Supplementary Material to A General Method for Third-Order Bias and Variance Corrections on a Nonlinear Estimator

Size: px
Start display at page:

Download "Supplementary Material to A General Method for Third-Order Bias and Variance Corrections on a Nonlinear Estimator"

Transcription

1 Supplemetary Material to A Geeral Method for Third-Order Bias ad Variace Correctios o a Noliear Estimator Zheli Yag School of Ecoomics, Sigapore Maagemet Uiversity, 90 Stamford Road, Sigapore s: zlyag@smu.edu.sg March, 2012 Summary This supplemetary material cotais exteded Mote Carlo results icludig those reported i a paper etitled A Geeral Method for Third-Order Bias ad Variace Correctios o a Noliear Estimator. More detailed aalyses relatig to the geeral observatios reported i the paper are also give. 1 Itroductio Extesive Mote Carlo experimets are carried out to ivestigate (i) the fiite sample performace of the QMLE ad the bias-corrected QMLEs bc2 ad bc3 of the spatial lag parameter λ, (ii) the fiite sample performace of the corrected stadard errors (se) of the origial QMLE as well the bias-corrected QMLE, ad (iii) the impact of the bias ad se correctios o the subsequet ifereces for λ. Also, through the process of our ivestigatio o the higher-order properties of the SAR model, we foud some aomalies i the documeted Mote Carlo results i Bao ad Ullah (2007a) ad i Lee (2004a). Their Mote Carlo experimets are reru ad the ameded results reported. A compariso is thus made with the aalytical approach of Bao ad Ullah (2007a). 2 Mote Carlo Experimet I To demostrate the effectiveess of the proposed bias-correctio procedure, ad to ivestigate the impact of bias ad se correctios o the subsequet iterfereces, a comprehesive set of Mote Carlo experimets is carried out based o the followig geeral SAR model: Y = λw Y + β X 1 β 1 + X 2 β 2 + u, where 1 is a -vector of oes. For all the Mote Carlo experimets, β = {β 0, β 1, β 2 } is set at {5, 1, 1} or {.5,.1,.1}, σ at 1 or 2, λ takes values {.5,.25,0,.25,.5}, ad takes values

2 {50, 100, 200,500}. 1 Several ways of geeratig W, (X 1, X 2 ), ad u are cosidered. First, the values {x 1i } or {x 1,ir } of X 1, ad the values {x 2i } or {x 2,ir } of X 2 are, MRSAR-A: {x 1i } iid N(0, 1)/ 2, ad {x 2i } iid N(0, 1)/ 2, or MRSAR-B: {x 1,ir } = (2z r + z ir )/ 7, ad {x 2,ir } = (v r + v ir )/ 7, where i MRSAR-B, {z r, z ir, v r, v ir } iid N(0, 1), across all i ad r. Apparetly, MRSAR-A gives iid X values, ad MRSAR-B gives o-iid X values, or differet group meas uder group iteractio, see Lee (2004a) ad below for details. Both schemes give sigal-to-oise ratios 1 or 1/2 whe σ = 1 or 2. Spatial layouts. Three geeral spatial layouts are cosidered i the Mote Carlo experimets. The first is based o Rook cotiguity, the secod is based o Quee cotiguity ad the third is based o the otio of group iteractios. The methods used i geeratig these three spatial layouts are similar to those used i Yag (2010). The detail for geeratig the W matrix uder rook cotiguity is as follows: (i) idex the spatial uits by {1, 2,, }, radomly permute these idices ad the allocate them ito a lattice of k m( ) squares, (ii) let W ij = 1 if the idex j is i a square which is o immediate left, or right, or above, or below the square which cotais the idex i, otherwise W ij = 0, i, j = 1,,, to form a matrix, ad (iii) divide each elemet of this matrix by its row sum to give W. Similarly, oe geerates the W matrix uder Quee cotiguity with additioal eighbors sharig a commo vertex with the uit of iterest. To geerate the W matrix accordig to the group iteractio scheme, suppose we have k groups of sizes m 1, m 2,, m k. Defie W = diag{w j /(m j 1), j = 1,, k}, a matrix formed by placig the submatrices W j alog the diagoal directio, where W j is a m j m j matrix with oes o the off-diagoal positios ad zeros o the diagoal positios. The group sizes {m j } ca be the same or differet, ad idepedet or depedet o, allowig for a full rage of spatial scearios cosidered i Lee (2004a). The details are as follows: (i) calculate the umber of groups accordig to k = K(), ad the approximate average group size m = /k, (ii) geerate the group sizes (m 1, m 2,, m k ) accordig to a discrete distributio cetered at m, ad (iii) adjust the group sizes so that k j=1 m j =. 2 I our Mote Carlo experimets, we use K() = Roud( ǫ ) with ǫ = 0.35, 0.50, ad 0.75, 1 As i Lee (2007a), the maximizatio of l c (λ) is performed globally without imposig a restricted lower boud o λ. This is importat whe the true λ value is egative ad big, because QMLE is dowward biased ad a restricted lower boud, say, would result i the searchig process to hit the lower boud quite ofte, thus failig to reach the true maximum poit. This would i tur give a wrog impressio that the QMLE ca be upward biased ad the bias-correctio may ot work i certai cases. This is believed to be the reaso for the icoheret Mote Carlo results of Bao ad Ullah (2007a). See Aseli (1988, p ) for a theoretical discussio o the parameter space of λ i relatio to the eigevalues of W. 2 Clearly, this desig covers the sceario cosidered i Case (1991). Typical forms of K() iclude K() = /m where m is a prespecified costat idepedet of ad K() = Roud( ǫ ). Lee (2007b) shows that the group size variatio plays a importat role i the idetificatio ad estimatio of ecoometric 2

3 represetig respectively the situatios where (a) there are few groups of may spatial uits i each, (b) the umber of groups ad the sizes of the groups are of the same magitude, ad (c) there are may groups of few elemets i each. Clearly, h = O( 1 ǫ ). The group sizes are draw from a discrete uiform distributio from 0.5m to 1.5m. Error distributios. To geerate u = σe, three distributios are cosidered: dgp1: the elemets {e i } of e are iid stadard ormal, dgp2: {e i } are iid stadardized ormal mixture, ad dgp3: {e i } are iid stadardized log-ormal. Specifically, for dgp2, e i = ((1 ξ i )Z i + ξ i τz i )/(1 p + p σ 2 ) 0.5, where ξ Beroulli(p), ad Z i N(0, 1) idepedet of ξ. The parameter p represets the proportio of mixig the two ormal populatios. I our experimets, we choose p = 0.1, meaig that 90% of the radom variates are from stadard ormal ad the remaiig 10% are from aother ormal populatio with stadard deviatio τ. We choose τ = 4 to simulate the situatio where there are gross errors i the data. For dgp3, e i = [exp(z i ) exp(0.5)]/[exp(2) exp(1)] 0.5, which gives a error distributio that is both skewed ad leptokurtic. The ormal mixture gives a error distributio that is still symmetric like ormal but leptokurtic. Other oormal distributios, such as ormal-gamma mixture ad chi-square, are also cosidered ad the results (available from the author upo request) exhibit a similar patter. Fiite sample performace of the spatial estimators. We report the Mote Carlo mea, rmse ad sd of, bc2 ad bc3 uder various combiatios of the values for (, λ, σ), the error distributios, ad the spatial layouts. We also report the averages (over Mote Carlo samples) of the 1st-, 2d- ad 3rd-order ses: V 1 ( ) 1 2, V 2 ( ) 1 2, V 3 ( ) 1 2 ad V 3 ( bc3 ) 1 2, defied by Corollaries 3.3 ad 3.4 ad calculated based o the proposed bootstrap method. Each set of results is based o 10,000 Mote Carlo samples, ad B = floor( 0.75 ) bootstrap samples for each Mote Carlo sample. Table 1 summarizes the results (reported i the paper) with β = {5, 1, 1} ad σ = 1, where the regressors values are geerated accordig to MRSAR-A for Quee cotiguity spatial layout, ad MRSAR-B for group iteractio spatial layout. Table 1-1 cotais additioal results uder the same setup as the group iteractio scheme but with differet group size cofiguratios. Table 1-2 replicates the results of Table 1 uder β = {.5,.1,.1}, ad Table 1-3 replicates the results of Table 1 uder σ = 2. For the results i both Tables 1b ad 1c, 1,000 Mote Carlo rus ad floor( 0.5 ) bootstrap samples for each Mote Carlo ru are used. Some geeral observatios are i order: models with group iteractios, cotextual factors ad fixed effects. Yag (2010) shows that it also plays a importat role i the robustess of the LM test of spatial error compoets. 3

4 (i) the bias-corrected QMLEs bc2 ad outperform the origial QMLE ; bc3 are i geeral early ubiased ad clearly (ii) is always dowward biased ad the biasess ca be very serious depedig o the (iii) spatial layout, the sample size ad the error stadard deviatio; bc3 bc2 bc2 improves over, but usig seems to be sufficiet uder most of the situatios as far as bias-correctio is cocered; (iv) spatial layouts ca have a huge impact o the fiite sample performace of the stroger the spatial depedece the worse performs; (v) the values of σ ad the slope parameters also have a big impact the bigger the σ is, or the smaller the β 1 ad β 2 are, the bigger are the biases, rmses ad sds of ; (vi) the value of λ ad the way the regressors beig geerated affect the fiite sample performace of as λ decreases, the bias of decreases uder iid regressors but icreases uder o-iid regressors, whereas the [rmse](se) of always icreases as λ decreases, with a sharper amout for the case of o-iid regressors; (vii) the error distributio does ot affect much o the geeral performace of the three estimators, showig the robustess of the proposed approach. (viii) The empirical sd of ca be slightly differet from that of small, suggestig that the variaces of ad bc3 bc3 whe sample size is may differ o higher-order term (see paels (a)-(c), Table 1). The results i the last four colums of Table 1 show that V 3 ( bc3 ) provides the best approximatio to the variace of. The empirical sds of ad bc2 bc3 bc3 ad agree closely, suggestig that the fiite sample variaces of bc3 are about the same. These are cosistet with the result of Corollary 3.4. I summary, the proposed bias-correctio procedure works excelletly i geeral, it is simple ad widely applicable, ad thus should be recommeded for the practitioers. The performace of t-ratios. The fiite sample behavior of the t-ratios t ij for testig H 0 : λ = 0, defied i (23) are ivestigated. Partial Mote Carlo results i terms of meas, sds, ad tail probabilities are reported i Table 2. From the results, the followig coclusios ca be draw: (i) the asymptotic t-ratio t 11 ca perform quite badly with severe distortios o mea ad sizes; (ii) use of secod-order bias-corrected estimator oly (t 21 ) immediately improves; (iii) use of both secod-order bias-corrected estimator ad secod-order variace gives further improvemets; ad (iv) use of the third-order bias-corrected estimator ad the third-order variace estimate gives the best results. bc2 4

5 3 Mote Carlo Experimet II The Mote Carlo experimet coducted by Bao ad Ullah (2007a) is replicated ad exteded for two purposes: (i) to compare our bootstrap-based bias correctio with their aalytical bias correctio, ad (ii) to ivestigate the cause of icoheret Mote Carlo results of Bao ad Ullah (2007a) for the case of λ = 0.9 ad J = 10, where J is the umber of eighbors each spatial uit has whe the circular-world desig is used. The empirical meas ad rmses for the four estimators: the MLE, the secod-order bias-corrected MLE bc2, ad the aalytically bias-corrected MLE BU of Bao ad Ullah (2007a), are summarized i Table 3. The results show that the secod-order bias correctio works excelletly i geeral: (i) i case of ormal errors, the bootstrap method ad aalytical method produce almost idetical results, cofirmig the validity of the proposed bootstrap method, ad (ii) i case of o-ormal errors, bootstrap method produces slightly better results, showig that the proposed method is more robust agaist the error distributio tha the aalytical method that is based o the ormality assumptio. The results also show a very coheret behavior of the MLE ad the bias-corrected MLEs i that the MLE is almost ubiased whe J is small ad is dowward biased whe J is big. I cases where the MLE is biased, the bias-corrected estimators always be able to correct the bias. However, the Mote Carlo results of Bao ad Ullah show a differet picture for the cases where J is large ad λ is large ad egative: the MLE is upward biased ad the bias-correctio does ot work. A possible explaatio for this ca be foud i Footote 9. 4 Mote Carlo Experimet III The Mote Carlo experimets of Lee (2004) are reru ad exteded agai for two purposes: i) to further compare MLEs (estimators uder ormal errors) ad secod-order bias-corrected MLEs uder a model without itercept, ad ii) to amed the aomalies i his Mote Carlo results. Uder the idetical set-up but with more Mote Carlo replicatios (10,000 vs 400) for each case, we foud that with the umber of districts R = (30, 60, 120) ad the umber of members i each district m = (2, 3, 5,1020,50,100),the MLEs all perform very well i all cases, showig a big cotrast to the results of Lee (2004a). However, whe the values for R ad m are switched, the results obtaied are more i lie with those of Lee (2004a) i terms of bias but ot i terms of sd. Table 4a correspods to Tables I & II i Lee (2004a). Tables 4b summarize the results of the Mote Carlo experimets whe the values for R ad m are switched, i.e., R = (3, 5, 10,20,50, 100) ad m = (30, 60, 120). The results i Tables 4b are ow more i lie with Lee s results i terms of bias but ot i terms of sd of. The results further show that for a give R value, icreasig the m value does ot ecessarily reduce the bias of. 5

6 However, for a give m, icreasig R clearly improves the performace of the estimators with both bias ad sd sigificatly reduced. From the theoretical poit of view, our results make more sese as icreasig m elarges the degree of spatial depedece, makig the estimatio of the spatial parameter harder (or at least ot easier). I cotrast, icreasig R clearly reduces the degree of spatial depedece, makig the estimatio of the spatial parameter much easier. 6

7 Table 1. Empirical Mea[rmse](sd) of Estimators of λ, ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (a) Quee Cotiguity, Normal Errors, MRSAR-A [.195](.174).492 [.175](.175).497 [.175](.175) [.123](.116).498 [.117](.117).500 [.117](.117) [.078](.076).499 [.075](.075).499 [.075](.075) [.049](.048).501 [.048](.048).501 [.048](.048) [.222](.204).242 [.209](.209).246 [.210](.210) [.146](.140).248 [.142](.142).250 [.143](.143) [.094](.092).250 [.093](.093).250 [.093](.093) [.060](.060).250 [.060](.060).250 [.060](.060) [.229](.216) [.224](.224) [.226](.226) [.157](.153) [.156](.156) [.157](.157) [.106](.104) [.105](.105).000 [.105](.105) [.068](.067) [.068](.068) [.068](.068) [.233](.223) [.236](.236) [.237](.237) [.164](.161) [.166](.166) [.166](.166) [.112](.111) [.112](.112) [.112](.112) [.073](.072) [.073](.073) [.073](.073) [.228](.222) [.236](.236) [.237](.237) [.162](.161) [.166](.166) [.166](.166) [.113](.113) [.114](.114) [.114](.114) [.073](.073) [.073](.073) [.073](.073) (b) Quee Cotiguity, Normal Mixture Errors, MRSAR-A [.182](.164).494 [.165](.165).498 [.165](.165) [.120](.114).499 [.114](.114).500 [.114](.114) [.076](.074).500 [.074](.074).500 [.074](.074) [.049](.048).500 [.048](.048).500 [.048](.048) [.207](.190).241 [.195](.195).244 [.195](.195) [.140](.135).248 [.136](.136).249 [.137](.137) [.092](.090).249 [.090](.090).249 [.090](.090) [.060](.060).250 [.060](.060).250 [.060](.060) [.217](.206) [.213](.213) [.214](.214) [.150](.147) [.150](.150) [.150](.150) [.104](.103) [.103](.103) [.103](.103) [.068](.067) [.067](.067) [.067](.067) [.223](.213) [.224](.224) [.225](.225) [.155](.153) [.157](.157) [.157](.157) [.111](.110) [.112](.112) [.112](.112) [.072](.072) [.072](.072) [.072](.072) [.218](.212) [.224](.224) [.225](.225) [.155](.153) [.158](.158) [.158](.158) [.112](.111) [.113](.113) [.113](.113) [.074](.073) [.074](.074) [.074](.074) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 7

8 Table 1 (cot d). Empirical Mea[rmse](sd) of Estimators of λ, ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (c) Quee Cotiguity, Logormal Errors, MRSAR-A [.163](.146).491 [.146](.146).493 [.146](.146) [.110](.105).498 [.105](.105).498 [.105](.105) [.072](.069).499 [.069](.069).499 [.069](.069) [.047](.046).499 [.046](.046).499 [.046](.046) [.185](.171).241 [.174](.174).244 [.174](.174) [.128](.124).247 [.126](.125).248 [.126](.125) [.087](.085).249 [.085](.085).249 [.085](.085) [.058](.057).249 [.057](.057).249 [.057](.057) [.198](.186) [.192](.191) [.192](.192) [.139](.136) [.138](.138) [.138](.138) [.099](.097) [.098](.098) [.098](.098) [.065](.064) [.065](.065).000 [.065](.065) [.199](.191) [.198](.198) [.199](.199) [.142](.140) [.144](.144) [.144](.144) [.105](.104) [.105](.105) [.105](.105) [.070](.070) [.070](.070) [.070](.070) [.196](.190) [.200](.199) [.200](.200) [.145](.144) [.148](.148) [.148](.148) [.106](.106) [.107](.107) [.107](.107) [.070](.070) [.070](.070) [.070](.070) (d) Group Iteractio with k = 0.5, Normal Errors, MRSAR-B [.145](.124).495 [.122](.122).499 [.122](.122) [.112](.099).498 [.097](.097).500 [.097](.097) [.073](.068).499 [.067](.067).500 [.067](.067) [.042](.041).500 [.041](.041).500 [.041](.041) [.209](.179).239 [.178](.178).244 [.179](.178) [.160](.143).248 [.141](.141).250 [.141](.141) [.108](.102).249 [.101](.101).249 [.101](.101) [.062](.060).250 [.061](.061).250 [.061](.061) [.261](.224) [.226](.226) [.227](.227) [.206](.183) [.182](.182) [.182](.182) [.137](.128).001 [.128](.128).001 [.128](.128) [.081](.079) [.079](.079) [.079](.079) [.303](.260) [.266](.266) [.267](.267) [.243](.218) [.219](.219) [.219](.219) [.170](.160) [.160](.160) [.160](.160) [.101](.098) [.098](.098) [.098](.098) [.337](.291) [.302](.301) [.303](.302) [.281](.254) [.257](.257) [.257](.257) [.198](.186) [.187](.187) [.187](.187) [.118](.115) [.116](.116) [.116](.116) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 8

9 Table 1 (cot d). Empirical Mea[rmse](sd) of Estimators of λ, ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (e) Group Iteractio with k = 0.5, Normal Mixture Errors, MRSAR-B [.144](.124).489 [.121](.120).493 [.120](.120) [.111](.098).495 [.096](.096).497 [.096](.096) [.073](.068).498 [.068](.068).499 [.068](.068) [.042](.041).500 [.041](.041).500 [.041](.041) [.203](.175).234 [.172](.171).239 [.172](.171) [.157](.140).245 [.138](.137).248 [.138](.138) [.104](.097).249 [.097](.097).249 [.097](.097) [.062](.060).250 [.060](.060).250 [.060](.060) [.250](.215) [.214](.213) [.214](.214) [.203](.182) [.180](.180) [.181](.181) [.137](.129) [.129](.128) [.129](.129) [.082](.080) [.080](.080) [.080](.080) [.294](.256) [.259](.259) [.260](.259) [.241](.216) [.216](.216) [.216](.216) [.165](.156) [.155](.155) [.155](.155) [.101](.098) [.099](.099) [.099](.099) [.330](.289) [.298](.297) [.298](.298) [.270](.243) [.245](.245) [.245](.245) [.197](.185) [.186](.186) [.186](.186) [.120](.117) [.117](.117) [.117](.117) (f) Group Iteractio with k = 0.5, Logormal Errors, MRSAR-B [.127](.110).488 [.107](.106).492 [.106](.106) [.104](.092).492 [.090](.090).494 [.090](.090) [.071](.067).497 [.066](.066).497 [.066](.066) [.041](.039).499 [.040](.040).499 [.040](.040) [.180](.158).236 [.156](.155).241 [.155](.155) [.146](.131).242 [.128](.128).244 [.128](.128) [.101](.094).247 [.094](.093).247 [.093](.093) [.060](.059).248 [.059](.059).248 [.059](.059) [.231](.203) [.202](.201) [.201](.201) [.179](.160) [.159](.159) [.159](.158) [.131](.123) [.122](.122) [.122](.122) [.078](.076) [.077](.077) [.077](.076) [.274](.243) [.245](.244) [.244](.244) [.216](.193) [.194](.194) [.194](.193) [.159](.148) [.148](.148) [.148](.148) [.099](.096) [.097](.097) [.097](.097) [.312](.279) [.286](.285) [.285](.285) [.245](.219) [.222](.221) [.222](.221) [.186](.174) [.174](.174) [.174](.174) [.117](.114) [.114](.114) [.114](.114) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 9

10 Table 1-1. Additioal Results i Coectio to Table 1 λ bc2 bc3 se 1 se 2 se 3 se c 3 (g) Group Iteractio with k = 0.35, Normal Errors, MRSAR-B [.149](.126).491 [.129](.128).494 [.129](.129) [.127](.109).496 [.112](.112).498 [.113](.113) [.086](.080).499 [.080](.080).500 [.080](.080) [.051](.049).500 [.050](.050).500 [.050](.050) [.213](.180).237 [.185](.185).241 [.186](.186) [.189](.161).241 [.166](.166).243 [.166](.166) [.130](.120).247 [.120](.120).248 [.120](.120) [.076](.073).249 [.074](.074).249 [.074](.074) [.272](.232) [.241](.241) [.241](.241) [.246](.212) [.219](.219) [.219](.219) [.170](.156) [.157](.157) [.157](.157) [.100](.097).001 [.098](.098).001 [.098](.098) [.328](.279) [.291](.290) [.291](.291) [.301](.256) [.266](.266) [.267](.267) [.211](.195) [.195](.195) [.195](.195) [.125](.120) [.122](.122) [.122](.122) [.384](.325) [.343](.342) [.343](.343) [.360](.307) [.320](.320) [.321](.320) [.247](.229) [.230](.230) [.230](.230) [.150](.145) [.146](.146) [.146](.146) (h) Group Iteractio with k = 0.35, Normal Mixture, MRSAR-B [.149](.127).485 [.127](.126).490 [.127](.126) [.128](.110).491 [.112](.112).493 [.112](.112) [.086](.080).498 [.079](.079).498 [.079](.079) [.050](.048).500 [.048](.048).500 [.048](.048) [.214](.183).229 [.185](.183).235 [.184](.183) [.187](.161).238 [.165](.165).241 [.165](.165) [.128](.118).246 [.117](.117).247 [.117](.117) [.076](.074).248 [.074](.074).248 [.074](.074) [.277](.238) [.242](.240) [.241](.240) [.243](.210) [.215](.214) [.214](.214) [.169](.156) [.156](.156) [.156](.156) [.101](.097) [.098](.098) [.098](.098) [.324](.278) [.284](.283) [.283](.282) [.297](.254) [.262](.262) [.262](.261) [.211](.196) [.196](.196) [.196](.196) [.124](.119) [.121](.121) [.121](.121) [.384](.329) [.339](.336) [.338](.336) [.353](.304) [.314](.313) [.313](.313) [.248](.230) [.231](.231) [.231](.231) [.148](.143) [.145](.145) [.145](.145) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 10

11 Table 1-1 (cot d). Empirical Mea[rmse](sd), ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (i) Group Iteractio with k = 0.35, Logormal Errors, MRSAR-B [.137](.120).484 [.118](.117).489 [.117](.116) [.124](.108).488 [.108](.107).492 [.107](.107) [.085](.080).496 [.079](.079).497 [.079](.078) [.051](.050).499 [.050](.050).499 [.050](.050) [.199](.174).225 [.172](.170).232 [.170](.169) [.177](.155).234 [.156](.155).239 [.154](.154) [.126](.117).245 [.116](.116).246 [.116](.116) [.077](.074).247 [.075](.075).247 [.075](.075) [.252](.223) [.221](.220) [.220](.219) [.231](.200) [.201](.200) [.199](.198) [.171](.159) [.157](.156) [.156](.156) [.102](.098) [.099](.099) [.099](.099) [.319](.282) [.282](.279) [.280](.278) [.289](.252) [.255](.254) [.252](.251) [.208](.194) [.192](.192) [.192](.191) [.126](.121) [.122](.122) [.122](.122) [.376](.333) [.334](.330) [.330](.328) [.333](.288) [.294](.292) [.291](.290) [.243](.226) [.224](.224) [.224](.224) [.152](.147) [.149](.149) [.149](.149) (j) Group Iteractio with k = 0.65, Normal Error, MRSAR-B [.099](.091).498 [.089](.089).500 [.089](.089) [.078](.074).501 [.072](.072).502 [.072](.072) [.058](.055).499 [.054](.054).499 [.054](.054) [.035](.035).500 [.035](.035).500 [.035](.035) [.134](.123).249 [.123](.123).251 [.124](.124) [.109](.102).250 [.101](.101).252 [.101](.101) [.080](.077).250 [.077](.077).251 [.077](.077) [.052](.051).250 [.051](.051).250 [.051](.051) [.159](.146) [.149](.149) [.149](.149) [.133](.125).001 [.125](.125).002 [.125](.125) [.102](.098).000 [.098](.098).001 [.098](.098) [.066](.065) [.065](.065) [.065](.065) [.178](.166) [.171](.171) [.172](.172) [.150](.141) [.142](.142) [.143](.143) [.120](.116) [.116](.116) [.116](.116) [.078](.077) [.077](.077) [.077](.077) [.182](.171) [.179](.179) [.180](.180) [.159](.151) [.155](.155) [.155](.155) [.131](.127) [.128](.128) [.128](.128) [.091](.090) [.090](.090) [.090](.090) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 11

12 Table 1-1 (cot d). Empirical Mea[rmse](sd), ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (k) Group Iteractio with k = 0.65, Normal Mixture, MRSAR-B [.094](.086).498 [.084](.084).500 [.084](.084) [.077](.072).499 [.070](.070).500 [.070](.070) [.057](.054).499 [.054](.054).500 [.054](.054) [.035](.035).500 [.035](.035).500 [.035](.035) [.128](.118).246 [.118](.118).247 [.118](.118) [.106](.099).249 [.098](.098).250 [.098](.098) [.080](.076).249 [.076](.076).249 [.076](.076) [.050](.049).250 [.049](.049).250 [.049](.049) [.152](.141) [.143](.143) [.143](.143) [.128](.120) [.120](.120) [.120](.120) [.099](.095).001 [.095](.095).002 [.095](.095) [.066](.065) [.065](.065) [.065](.065) [.168](.157) [.161](.161) [.161](.161) [.146](.138) [.140](.140) [.140](.140) [.117](.113) [.114](.114) [.114](.114) [.079](.078) [.078](.078) [.078](.078) [.173](.163) [.170](.170) [.171](.170) [.155](.147) [.152](.152) [.152](.152) [.129](.125) [.127](.127) [.127](.127) [.091](.089) [.090](.090) [.090](.090) (l) Group Iteractio with k = 0.65, Logormal Errors, MRSAR-B [.085](.078).496 [.076](.076).498 [.076](.076) [.072](.067).497 [.065](.065).498 [.065](.065) [.053](.050).499 [.050](.050).500 [.050](.050) [.035](.034).500 [.034](.034).500 [.034](.034) [.111](.104).247 [.103](.103).249 [.103](.103) [.097](.091).247 [.090](.090).248 [.090](.090) [.073](.070).250 [.070](.070).250 [.070](.070) [.049](.049).250 [.048](.048).250 [.048](.048) [.135](.125) [.126](.126) [.126](.126) [.117](.109) [.109](.109) [.109](.109) [.092](.088) [.088](.088) [.088](.088) [.063](.062) [.062](.062) [.062](.062) [.150](.141) [.144](.144) [.144](.144) [.133](.125) [.127](.127) [.127](.127) [.109](.106) [.106](.106) [.106](.106) [.076](.075) [.075](.075) [.075](.075) [.161](.153) [.159](.158) [.159](.159) [.145](.138) [.143](.143) [.143](.143) [.124](.121) [.123](.123) [.123](.123) [.089](.088) [.088](.088) [.088](.088) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 12

13 Table 1-2. Replicatio of Table 1, uder β = {.5,.1,.1} λ bc2 bc3 se 1 se 2 se 3 se c 3 (a) Quee, Normal Error, MRSAR-A [.252](.215).486 [.215](.215).493 [.216](.216) [.150](.140).500 [.139](.139).501 [.139](.139) [.098](.093).497 [.093](.093).497 [.093](.093) [.059](.058).500 [.058](.058).500 [.058](.058) [.277](.246).236 [.253](.253).241 [.255](.255) [.181](.171).246 [.173](.173).247 [.174](.174) [.115](.111).247 [.112](.112).247 [.112](.112) [.073](.071).249 [.071](.071).249 [.071](.071) [.296](.264) [.282](.281) [.284](.283) [.198](.188) [.193](.193) [.194](.193) [.135](.131) [.133](.133) [.133](.133) [.080](.080).001 [.080](.080).001 [.080](.080) [.284](.269) [.290](.290) [.292](.292) [.197](.195) [.203](.202) [.203](.203) [.135](.133) [.136](.136) [.136](.136) [.088](.087) [.088](.088) [.088](.088) [.272](.259) [.284](.284) [.286](.286) [.190](.188) [.197](.197) [.198](.198) [.138](.137) [.141](.140) [.141](.141) [.086](.086) [.087](.087) [.087](.087) (b) Quee, Normal Mixture, MRSAR-A [.234](.203).497 [.203](.203).503 [.204](.204) [.150](.138).496 [.138](.138).497 [.138](.138) [.094](.090).502 [.089](.089).502 [.089](.089) [.059](.058).501 [.058](.058).501 [.058](.058) [.259](.229).243 [.235](.235).248 [.237](.237) [.166](.158).252 [.160](.160).253 [.161](.160) [.113](.111).257 [.112](.112).258 [.112](.112) [.071](.070).252 [.071](.071).252 [.071](.071) [.268](.251).009 [.264](.264).012 [.267](.266) [.181](.175).001 [.180](.180).002 [.180](.180) [.128](.127).005 [.128](.128).005 [.128](.128) [.079](.078).001 [.079](.079).001 [.079](.079) [.266](.246) [.265](.265) [.267](.267) [.185](.180) [.186](.186) [.187](.187) [.139](.137) [.139](.139) [.139](.139) [.087](.087) [.087](.087) [.087](.087) [.266](.255) [.278](.277) [.279](.279) [.197](.195) [.204](.204) [.204](.204) [.136](.135) [.138](.138) [.138](.138) [.087](.086) [.087](.087) [.087](.087) Note: se 1 = mea( bv 1( ) 1 2 ), se2 = mea( bv 2( ) 1 2 ), se3 = mea( bv 3( ) 1 2 ) ad se c 3 = mea( bv 3( bc3 ) 1 2 ). 13

14 Table 1-2 (Cot d). Empirical Mea[rmse](sd), ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (c) Quee, logormal, MRSAR-A [.214](.179).493 [.178](.177).499 [.178](.178) [.135](.125).499 [.124](.124).500 [.124](.124) [.089](.086).502 [.085](.085).502 [.085](.085) [.055](.054).499 [.054](.054).499 [.054](.054) [.234](.205).247 [.210](.210).251 [.211](.211) [.159](.150).248 [.151](.151).249 [.151](.151) [.111](.108).248 [.108](.108).249 [.108](.108) [.068](.067).250 [.067](.067).250 [.067](.067) [.263](.233) [.246](.245) [.247](.246) [.166](.161).007 [.165](.165).008 [.165](.165) [.127](.123) [.125](.125) [.125](.125) [.080](.079).001 [.080](.080).001 [.080](.080) [.262](.242) [.260](.259) [.261](.261) [.177](.170) [.176](.176) [.176](.176) [.130](.128) [.130](.130) [.130](.130) [.081](.081) [.081](.081) [.081](.081) [.254](.245) [.266](.266) [.268](.268) [.174](.171) [.178](.178) [.178](.178) [.129](.128) [.131](.131) [.131](.131) [.084](.083) [.084](.084) [.084](.084) (d) Group Iteractio with k = 0.5, Normal Errors, MRSAR-B [.302](.238).488 [.198](.198).502 [.198](.198) [.195](.161).499 [.138](.138).504 [.137](.137) [.141](.125).502 [.112](.112).504 [.112](.112) [.100](.089).498 [.082](.082).498 [.082](.082) [.381](.297).247 [.257](.257).262 [.260](.260) [.285](.235).242 [.208](.208).248 [.208](.208) [.209](.186).255 [.168](.168).257 [.168](.168) [.151](.136).249 [.127](.127).250 [.127](.127) [.464](.365) [.333](.333).010 [.338](.338) [.364](.304) [.277](.277) [.278](.278) [.263](.230).001 [.209](.209).003 [.209](.209) [.188](.167) [.156](.156) [.156](.155) [.564](.441) [.428](.427) [.435](.434) [.396](.330) [.306](.306) [.309](.309) [.330](.296) [.271](.271) [.272](.272) [.241](.216) [.204](.204) [.204](.204) [.568](.436) [.444](.442) [.450](.449) [.465](.387) [.375](.374) [.378](.377) [.374](.321) [.297](.297) [.298](.298) [.260](.237) [.223](.223) [.224](.223) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 14

15 Table 1-2 (Cot d). Empirical Mea[rmse](sd), ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (e) Group Iteractio with k = 0.5, Normal Mixture, MRSAR-B [.284](.224).493 [.184](.184).507 [.184](.184) [.189](.158).502 [.137](.136).507 [.136](.136) [.135](.117).502 [.105](.105).504 [.105](.105) [.099](.090).501 [.083](.083).502 [.083](.083) [.362](.290).258 [.255](.255).272 [.258](.257) [.272](.223).243 [.198](.198).249 [.198](.198) [.200](.174).250 [.157](.157).252 [.157](.157) [.145](.131).252 [.123](.123).253 [.123](.123) [.451](.358) [.328](.328).011 [.334](.334) [.355](.294) [.267](.267) [.269](.269) [.263](.226) [.206](.205) [.206](.206) [.196](.174) [.163](.162) [.162](.162) [.503](.399) [.385](.385) [.393](.393) [.399](.329) [.307](.307) [.310](.310) [.302](.262) [.241](.241) [.242](.242) [.231](.206) [.194](.194) [.194](.194) [.576](.461) [.477](.476) [.484](.484) [.427](.351) [.341](.341) [.346](.346) [.351](.301) [.279](.279) [.280](.280) [.265](.239) [.224](.224) [.224](.224) (f) Group Iteractio with k = 0.5, logormal, MRSAR-B [.235](.184).511 [.155](.154).523 [.156](.154) [.183](.147).495 [.127](.127).499 [.127](.127) [.123](.108).506 [.097](.097).506 [.097](.097) [.095](.083).497 [.077](.077).497 [.077](.077) [.336](.257).251 [.228](.228).263 [.230](.230) [.246](.202).255 [.179](.179).259 [.180](.179) [.179](.155).256 [.140](.140).257 [.140](.140) [.140](.125).250 [.116](.116).249 [.116](.116) [.417](.319) [.291](.291).007 [.295](.295) [.309](.252) [.229](.229).003 [.231](.231) [.243](.207) [.189](.189) [.189](.189) [.178](.161).005 [.151](.151).004 [.151](.151) [.475](.368) [.359](.359) [.365](.365) [.343](.282) [.264](.264) [.267](.266) [.300](.257) [.237](.237) [.237](.237) [.225](.200) [.187](.187) [.187](.187) [.510](.401) [.407](.407) [.414](.414) [.385](.320) [.312](.312) [.316](.316) [.323](.279) [.260](.260) [.261](.261) [.247](.222) [.209](.209) [.210](.210) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 15

16 λ bc2 Table 1-3. Replicatio of Table 1, uder σ = 2 bc3 se 1 se 2 se 3 se c 3 (a) Quee, Normal Error, MRSAR-A [.234](.203).487 [.203](.203).493 [.204](.203) [.143](.134).500 [.134](.134).501 [.133](.133) [.089](.085).497 [.085](.084).498 [.085](.084) [.054](.053).500 [.053](.053).500 [.053](.053) [.256](.229).238 [.235](.235).243 [.236](.236) [.173](.164).245 [.166](.166).246 [.166](.166) [.109](.105).245 [.105](.105).246 [.105](.105) [.067](.066).250 [.066](.066).250 [.066](.066) [.275](.249) [.264](.263) [.266](.266) [.188](.179) [.184](.184) [.184](.184) [.125](.122) [.124](.123) [.124](.124) [.074](.074).001 [.075](.075).001 [.075](.075) [.268](.255) [.273](.273) [.275](.275) [.187](.185) [.191](.191) [.192](.192) [.129](.127) [.130](.130) [.130](.130) [.082](.082) [.082](.082) [.082](.082) [.260](.249) [.270](.270) [.272](.272) [.182](.180) [.188](.188) [.188](.188) [.130](.130) [.132](.132) [.133](.132) [.080](.080) [.081](.081) [.081](.081) (b) Quee, Normal Mixture, MRSAR-A [.215](.188).497 [.189](.189).502 [.190](.190) [.141](.131).497 [.131](.131).498 [.131](.131) [.088](.085).501 [.084](.084).502 [.084](.084) [.054](.053).501 [.053](.053).501 [.053](.053) [.243](.219).244 [.225](.225).248 [.226](.226) [.156](.149).252 [.151](.151).254 [.151](.151) [.108](.106).256 [.107](.107).256 [.107](.107) [.065](.064).251 [.064](.064).251 [.064](.064) [.249](.235).008 [.246](.246).010 [.248](.247) [.170](.165) [.169](.169).001 [.169](.169) [.120](.118).003 [.119](.119).003 [.120](.120) [.073](.073).001 [.073](.073).001 [.073](.073) [.253](.236) [.251](.251) [.253](.253) [.175](.171) [.176](.176) [.176](.176) [.129](.128) [.129](.129) [.130](.130) [.081](.080) [.081](.081) [.081](.081) [.251](.242) [.261](.260) [.262](.262) [.188](.186) [.194](.194) [.194](.194) [.129](.128) [.131](.131) [.131](.131) [.081](.081) [.082](.082) [.082](.082) Note: se 1 = mea( bv 1( ) 1 2 ), se2 = mea( bv 2( ) 1 2 ), se3 = mea( bv 3( ) 1 2 ) ad se c 3 = mea( bv 3( bc3 ) 1 2 ). 16

17 Table 1-3 (cot d). Empirical Mea[rmse](sd), ad Averaged Bootstrap SEs λ bc2 bc3 se 1 se 2 se 3 se c 3 (c) Quee, Logormal Error, MRSAR-A [.194](.166).491 [.166](.165).496 [.166](.166) [.129](.119).497 [.119](.119).498 [.119](.119) [.084](.082).502 [.081](.081).502 [.081](.081) [.050](.048).498 [.048](.048).498 [.048](.048) [.223](.199).242 [.203](.203).246 [.204](.204) [.150](.143).250 [.145](.145).251 [.145](.145) [.105](.102).248 [.103](.103).249 [.103](.103) [.062](.061).250 [.062](.062).250 [.062](.062) [.242](.218) [.228](.227) [.229](.228) [.161](.156).003 [.160](.160).004 [.160](.160) [.120](.116) [.118](.118) [.118](.118) [.074](.073).000 [.073](.073).000 [.073](.073) [.244](.225) [.240](.239) [.241](.241) [.169](.163) [.168](.167) [.168](.168) [.121](.120) [.121](.121) [.121](.121) [.076](.075) [.076](.076) [.076](.076) [.236](.230) [.246](.246) [.247](.247) [.166](.164) [.170](.170) [.170](.170) [.121](.120) [.123](.123) [.123](.123) [.078](.078) [.079](.079) [.079](.079) (d) Group Iteractio with k = 0.5, Normal Error, MRSAR-B [.233](.188).486 [.171](.170).495 [.171](.171) [.145](.122).498 [.115](.115).501 [.115](.115) [.114](.102).501 [.096](.096).502 [.096](.096) [.076](.070).497 [.068](.068).497 [.068](.068) [.314](.254).238 [.237](.237).248 [.238](.238) [.214](.181).241 [.173](.173).244 [.174](.173) [.169](.154).254 [.145](.145).255 [.145](.145) [.112](.103).247 [.100](.100).248 [.100](.100) [.366](.297) [.284](.284).006 [.287](.287) [.275](.237) [.230](.230) [.231](.231) [.218](.195) [.185](.185).001 [.185](.185) [.145](.134) [.130](.130) [.130](.130) [.455](.366) [.363](.362) [.366](.365) [.305](.263) [.257](.257) [.258](.258) [.277](.253) [.241](.241) [.241](.241) [.179](.167) [.163](.163) [.163](.163) [.467](.371) [.382](.381) [.385](.385) [.368](.320) [.320](.320) [.322](.322) [.302](.266) [.256](.256) [.256](.256) [.204](.191) [.187](.187) [.187](.187) Note: se 1 = mea( b V 1( ) 1 2 ), se2 = mea( b V 2( ) 1 2 ), se3 = mea( b V 3( ) 1 2 ) ad se c 3 = mea( b V 3( bc3 ) 1 2 ). 17

A General Method for Third-Order Bias and Variance Corrections on a Nonlinear Estimator

A General Method for Third-Order Bias and Variance Corrections on a Nonlinear Estimator A Geeral Method for Third-Order Bias ad Variace Correctios o a Noliear Estimator Zheli Yag School of Ecoomics, Sigapore Maagemet Uiversity, 90 Stamford Road, Sigapore 178903 emails: zlyag@smu.edu.sg March,

More information

Resampling Methods. X (1/2), i.e., Pr (X i m) = 1/2. We order the data: X (1) X (2) X (n). Define the sample median: ( n.

Resampling Methods. X (1/2), i.e., Pr (X i m) = 1/2. We order the data: X (1) X (2) X (n). Define the sample median: ( n. Jauary 1, 2019 Resamplig Methods Motivatio We have so may estimators with the property θ θ d N 0, σ 2 We ca also write θ a N θ, σ 2 /, where a meas approximately distributed as Oce we have a cosistet estimator

More information

A statistical method to determine sample size to estimate characteristic value of soil parameters

A statistical method to determine sample size to estimate characteristic value of soil parameters A statistical method to determie sample size to estimate characteristic value of soil parameters Y. Hojo, B. Setiawa 2 ad M. Suzuki 3 Abstract Sample size is a importat factor to be cosidered i determiig

More information

MATH 320: Probability and Statistics 9. Estimation and Testing of Parameters. Readings: Pruim, Chapter 4

MATH 320: Probability and Statistics 9. Estimation and Testing of Parameters. Readings: Pruim, Chapter 4 MATH 30: Probability ad Statistics 9. Estimatio ad Testig of Parameters Estimatio ad Testig of Parameters We have bee dealig situatios i which we have full kowledge of the distributio of a radom variable.

More information

CEE 522 Autumn Uncertainty Concepts for Geotechnical Engineering

CEE 522 Autumn Uncertainty Concepts for Geotechnical Engineering CEE 5 Autum 005 Ucertaity Cocepts for Geotechical Egieerig Basic Termiology Set A set is a collectio of (mutually exclusive) objects or evets. The sample space is the (collectively exhaustive) collectio

More information

Properties and Hypothesis Testing

Properties and Hypothesis Testing Chapter 3 Properties ad Hypothesis Testig 3.1 Types of data The regressio techiques developed i previous chapters ca be applied to three differet kids of data. 1. Cross-sectioal data. 2. Time series data.

More information

Lecture 2: Monte Carlo Simulation

Lecture 2: Monte Carlo Simulation STAT/Q SCI 43: Itroductio to Resamplig ethods Sprig 27 Istructor: Ye-Chi Che Lecture 2: ote Carlo Simulatio 2 ote Carlo Itegratio Assume we wat to evaluate the followig itegratio: e x3 dx What ca we do?

More information

DS 100: Principles and Techniques of Data Science Date: April 13, Discussion #10

DS 100: Principles and Techniques of Data Science Date: April 13, Discussion #10 DS 00: Priciples ad Techiques of Data Sciece Date: April 3, 208 Name: Hypothesis Testig Discussio #0. Defie these terms below as they relate to hypothesis testig. a) Data Geeratio Model: Solutio: A set

More information

If, for instance, we were required to test whether the population mean μ could be equal to a certain value μ

If, for instance, we were required to test whether the population mean μ could be equal to a certain value μ STATISTICAL INFERENCE INTRODUCTION Statistical iferece is that brach of Statistics i which oe typically makes a statemet about a populatio based upo the results of a sample. I oesample testig, we essetially

More information

There is no straightforward approach for choosing the warmup period l.

There is no straightforward approach for choosing the warmup period l. B. Maddah INDE 504 Discrete-Evet Simulatio Output Aalysis () Statistical Aalysis for Steady-State Parameters I a otermiatig simulatio, the iterest is i estimatig the log ru steady state measures of performace.

More information

Hypothesis Testing. Evaluation of Performance of Learned h. Issues. Trade-off Between Bias and Variance

Hypothesis Testing. Evaluation of Performance of Learned h. Issues. Trade-off Between Bias and Variance Hypothesis Testig Empirically evaluatig accuracy of hypotheses: importat activity i ML. Three questios: Give observed accuracy over a sample set, how well does this estimate apply over additioal samples?

More information

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 9

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 9 Hypothesis testig PSYCHOLOGICAL RESEARCH (PYC 34-C Lecture 9 Statistical iferece is that brach of Statistics i which oe typically makes a statemet about a populatio based upo the results of a sample. I

More information

A goodness-of-fit test based on the empirical characteristic function and a comparison of tests for normality

A goodness-of-fit test based on the empirical characteristic function and a comparison of tests for normality A goodess-of-fit test based o the empirical characteristic fuctio ad a compariso of tests for ormality J. Marti va Zyl Departmet of Mathematical Statistics ad Actuarial Sciece, Uiversity of the Free State,

More information

Stat 200 -Testing Summary Page 1

Stat 200 -Testing Summary Page 1 Stat 00 -Testig Summary Page 1 Mathematicias are like Frechme; whatever you say to them, they traslate it ito their ow laguage ad forthwith it is somethig etirely differet Goethe 1 Large Sample Cofidece

More information

Chapter 6 Sampling Distributions

Chapter 6 Sampling Distributions Chapter 6 Samplig Distributios 1 I most experimets, we have more tha oe measuremet for ay give variable, each measuremet beig associated with oe radomly selected a member of a populatio. Hece we eed to

More information

Economics 241B Relation to Method of Moments and Maximum Likelihood OLSE as a Maximum Likelihood Estimator

Economics 241B Relation to Method of Moments and Maximum Likelihood OLSE as a Maximum Likelihood Estimator Ecoomics 24B Relatio to Method of Momets ad Maximum Likelihood OLSE as a Maximum Likelihood Estimator Uder Assumptio 5 we have speci ed the distributio of the error, so we ca estimate the model parameters

More information

µ and π p i.e. Point Estimation x And, more generally, the population proportion is approximately equal to a sample proportion

µ and π p i.e. Point Estimation x And, more generally, the population proportion is approximately equal to a sample proportion Poit Estimatio Poit estimatio is the rather simplistic (ad obvious) process of usig the kow value of a sample statistic as a approximatio to the ukow value of a populatio parameter. So we could for example

More information

Statisticians use the word population to refer the total number of (potential) observations under consideration

Statisticians use the word population to refer the total number of (potential) observations under consideration 6 Samplig Distributios Statisticias use the word populatio to refer the total umber of (potetial) observatios uder cosideratio The populatio is just the set of all possible outcomes i our sample space

More information

1 Inferential Methods for Correlation and Regression Analysis

1 Inferential Methods for Correlation and Regression Analysis 1 Iferetial Methods for Correlatio ad Regressio Aalysis I the chapter o Correlatio ad Regressio Aalysis tools for describig bivariate cotiuous data were itroduced. The sample Pearso Correlatio Coefficiet

More information

Parameter, Statistic and Random Samples

Parameter, Statistic and Random Samples Parameter, Statistic ad Radom Samples A parameter is a umber that describes the populatio. It is a fixed umber, but i practice we do ot kow its value. A statistic is a fuctio of the sample data, i.e.,

More information

Output Analysis (2, Chapters 10 &11 Law)

Output Analysis (2, Chapters 10 &11 Law) B. Maddah ENMG 6 Simulatio Output Aalysis (, Chapters 10 &11 Law) Comparig alterative system cofiguratio Sice the output of a simulatio is radom, the comparig differet systems via simulatio should be doe

More information

7-1. Chapter 4. Part I. Sampling Distributions and Confidence Intervals

7-1. Chapter 4. Part I. Sampling Distributions and Confidence Intervals 7-1 Chapter 4 Part I. Samplig Distributios ad Cofidece Itervals 1 7- Sectio 1. Samplig Distributio 7-3 Usig Statistics Statistical Iferece: Predict ad forecast values of populatio parameters... Test hypotheses

More information

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING Lectures MODULE 5 STATISTICS II. Mea ad stadard error of sample data. Biomial distributio. Normal distributio 4. Samplig 5. Cofidece itervals

More information

Expectation and Variance of a random variable

Expectation and Variance of a random variable Chapter 11 Expectatio ad Variace of a radom variable The aim of this lecture is to defie ad itroduce mathematical Expectatio ad variace of a fuctio of discrete & cotiuous radom variables ad the distributio

More information

3 Resampling Methods: The Jackknife

3 Resampling Methods: The Jackknife 3 Resamplig Methods: The Jackkife 3.1 Itroductio I this sectio, much of the cotet is a summary of material from Efro ad Tibshirai (1993) ad Maly (2007). Here are several useful referece texts o resamplig

More information

Instructor: Judith Canner Spring 2010 CONFIDENCE INTERVALS How do we make inferences about the population parameters?

Instructor: Judith Canner Spring 2010 CONFIDENCE INTERVALS How do we make inferences about the population parameters? CONFIDENCE INTERVALS How do we make ifereces about the populatio parameters? The samplig distributio allows us to quatify the variability i sample statistics icludig how they differ from the parameter

More information

Because it tests for differences between multiple pairs of means in one test, it is called an omnibus test.

Because it tests for differences between multiple pairs of means in one test, it is called an omnibus test. Math 308 Sprig 018 Classes 19 ad 0: Aalysis of Variace (ANOVA) Page 1 of 6 Itroductio ANOVA is a statistical procedure for determiig whether three or more sample meas were draw from populatios with equal

More information

Final Examination Solutions 17/6/2010

Final Examination Solutions 17/6/2010 The Islamic Uiversity of Gaza Faculty of Commerce epartmet of Ecoomics ad Political Scieces A Itroductio to Statistics Course (ECOE 30) Sprig Semester 009-00 Fial Eamiatio Solutios 7/6/00 Name: I: Istructor:

More information

Statistical Inference (Chapter 10) Statistical inference = learn about a population based on the information provided by a sample.

Statistical Inference (Chapter 10) Statistical inference = learn about a population based on the information provided by a sample. Statistical Iferece (Chapter 10) Statistical iferece = lear about a populatio based o the iformatio provided by a sample. Populatio: The set of all values of a radom variable X of iterest. Characterized

More information

Random Variables, Sampling and Estimation

Random Variables, Sampling and Estimation Chapter 1 Radom Variables, Samplig ad Estimatio 1.1 Itroductio This chapter will cover the most importat basic statistical theory you eed i order to uderstad the ecoometric material that will be comig

More information

Statistics 511 Additional Materials

Statistics 511 Additional Materials Cofidece Itervals o mu Statistics 511 Additioal Materials This topic officially moves us from probability to statistics. We begi to discuss makig ifereces about the populatio. Oe way to differetiate probability

More information

Overview. p 2. Chapter 9. Pooled Estimate of. q = 1 p. Notation for Two Proportions. Inferences about Two Proportions. Assumptions

Overview. p 2. Chapter 9. Pooled Estimate of. q = 1 p. Notation for Two Proportions. Inferences about Two Proportions. Assumptions Chapter 9 Slide Ifereces from Two Samples 9- Overview 9- Ifereces about Two Proportios 9- Ifereces about Two Meas: Idepedet Samples 9-4 Ifereces about Matched Pairs 9-5 Comparig Variatio i Two Samples

More information

STA Learning Objectives. Population Proportions. Module 10 Comparing Two Proportions. Upon completing this module, you should be able to:

STA Learning Objectives. Population Proportions. Module 10 Comparing Two Proportions. Upon completing this module, you should be able to: STA 2023 Module 10 Comparig Two Proportios Learig Objectives Upo completig this module, you should be able to: 1. Perform large-sample ifereces (hypothesis test ad cofidece itervals) to compare two populatio

More information

Chapter 22. Comparing Two Proportions. Copyright 2010, 2007, 2004 Pearson Education, Inc.

Chapter 22. Comparing Two Proportions. Copyright 2010, 2007, 2004 Pearson Education, Inc. Chapter 22 Comparig Two Proportios Copyright 2010, 2007, 2004 Pearso Educatio, Ic. Comparig Two Proportios Read the first two paragraphs of pg 504. Comparisos betwee two percetages are much more commo

More information

A Note on Box-Cox Quantile Regression Estimation of the Parameters of the Generalized Pareto Distribution

A Note on Box-Cox Quantile Regression Estimation of the Parameters of the Generalized Pareto Distribution A Note o Box-Cox Quatile Regressio Estimatio of the Parameters of the Geeralized Pareto Distributio JM va Zyl Abstract: Makig use of the quatile equatio, Box-Cox regressio ad Laplace distributed disturbaces,

More information

First Year Quantitative Comp Exam Spring, Part I - 203A. f X (x) = 0 otherwise

First Year Quantitative Comp Exam Spring, Part I - 203A. f X (x) = 0 otherwise First Year Quatitative Comp Exam Sprig, 2012 Istructio: There are three parts. Aswer every questio i every part. Questio I-1 Part I - 203A A radom variable X is distributed with the margial desity: >

More information

It should be unbiased, or approximately unbiased. Variance of the variance estimator should be small. That is, the variance estimator is stable.

It should be unbiased, or approximately unbiased. Variance of the variance estimator should be small. That is, the variance estimator is stable. Chapter 10 Variace Estimatio 10.1 Itroductio Variace estimatio is a importat practical problem i survey samplig. Variace estimates are used i two purposes. Oe is the aalytic purpose such as costructig

More information

MA Advanced Econometrics: Properties of Least Squares Estimators

MA Advanced Econometrics: Properties of Least Squares Estimators MA Advaced Ecoometrics: Properties of Least Squares Estimators Karl Whela School of Ecoomics, UCD February 5, 20 Karl Whela UCD Least Squares Estimators February 5, 20 / 5 Part I Least Squares: Some Fiite-Sample

More information

2 1. The r.s., of size n2, from population 2 will be. 2 and 2. 2) The two populations are independent. This implies that all of the n1 n2

2 1. The r.s., of size n2, from population 2 will be. 2 and 2. 2) The two populations are independent. This implies that all of the n1 n2 Chapter 8 Comparig Two Treatmets Iferece about Two Populatio Meas We wat to compare the meas of two populatios to see whether they differ. There are two situatios to cosider, as show i the followig examples:

More information

Kolmogorov-Smirnov type Tests for Local Gaussianity in High-Frequency Data

Kolmogorov-Smirnov type Tests for Local Gaussianity in High-Frequency Data Proceedigs 59th ISI World Statistics Cogress, 5-30 August 013, Hog Kog (Sessio STS046) p.09 Kolmogorov-Smirov type Tests for Local Gaussiaity i High-Frequecy Data George Tauche, Duke Uiversity Viktor Todorov,

More information

t distribution [34] : used to test a mean against an hypothesized value (H 0 : µ = µ 0 ) or the difference

t distribution [34] : used to test a mean against an hypothesized value (H 0 : µ = µ 0 ) or the difference EXST30 Backgroud material Page From the textbook The Statistical Sleuth Mea [0]: I your text the word mea deotes a populatio mea (µ) while the work average deotes a sample average ( ). Variace [0]: The

More information

CEU Department of Economics Econometrics 1, Problem Set 1 - Solutions

CEU Department of Economics Econometrics 1, Problem Set 1 - Solutions CEU Departmet of Ecoomics Ecoometrics, Problem Set - Solutios Part A. Exogeeity - edogeeity The liear coditioal expectatio (CE) model has the followig form: We would like to estimate the effect of some

More information

Parameter, Statistic and Random Samples

Parameter, Statistic and Random Samples Parameter, Statistic ad Radom Samples A parameter is a umber that describes the populatio. It is a fixed umber, but i practice we do ot kow its value. A statistic is a fuctio of the sample data, i.e.,

More information

Discrete Mathematics for CS Spring 2008 David Wagner Note 22

Discrete Mathematics for CS Spring 2008 David Wagner Note 22 CS 70 Discrete Mathematics for CS Sprig 2008 David Wager Note 22 I.I.D. Radom Variables Estimatig the bias of a coi Questio: We wat to estimate the proportio p of Democrats i the US populatio, by takig

More information

Chi-Squared Tests Math 6070, Spring 2006

Chi-Squared Tests Math 6070, Spring 2006 Chi-Squared Tests Math 6070, Sprig 2006 Davar Khoshevisa Uiversity of Utah February XXX, 2006 Cotets MLE for Goodess-of Fit 2 2 The Multiomial Distributio 3 3 Applicatio to Goodess-of-Fit 6 3 Testig for

More information

Summary and Discussion on Simultaneous Analysis of Lasso and Dantzig Selector

Summary and Discussion on Simultaneous Analysis of Lasso and Dantzig Selector Summary ad Discussio o Simultaeous Aalysis of Lasso ad Datzig Selector STAT732, Sprig 28 Duzhe Wag May 4, 28 Abstract This is a discussio o the work i Bickel, Ritov ad Tsybakov (29). We begi with a short

More information

Double Stage Shrinkage Estimator of Two Parameters. Generalized Exponential Distribution

Double Stage Shrinkage Estimator of Two Parameters. Generalized Exponential Distribution Iteratioal Mathematical Forum, Vol., 3, o. 3, 3-53 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/.9/imf.3.335 Double Stage Shrikage Estimator of Two Parameters Geeralized Expoetial Distributio Alaa M.

More information

Control Charts for Mean for Non-Normally Correlated Data

Control Charts for Mean for Non-Normally Correlated Data Joural of Moder Applied Statistical Methods Volume 16 Issue 1 Article 5 5-1-017 Cotrol Charts for Mea for No-Normally Correlated Data J. R. Sigh Vikram Uiversity, Ujjai, Idia Ab Latif Dar School of Studies

More information

THE SYSTEMATIC AND THE RANDOM. ERRORS - DUE TO ELEMENT TOLERANCES OF ELECTRICAL NETWORKS

THE SYSTEMATIC AND THE RANDOM. ERRORS - DUE TO ELEMENT TOLERANCES OF ELECTRICAL NETWORKS R775 Philips Res. Repts 26,414-423, 1971' THE SYSTEMATIC AND THE RANDOM. ERRORS - DUE TO ELEMENT TOLERANCES OF ELECTRICAL NETWORKS by H. W. HANNEMAN Abstract Usig the law of propagatio of errors, approximated

More information

Lecture 19: Convergence

Lecture 19: Convergence Lecture 19: Covergece Asymptotic approach I statistical aalysis or iferece, a key to the success of fidig a good procedure is beig able to fid some momets ad/or distributios of various statistics. I may

More information

Binomial Distribution

Binomial Distribution 0.0 0.5 1.0 1.5 2.0 2.5 3.0 0 1 2 3 4 5 6 7 0.0 0.5 1.0 1.5 2.0 2.5 3.0 Overview Example: coi tossed three times Defiitio Formula Recall that a r.v. is discrete if there are either a fiite umber of possible

More information

11 Correlation and Regression

11 Correlation and Regression 11 Correlatio Regressio 11.1 Multivariate Data Ofte we look at data where several variables are recorded for the same idividuals or samplig uits. For example, at a coastal weather statio, we might record

More information

MOST PEOPLE WOULD RATHER LIVE WITH A PROBLEM THEY CAN'T SOLVE, THAN ACCEPT A SOLUTION THEY CAN'T UNDERSTAND.

MOST PEOPLE WOULD RATHER LIVE WITH A PROBLEM THEY CAN'T SOLVE, THAN ACCEPT A SOLUTION THEY CAN'T UNDERSTAND. XI-1 (1074) MOST PEOPLE WOULD RATHER LIVE WITH A PROBLEM THEY CAN'T SOLVE, THAN ACCEPT A SOLUTION THEY CAN'T UNDERSTAND. R. E. D. WOOLSEY AND H. S. SWANSON XI-2 (1075) STATISTICAL DECISION MAKING Advaced

More information

Chapter 2 The Monte Carlo Method

Chapter 2 The Monte Carlo Method Chapter 2 The Mote Carlo Method The Mote Carlo Method stads for a broad class of computatioal algorithms that rely o radom sampligs. It is ofte used i physical ad mathematical problems ad is most useful

More information

4 Multidimensional quantitative data

4 Multidimensional quantitative data Chapter 4 Multidimesioal quatitative data 4 Multidimesioal statistics Basic statistics are ow part of the curriculum of most ecologists However, statistical techiques based o such simple distributios as

More information

CSE 527, Additional notes on MLE & EM

CSE 527, Additional notes on MLE & EM CSE 57 Lecture Notes: MLE & EM CSE 57, Additioal otes o MLE & EM Based o earlier otes by C. Grat & M. Narasimha Itroductio Last lecture we bega a examiatio of model based clusterig. This lecture will be

More information

1.010 Uncertainty in Engineering Fall 2008

1.010 Uncertainty in Engineering Fall 2008 MIT OpeCourseWare http://ocw.mit.edu.00 Ucertaity i Egieerig Fall 2008 For iformatio about citig these materials or our Terms of Use, visit: http://ocw.mit.edu.terms. .00 - Brief Notes # 9 Poit ad Iterval

More information

Econ 325/327 Notes on Sample Mean, Sample Proportion, Central Limit Theorem, Chi-square Distribution, Student s t distribution 1.

Econ 325/327 Notes on Sample Mean, Sample Proportion, Central Limit Theorem, Chi-square Distribution, Student s t distribution 1. Eco 325/327 Notes o Sample Mea, Sample Proportio, Cetral Limit Theorem, Chi-square Distributio, Studet s t distributio 1 Sample Mea By Hiro Kasahara We cosider a radom sample from a populatio. Defiitio

More information

Lecture 3. Properties of Summary Statistics: Sampling Distribution

Lecture 3. Properties of Summary Statistics: Sampling Distribution Lecture 3 Properties of Summary Statistics: Samplig Distributio Mai Theme How ca we use math to justify that our umerical summaries from the sample are good summaries of the populatio? Lecture Summary

More information

This chapter focuses on two experimental designs that are crucial to comparative studies: (1) independent samples and (2) matched pair samples.

This chapter focuses on two experimental designs that are crucial to comparative studies: (1) independent samples and (2) matched pair samples. Chapter 9 & : Comparig Two Treatmets: This chapter focuses o two eperimetal desigs that are crucial to comparative studies: () idepedet samples ad () matched pair samples Idepedet Radom amples from Two

More information

Topic 9: Sampling Distributions of Estimators

Topic 9: Sampling Distributions of Estimators Topic 9: Samplig Distributios of Estimators Course 003, 2016 Page 0 Samplig distributios of estimators Sice our estimators are statistics (particular fuctios of radom variables), their distributio ca be

More information

Simulation. Two Rule For Inverting A Distribution Function

Simulation. Two Rule For Inverting A Distribution Function Simulatio Two Rule For Ivertig A Distributio Fuctio Rule 1. If F(x) = u is costat o a iterval [x 1, x 2 ), the the uiform value u is mapped oto x 2 through the iversio process. Rule 2. If there is a jump

More information

Comparing Two Populations. Topic 15 - Two Sample Inference I. Comparing Two Means. Comparing Two Pop Means. Background Reading

Comparing Two Populations. Topic 15 - Two Sample Inference I. Comparing Two Means. Comparing Two Pop Means. Background Reading Topic 15 - Two Sample Iferece I STAT 511 Professor Bruce Craig Comparig Two Populatios Research ofte ivolves the compariso of two or more samples from differet populatios Graphical summaries provide visual

More information

Basics of Probability Theory (for Theory of Computation courses)

Basics of Probability Theory (for Theory of Computation courses) Basics of Probability Theory (for Theory of Computatio courses) Oded Goldreich Departmet of Computer Sciece Weizma Istitute of Sciece Rehovot, Israel. oded.goldreich@weizma.ac.il November 24, 2008 Preface.

More information

Topic 9: Sampling Distributions of Estimators

Topic 9: Sampling Distributions of Estimators Topic 9: Samplig Distributios of Estimators Course 003, 2018 Page 0 Samplig distributios of estimators Sice our estimators are statistics (particular fuctios of radom variables), their distributio ca be

More information

AP Statistics Review Ch. 8

AP Statistics Review Ch. 8 AP Statistics Review Ch. 8 Name 1. Each figure below displays the samplig distributio of a statistic used to estimate a parameter. The true value of the populatio parameter is marked o each samplig distributio.

More information

AAEC/ECON 5126 FINAL EXAM: SOLUTIONS

AAEC/ECON 5126 FINAL EXAM: SOLUTIONS AAEC/ECON 5126 FINAL EXAM: SOLUTIONS SPRING 2015 / INSTRUCTOR: KLAUS MOELTNER This exam is ope-book, ope-otes, but please work strictly o your ow. Please make sure your ame is o every sheet you re hadig

More information

Analysis of Experimental Measurements

Analysis of Experimental Measurements Aalysis of Experimetal Measuremets Thik carefully about the process of makig a measuremet. A measuremet is a compariso betwee some ukow physical quatity ad a stadard of that physical quatity. As a example,

More information

General IxJ Contingency Tables

General IxJ Contingency Tables page1 Geeral x Cotigecy Tables We ow geeralize our previous results from the prospective, retrospective ad cross-sectioal studies ad the Poisso samplig case to x cotigecy tables. For such tables, the test

More information

ECO 312 Fall 2013 Chris Sims LIKELIHOOD, POSTERIORS, DIAGNOSING NON-NORMALITY

ECO 312 Fall 2013 Chris Sims LIKELIHOOD, POSTERIORS, DIAGNOSING NON-NORMALITY ECO 312 Fall 2013 Chris Sims LIKELIHOOD, POSTERIORS, DIAGNOSING NON-NORMALITY (1) A distributio that allows asymmetry differet probabilities for egative ad positive outliers is the asymmetric double expoetial,

More information

Kinetics of Complex Reactions

Kinetics of Complex Reactions Kietics of Complex Reactios by Flick Colema Departmet of Chemistry Wellesley College Wellesley MA 28 wcolema@wellesley.edu Copyright Flick Colema 996. All rights reserved. You are welcome to use this documet

More information

Element sampling: Part 2

Element sampling: Part 2 Chapter 4 Elemet samplig: Part 2 4.1 Itroductio We ow cosider uequal probability samplig desigs which is very popular i practice. I the uequal probability samplig, we ca improve the efficiecy of the resultig

More information

Bayesian Methods: Introduction to Multi-parameter Models

Bayesian Methods: Introduction to Multi-parameter Models Bayesia Methods: Itroductio to Multi-parameter Models Parameter: θ = ( θ, θ) Give Likelihood p(y θ) ad prior p(θ ), the posterior p proportioal to p(y θ) x p(θ ) Margial posterior ( θ, θ y) is Iterested

More information

CHAPTER 2. Mean This is the usual arithmetic mean or average and is equal to the sum of the measurements divided by number of measurements.

CHAPTER 2. Mean This is the usual arithmetic mean or average and is equal to the sum of the measurements divided by number of measurements. CHAPTER 2 umerical Measures Graphical method may ot always be sufficiet for describig data. You ca use the data to calculate a set of umbers that will covey a good metal picture of the frequecy distributio.

More information

STAT 350 Handout 19 Sampling Distribution, Central Limit Theorem (6.6)

STAT 350 Handout 19 Sampling Distribution, Central Limit Theorem (6.6) STAT 350 Hadout 9 Samplig Distributio, Cetral Limit Theorem (6.6) A radom sample is a sequece of radom variables X, X 2,, X that are idepedet ad idetically distributed. o This property is ofte abbreviated

More information

Chapter 22. Comparing Two Proportions. Copyright 2010 Pearson Education, Inc.

Chapter 22. Comparing Two Proportions. Copyright 2010 Pearson Education, Inc. Chapter 22 Comparig Two Proportios Copyright 2010 Pearso Educatio, Ic. Comparig Two Proportios Comparisos betwee two percetages are much more commo tha questios about isolated percetages. Ad they are more

More information

A quick activity - Central Limit Theorem and Proportions. Lecture 21: Testing Proportions. Results from the GSS. Statistics and the General Population

A quick activity - Central Limit Theorem and Proportions. Lecture 21: Testing Proportions. Results from the GSS. Statistics and the General Population A quick activity - Cetral Limit Theorem ad Proportios Lecture 21: Testig Proportios Statistics 10 Coli Rudel Flip a coi 30 times this is goig to get loud! Record the umber of heads you obtaied ad calculate

More information

Investigating the Significance of a Correlation Coefficient using Jackknife Estimates

Investigating the Significance of a Correlation Coefficient using Jackknife Estimates Iteratioal Joural of Scieces: Basic ad Applied Research (IJSBAR) ISSN 2307-4531 (Prit & Olie) http://gssrr.org/idex.php?joural=jouralofbasicadapplied ---------------------------------------------------------------------------------------------------------------------------

More information

Estimation of Gumbel Parameters under Ranked Set Sampling

Estimation of Gumbel Parameters under Ranked Set Sampling Joural of Moder Applied Statistical Methods Volume 13 Issue 2 Article 11-2014 Estimatio of Gumbel Parameters uder Raked Set Samplig Omar M. Yousef Al Balqa' Applied Uiversity, Zarqa, Jorda, abuyaza_o@yahoo.com

More information

The Sample Variance Formula: A Detailed Study of an Old Controversy

The Sample Variance Formula: A Detailed Study of an Old Controversy The Sample Variace Formula: A Detailed Study of a Old Cotroversy Ky M. Vu PhD. AuLac Techologies Ic. c 00 Email: kymvu@aulactechologies.com Abstract The two biased ad ubiased formulae for the sample variace

More information

Lecture 22: Review for Exam 2. 1 Basic Model Assumptions (without Gaussian Noise)

Lecture 22: Review for Exam 2. 1 Basic Model Assumptions (without Gaussian Noise) Lecture 22: Review for Exam 2 Basic Model Assumptios (without Gaussia Noise) We model oe cotiuous respose variable Y, as a liear fuctio of p umerical predictors, plus oise: Y = β 0 + β X +... β p X p +

More information

EECS564 Estimation, Filtering, and Detection Hwk 2 Solns. Winter p θ (z) = (2θz + 1 θ), 0 z 1

EECS564 Estimation, Filtering, and Detection Hwk 2 Solns. Winter p θ (z) = (2θz + 1 θ), 0 z 1 EECS564 Estimatio, Filterig, ad Detectio Hwk 2 Sols. Witer 25 4. Let Z be a sigle observatio havig desity fuctio where. p (z) = (2z + ), z (a) Assumig that is a oradom parameter, fid ad plot the maximum

More information

PROPERTIES OF AN EULER SQUARE

PROPERTIES OF AN EULER SQUARE PROPERTIES OF N EULER SQURE bout 0 the mathematicia Leoard Euler discussed the properties a x array of letters or itegers ow kow as a Euler or Graeco-Lati Square Such squares have the property that every

More information

GUIDELINES ON REPRESENTATIVE SAMPLING

GUIDELINES ON REPRESENTATIVE SAMPLING DRUGS WORKING GROUP VALIDATION OF THE GUIDELINES ON REPRESENTATIVE SAMPLING DOCUMENT TYPE : REF. CODE: ISSUE NO: ISSUE DATE: VALIDATION REPORT DWG-SGL-001 002 08 DECEMBER 2012 Ref code: DWG-SGL-001 Issue

More information

Lecture 7: Density Estimation: k-nearest Neighbor and Basis Approach

Lecture 7: Density Estimation: k-nearest Neighbor and Basis Approach STAT 425: Itroductio to Noparametric Statistics Witer 28 Lecture 7: Desity Estimatio: k-nearest Neighbor ad Basis Approach Istructor: Ye-Chi Che Referece: Sectio 8.4 of All of Noparametric Statistics.

More information

Vector Quantization: a Limiting Case of EM

Vector Quantization: a Limiting Case of EM . Itroductio & defiitios Assume that you are give a data set X = { x j }, j { 2,,, }, of d -dimesioal vectors. The vector quatizatio (VQ) problem requires that we fid a set of prototype vectors Z = { z

More information

A NEW METHOD FOR CONSTRUCTING APPROXIMATE CONFIDENCE INTERVALS FOR M-ESTU1ATES. Dennis D. Boos

A NEW METHOD FOR CONSTRUCTING APPROXIMATE CONFIDENCE INTERVALS FOR M-ESTU1ATES. Dennis D. Boos .- A NEW METHOD FOR CONSTRUCTING APPROXIMATE CONFIDENCE INTERVALS FOR M-ESTU1ATES by Deis D. Boos Departmet of Statistics North Carolia State Uiversity Istitute of Statistics Mimeo Series #1198 September,

More information

Goodness-Of-Fit For The Generalized Exponential Distribution. Abstract

Goodness-Of-Fit For The Generalized Exponential Distribution. Abstract Goodess-Of-Fit For The Geeralized Expoetial Distributio By Amal S. Hassa stitute of Statistical Studies & Research Cairo Uiversity Abstract Recetly a ew distributio called geeralized expoetial or expoetiated

More information

Chapter 6 Principles of Data Reduction

Chapter 6 Principles of Data Reduction Chapter 6 for BST 695: Special Topics i Statistical Theory. Kui Zhag, 0 Chapter 6 Priciples of Data Reductio Sectio 6. Itroductio Goal: To summarize or reduce the data X, X,, X to get iformatio about a

More information

Computing Confidence Intervals for Sample Data

Computing Confidence Intervals for Sample Data Computig Cofidece Itervals for Sample Data Topics Use of Statistics Sources of errors Accuracy, precisio, resolutio A mathematical model of errors Cofidece itervals For meas For variaces For proportios

More information

Inferential Statistics. Inference Process. Inferential Statistics and Probability a Holistic Approach. Inference Process.

Inferential Statistics. Inference Process. Inferential Statistics and Probability a Holistic Approach. Inference Process. Iferetial Statistics ad Probability a Holistic Approach Iferece Process Chapter 8 Poit Estimatio ad Cofidece Itervals This Course Material by Maurice Geraghty is licesed uder a Creative Commos Attributio-ShareAlike

More information

(6) Fundamental Sampling Distribution and Data Discription

(6) Fundamental Sampling Distribution and Data Discription 34 Stat Lecture Notes (6) Fudametal Samplig Distributio ad Data Discriptio ( Book*: Chapter 8,pg5) Probability& Statistics for Egieers & Scietists By Walpole, Myers, Myers, Ye 8.1 Radom Samplig: Populatio:

More information

Kernel density estimator

Kernel density estimator Jauary, 07 NONPARAMETRIC ERNEL DENSITY ESTIMATION I this lecture, we discuss kerel estimatio of probability desity fuctios PDF Noparametric desity estimatio is oe of the cetral problems i statistics I

More information

6 Sample Size Calculations

6 Sample Size Calculations 6 Sample Size Calculatios Oe of the major resposibilities of a cliical trial statisticia is to aid the ivestigators i determiig the sample size required to coduct a study The most commo procedure for determiig

More information

Chapter If n is odd, the median is the exact middle number If n is even, the median is the average of the two middle numbers

Chapter If n is odd, the median is the exact middle number If n is even, the median is the average of the two middle numbers Chapter 4 4-1 orth Seattle Commuity College BUS10 Busiess Statistics Chapter 4 Descriptive Statistics Summary Defiitios Cetral tedecy: The extet to which the data values group aroud a cetral value. Variatio:

More information

Lecture 33: Bootstrap

Lecture 33: Bootstrap Lecture 33: ootstrap Motivatio To evaluate ad compare differet estimators, we eed cosistet estimators of variaces or asymptotic variaces of estimators. This is also importat for hypothesis testig ad cofidece

More information

Statistical Analysis on Uncertainty for Autocorrelated Measurements and its Applications to Key Comparisons

Statistical Analysis on Uncertainty for Autocorrelated Measurements and its Applications to Key Comparisons Statistical Aalysis o Ucertaity for Autocorrelated Measuremets ad its Applicatios to Key Comparisos Nie Fa Zhag Natioal Istitute of Stadards ad Techology Gaithersburg, MD 0899, USA Outlies. Itroductio.

More information

1 Review of Probability & Statistics

1 Review of Probability & Statistics 1 Review of Probability & Statistics a. I a group of 000 people, it has bee reported that there are: 61 smokers 670 over 5 960 people who imbibe (drik alcohol) 86 smokers who imbibe 90 imbibers over 5

More information

Castiel, Supernatural, Season 6, Episode 18

Castiel, Supernatural, Season 6, Episode 18 13 Differetial Equatios the aswer to your questio ca best be epressed as a series of partial differetial equatios... Castiel, Superatural, Seaso 6, Episode 18 A differetial equatio is a mathematical equatio

More information

An Introduction to Randomized Algorithms

An Introduction to Randomized Algorithms A Itroductio to Radomized Algorithms The focus of this lecture is to study a radomized algorithm for quick sort, aalyze it usig probabilistic recurrece relatios, ad also provide more geeral tools for aalysis

More information