a rhomb with Problm I Rflcto ad rfracto of lght A A trstg prsm Th ma scto of a glass prsm stuatd ar ' has th form of a rhomb wth A th yllow bam of moochromatc lght propagatg towards th prsm paralll wth th dagoal AC

More information

7THE DIFFUSION OF PRODUCT INNOVATIONS AND MARKET STRUCTURE

7THE DIFFUSION OF PRODUCT INNOVATIONS AND MARKET STRUCTURE 7THE DIFFUSION OF PRODUCT INNOVATIONS AND MARKET STRUCTURE Isttut of Ecoomc Forcastg Roxaa IDU Abstract I ths papr I aalyz th dffuso of a product ovato that was rctly mad avalabl for lcsd purchas wth a

More information

Chapter 6 Student Lecture Notes 6-1

Chapter 6 Student Lecture Notes 6-1 Chaptr 6 Studnt Lctur Nots 6-1 Chaptr Goals QM353: Busnss Statstcs Chaptr 6 Goodnss-of-Ft Tsts and Contngncy Analyss Aftr compltng ths chaptr, you should b abl to: Us th ch-squar goodnss-of-ft tst to dtrmn

More information

Ordinary Least Squares at advanced level

Ordinary Least Squares at advanced level Ordary Last Squars at advacd lvl. Rvw of th two-varat cas wth algbra OLS s th fudamtal tchqu for lar rgrssos. You should by ow b awar of th two-varat cas ad th usual drvatos. I ths txt w ar gog to rvw

More information

Irregular Boundary Area Computation. by Quantic Hermite Polynomial

Irregular Boundary Area Computation. by Quantic Hermite Polynomial It. J. Cotmp. Mat. Sccs, Vol. 6,, o., - Irrgular Boudar Ara Computato b Quatc Hrmt Polomal J. Karwa Hama Faraj, H.-S. Faradu Kadr ad A. Jamal Muamad Uvrst of Sulama-Collg of Scc Dpartmt of Matmatcs, Sualma,

More information

Group Consensus of Second-Order Multi-agent Networks with Multiple Time Delays

Group Consensus of Second-Order Multi-agent Networks with Multiple Time Delays Itratoal Cofrc o Appld Mathmatcs, Smulato ad Modllg (AMSM 6) Group Cossus of Scod-Ordr Mult-agt Ntworks wth Multpl Tm Dlays Laghao J* ad Xyu Zhao Chogqg Ky Laboratory of Computatoal Itllgc, Chogqg Uvrsty

More information

Chapter 5 Special Discrete Distributions. Wen-Guey Tzeng Computer Science Department National Chiao University

Chapter 5 Special Discrete Distributions. Wen-Guey Tzeng Computer Science Department National Chiao University Chatr 5 Scal Dscrt Dstrbutos W-Guy Tzg Comutr Scc Dartmt Natoal Chao Uvrsty Why study scal radom varabls Thy aar frqutly thory, alcatos, statstcs, scc, grg, fac, tc. For aml, Th umbr of customrs a rod

More information

Statistical Thermodynamics Essential Concepts. (Boltzmann Population, Partition Functions, Entropy, Enthalpy, Free Energy) - lecture 5 -

Statistical Thermodynamics Essential Concepts. (Boltzmann Population, Partition Functions, Entropy, Enthalpy, Free Energy) - lecture 5 - Statstcal Thrmodyamcs sstal Cocpts (Boltzma Populato, Partto Fuctos, tropy, thalpy, Fr rgy) - lctur 5 - uatum mchacs of atoms ad molculs STATISTICAL MCHANICS ulbrum Proprts: Thrmodyamcs MACROSCOPIC Proprts

More information

Estimation of Population Variance Using a Generalized Double Sampling Estimator

Estimation of Population Variance Using a Generalized Double Sampling Estimator r Laka Joural o Appl tatstcs Vol 5-3 stmato o Populato Varac Us a Gralz Doubl ampl stmator Push Msra * a R. Kara h Dpartmt o tatstcs D.A.V.P.G. Coll Dhrau- 8 Uttarakha Ia. Dpartmt o tatstcs Luckow Uvrst

More information

signal amplification; design of digital logic; memory circuits

signal amplification; design of digital logic; memory circuits hatr Th lctroc dvc that s caabl of currt ad voltag amlfcato, or ga, cojucto wth othr crcut lmts, s th trasstor, whch s a thr-trmal dvc. Th dvlomt of th slco trasstor by Bard, Bratta, ad chockly at Bll

More information

Three-Dimensional Theory of Nonlinear-Elastic. Bodies Stability under Finite Deformations

Three-Dimensional Theory of Nonlinear-Elastic. Bodies Stability under Finite Deformations Appld Mathmatcal Sccs ol. 9 5 o. 43 75-73 HKAR Ltd www.m-hkar.com http://dx.do.org/.988/ams.5.567 Thr-Dmsoal Thory of Nolar-Elastc Bods Stablty udr Ft Dformatos Yu.. Dmtrko Computatoal Mathmatcs ad Mathmatcal

More information

APPENDIX: STATISTICAL TOOLS

APPENDIX: STATISTICAL TOOLS I. Nots o radom samplig Why do you d to sampl radomly? APPENDI: STATISTICAL TOOLS I ordr to masur som valu o a populatio of orgaisms, you usually caot masur all orgaisms, so you sampl a subst of th populatio.

More information

T and V be the total kinetic energy and potential energy stored in the dynamic system. The Lagrangian L, can be defined by

T and V be the total kinetic energy and potential energy stored in the dynamic system. The Lagrangian L, can be defined by From MEC '05 Itrgratg Prosthtcs ad Mdc, Procdgs of th 005 MyoElctrc Cotrols/Powrd Prosthtcs Symposum, hld Frdrcto, Nw Bruswc, Caada, ugust 7-9, 005. EECROMECHNIC NYSIS OF COMPEE RM PROSHESIS (EMS) Prmary

More information

Integral points on hyperbolas over Z: A special case

Integral points on hyperbolas over Z: A special case Itgral pots o hprbolas ovr Z: A spcal cas `Pag of 7 Kostat Zlator Dpartmt of Mathmatcs ad Computr Scc Rhod Islad Collg 600 Mout Plasat Avu Provdc, R.I. 0908-99, U.S.A. -mal addrss: ) Kzlator@rc.du ) Kostat_zlator@ahoo.com

More information

BER Analysis of Optical Wireless Signals through Lognormal Fading Channels with Perfect CSI

BER Analysis of Optical Wireless Signals through Lognormal Fading Channels with Perfect CSI 7th tratoal Cofrc o Tlcommucatos BER Aalyss of Optcal Wrlss Sgals through ogormal Fadg Chals wth rfct CS Hassa Morad, Maryam Falahpour, Hazm H. Rfa Elctrcal ad Computr Egrg Uvrsty of Olahoma Tulsa, OK,

More information

Research on Motor Vehicle Ownership of Jinan Based on the Traffic Environmental Bearing Capacity Motor

Research on Motor Vehicle Ownership of Jinan Based on the Traffic Environmental Bearing Capacity Motor Assocato for Iformato Systms AIS Elctroc Lbrary (AISL) WHICEB 204 Procdgs Wuha Itratoal Cofrc o -Busss Summr 6--204 Rsarch o Motor Vhcl Owrshp of Ja Basd o th Traffc Evromtal Barg Capacty Motor Xaxa Y

More information

ME 501A Seminar in Engineering Analysis Page 1

ME 501A Seminar in Engineering Analysis Page 1 St Ssts o Ordar Drtal Equatos Novbr 7 St Ssts o Ordar Drtal Equatos Larr Cartto Mcacal Er 5A Sar Er Aalss Novbr 7 Outl Mr Rsults Rvw last class Stablt o urcal solutos Stp sz varato or rror cotrol Multstp

More information

Worksheet: Taylor Series, Lagrange Error Bound ilearnmath.net

Worksheet: Taylor Series, Lagrange Error Bound ilearnmath.net Taylor s Thorm & Lagrag Error Bouds Actual Error This is th ral amout o rror, ot th rror boud (worst cas scario). It is th dirc btw th actual () ad th polyomial. Stps:. Plug -valu ito () to gt a valu.

More information

Review - Probabilistic Classification

Review - Probabilistic Classification Mmoral Unvrsty of wfoundland Pattrn Rcognton Lctur 8 May 5, 6 http://www.ngr.mun.ca/~charlsr Offc Hours: Tusdays Thursdays 8:3-9:3 PM E- (untl furthr notc) Gvn lablld sampls { ɛc,,,..., } {. Estmat Rvw

More information

i j i i i = S i 1 Y Y i F i ..., X in

i j i i i = S i 1 Y Y i F i ..., X in R ASHI :43-48 (06 ESIA IO OF HE SALLES LOCA IO OF WO EGAIVE EXPOEIAL POPULAIOS Partha Pal ad Uttam Badyopadhyay Dpartmt of Statsts aulaa Azad Collg Kolkata Dpartmt of Statsts Uvrsty of Calutt a ABSRAC

More information

Entropy Equation for a Control Volume

Entropy Equation for a Control Volume Fudamtals of Thrmodyamcs Chaptr 7 Etropy Equato for a Cotrol Volum Prof. Syoug Jog Thrmodyamcs I MEE2022-02 Thrmal Egrg Lab. 2 Q ds Srr T Q S2 S1 1 Q S S2 S1 Srr T t t T t S S s m 1 2 t S S s m tt S S

More information

Graphs of q-exponentials and q-trigonometric functions

Graphs of q-exponentials and q-trigonometric functions Grahs of -otals ad -trgoomtrc fuctos Amla Carola Saravga To ct ths vrso: Amla Carola Saravga. Grahs of -otals ad -trgoomtrc fuctos. 26. HAL Id: hal-377262 htts://hal.archvs-ouvrts.fr/hal-377262

More information

Chapter 4 NUMERICAL METHODS FOR SOLVING BOUNDARY-VALUE PROBLEMS

Chapter 4 NUMERICAL METHODS FOR SOLVING BOUNDARY-VALUE PROBLEMS Chaptr 4 NUMERICL METHODS FOR SOLVING BOUNDRY-VLUE PROBLEMS 00 4. Varatoal formulato two-msoal magtostatcs Lt th followg magtostatc bouar-valu problm b cosr ( ) J (4..) 0 alog ΓD (4..) 0 alog ΓN (4..)

More information

Logistic Regression Sara Vyrostek Senior Exercise November 16, 2001

Logistic Regression Sara Vyrostek Senior Exercise November 16, 2001 ogstc Rgrsso Sara Vrostk Sor Ercs Novmbr 6, Itroducto: I th modlg of data, aalsts dvlop rlatoshps basd upo th obsrvd valus of a st of prdctor varabls ordr to dtrm th pctd valu of th rspos varabl of trst,

More information

Chapter (8) Estimation and Confedence Intervals Examples

Chapter (8) Estimation and Confedence Intervals Examples Chaptr (8) Estimatio ad Cofdc Itrvals Exampls Typs of stimatio: i. Poit stimatio: Exampl (1): Cosidr th sampl obsrvatios, 17,3,5,1,18,6,16,10 8 X i i1 17 3 5 118 6 16 10 116 X 14.5 8 8 8 14.5 is a poit

More information

A Multi-granular Linguistic Promethee Model

A Multi-granular Linguistic Promethee Model A Mult-graular Lgustc Promth Modl Nsr Haloua, Lus Martíz, Habb Chabchoub, Ja-Marc Martl, Ju Lu 4 Uvrsty of Ecoomc Sccs ad Maagmt, Sfax, Tusa, Uvrsty of Jaé, Spa, Uvrsty of Laval, Caada, 4 Uvrsty of Ulstr,

More information

Reliability Evaluation of Slopes Using Particle Swarm Optimization

Reliability Evaluation of Slopes Using Particle Swarm Optimization atoal Uvrsty of Malaysa From th lctdworks of Mohammad Khajhzadh 20 Rlablty Evaluato of lops Usg Partcl warm Optmzato Mohammad Khajhzadh Mohd Raha Taha hmd El-shaf valabl at: https://works.bprss.com/mohammad_khajhzadh/24/

More information

New bounds on Poisson approximation to the distribution of a sum of negative binomial random variables

New bounds on Poisson approximation to the distribution of a sum of negative binomial random variables Sogklaaka J. Sc. Tchol. 4 () 4-48 Ma. -. 8 Ogal tcl Nw bouds o Posso aomato to th dstbuto of a sum of gatv bomal adom vaabls * Kat Taabola Datmt of Mathmatcs Faculty of Scc Buaha Uvsty Muag Chobu 3 Thalad

More information

β-spline Estimation in a Semiparametric Regression Model with Nonlinear Time Series Errors

β-spline Estimation in a Semiparametric Regression Model with Nonlinear Time Series Errors Amrca Joural of Appld Sccs, (9): 343-349, 005 ISSN 546-939 005 Scc Publcatos β-spl Estmato a Smparamtrc Rgrsso Modl wth Nolar Tm Srs Errors Jhog You, ma Ch ad 3 Xa Zhou Dpartmt of ostatstcs, Uvrsty of

More information

ST 524 NCSU - Fall 2008 One way Analysis of variance Variances not homogeneous

ST 524 NCSU - Fall 2008 One way Analysis of variance Variances not homogeneous ST 54 NCSU - Fall 008 On way Analyss of varanc Varancs not homognous On way Analyss of varanc Exampl (Yandll, 997) A plant scntst masurd th concntraton of a partcular vrus n plant sap usng ELISA (nzym-lnkd

More information

Phase-Field Modeling for Dynamic Recrystallization

Phase-Field Modeling for Dynamic Recrystallization 0 (0000) 0 0 Plas lav ths spac mpty Phas-Fld Modlg for Dyamc Rcrystallzato T. Takak *, A. Yamaaka, Y. Tomta 3 Faculty of Martm Sccs, Kob Uvrsty, 5--, Fukamam, Hgashada, Kob, 658-00, Japa (Emal : takak@martm.kob-u.ac.p)

More information

Phase diagram and frustration of decoherence in Y-shaped Josephson junction networks. D.Giuliano(Cosenza), P. Sodano(Perugia)

Phase diagram and frustration of decoherence in Y-shaped Josephson junction networks. D.Giuliano(Cosenza), P. Sodano(Perugia) Phas dagram ad frustrato of dcohrc Y-shapd Josphso jucto tworks D.GulaoCosza, P. SodaoPruga Frz, Frz, Octobr Octobr 008 008 Ma da Y-Shapd twork of Josphso jucto chas YJJN wth a magtc frustrato Ft-couplg

More information

More Statistics tutorial at 1. Introduction to mathematical Statistics

More Statistics tutorial at   1. Introduction to mathematical Statistics Mor Sttstcs tutorl t wwwdumblttldoctorcom Itroducto to mthmtcl Sttstcs Fl Soluto A Gllup survy portrys US trprurs s " th mvrcks, drmrs, d lors whos rough dgs d ucompromsg d to do t thr ow wy st thm shrp

More information

International Journal of Advanced Scientific Research and Management, Volume 3 Issue 11, Nov

International Journal of Advanced Scientific Research and Management, Volume 3 Issue 11, Nov 199 Algothm ad Matlab Pogam fo Softwa Rlablty Gowth Modl Basd o Wbull Od Statstcs Dstbuto Akladswa Svasa Vswaatha 1 ad Saavth Rama 2 1 Mathmatcs, Saaatha Collg of Egg, Tchy, Taml Nadu, Ida Abstact I ths

More information

Lecture #11. A Note of Caution

Lecture #11. A Note of Caution ctur #11 OUTE uctos rvrs brakdow dal dod aalyss» currt flow (qualtatv)» morty carrr dstrbutos Radg: Chatr 6 Srg 003 EE130 ctur 11, Sld 1 ot of Cauto Tycally, juctos C dvcs ar formd by coutr-dog. Th quatos

More information

Chapter Discrete Fourier Transform

Chapter Discrete Fourier Transform haptr.4 Dscrt Fourr Trasform Itroducto Rcad th xpota form of Fourr srs s Equatos 8 ad from haptr., wt f t 8, h.. T w t f t dt T Wh th abov tgra ca b usd to comput, h.., t s mor prfrab to hav a dscrtzd

More information

BAYESIAN ANALYSIS OF THE SIMPLE LINEAR REGRESSION WITH MEASUREMENT ERRORS

BAYESIAN ANALYSIS OF THE SIMPLE LINEAR REGRESSION WITH MEASUREMENT ERRORS BAYESIAN ANALYSIS OF THE SIMPLE LINEAR REGRESSION WITH MEASUREMENT ERRORS Marta Yuk BABA Frado Atoo MOALA ABSTRACT: Usually th classcal approach to mak frc lar rgrsso modl assums that th dpdt varabl dos

More information

Option 3. b) xe dx = and therefore the series is convergent. 12 a) Divergent b) Convergent Proof 15 For. p = 1 1so the series diverges.

Option 3. b) xe dx = and therefore the series is convergent. 12 a) Divergent b) Convergent Proof 15 For. p = 1 1so the series diverges. Optio Chaptr Ercis. Covrgs to Covrgs to Covrgs to Divrgs Covrgs to Covrgs to Divrgs 8 Divrgs Covrgs to Covrgs to Divrgs Covrgs to Covrgs to Covrgs to Covrgs to 8 Proof Covrgs to π l 8 l a b Divrgt π Divrgt

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

1985 AP Calculus BC: Section I

1985 AP Calculus BC: Section I 985 AP Calculus BC: Sctio I 9 Miuts No Calculator Nots: () I this amiatio, l dots th atural logarithm of (that is, logarithm to th bas ). () Ulss othrwis spcifid, th domai of a fuctio f is assumd to b

More information

Learning from Data with Information Theoretic Criteria II

Learning from Data with Information Theoretic Criteria II Larg from Data th Iformato Thortc Crtra II Jos C. Prcp, Ph.D. Dstgushd Profssor of Elctrcal ad Bomdcal Egrg ad BllSouth Profssor Computatoal uroegrg Laborator Uvrst of Florda http://.cl.ufl.du prcp@cl.ufl.du

More information

PERFORMANCE ANALYSIS OF CIRCUIT SWITCHING BASELINE INTERCONNECTION NETWORKS. Manjal Lee and Chuan-lin Wu

PERFORMANCE ANALYSIS OF CIRCUIT SWITCHING BASELINE INTERCONNECTION NETWORKS. Manjal Lee and Chuan-lin Wu PERFORMANCE ANALYSIS OF CIRCUIT SWITCHING BASELINE INTERCONNECTION NETWORKS Majal L ad Chua-l Wu Dpartmt of Elctrcal Egrg Uvrsty of Txas at Aust Aust, TX 78712 Abstract Prformac valuato, usg both aalytlcal

More information

Round-Off Noise of Multiplicative FIR Filters Implemented on an FPGA Platform

Round-Off Noise of Multiplicative FIR Filters Implemented on an FPGA Platform Appl. Sc. 4, 4, 99-7; do:.339/app499 Artcl OPEN ACCESS appld sccs ISSN 76-347 www.mdp.com/joural/applsc Roud-Off Nos of Multplcatv FIR Fltrs Implmtd o a FPGA Platform Ja-Jacqus Vadbussch, *, Ptr L ad Joa

More information

Research on the Massive Data Classification Method in Large Scale Computer Information Management huangyun

Research on the Massive Data Classification Method in Large Scale Computer Information Management huangyun Itratoa Crc o Automato, Mchaca Cotro ad Computatoa Egrg (AMCCE 05) Rsarch o th Massv Data Cassfcato Mthod Larg Sca Computr Iformato Maagmt huagyu Chogqg ctroc grg Carr Acadmy, Chogqg 4733, Cha Kywords:

More information

Washington State University

Washington State University he 3 Ktics ad Ractor Dsig Sprg, 00 Washgto Stat Uivrsity Dpartmt of hmical Egrg Richard L. Zollars Exam # You will hav o hour (60 muts) to complt this xam which cosists of four (4) problms. You may us

More information

IAEA-CN-184/61 Y. GOTO, T. KATO, K.NIDAIRA. Nuclear Material Control Center, Tokai-mura Japan.

IAEA-CN-184/61 Y. GOTO, T. KATO, K.NIDAIRA. Nuclear Material Control Center, Tokai-mura Japan. IAEA-CN-84/6 Establshmt of accurat calbrato curv for atoal vrfcato at a larg scal ut accoutablt tak RRP - For strgthg stat sstm for mtg safguards oblgato. GOO. KAO K.NIDAIRA Nuclar Matral Cotrol Ctr oka-mura

More information

Nuclear Chemistry -- ANSWERS

Nuclear Chemistry -- ANSWERS Hoor Chstry Mr. Motro 5-6 Probl St Nuclar Chstry -- ANSWERS Clarly wrt aswrs o sparat shts. Show all work ad uts.. Wrt all th uclar quatos or th radoactv dcay srs o Urau-38 all th way to Lad-6. Th dcay

More information

Transmuted Exponentiated Gamma Distribution: A Generalization of the Exponentiated. Gamma Probability Distribution

Transmuted Exponentiated Gamma Distribution: A Generalization of the Exponentiated. Gamma Probability Distribution Appld Mathatcal Sccs Vol. 8 04 o. 7 97-30 HIKARI Ltd www.-hkar.co http//d.do.org/0.988/as.04.405 Trasutd Epotatd Gaa Dstrbuto A Gralzato o th Epotatd Gaa Probablty Dstrbuto Mohad A. Hussa Dpartt o Mathatcal

More information