JSM Survey Research Methods Section. Is it MAR or NMAR? Michail Sverchkov
|
|
- Reynard Golden
- 5 years ago
- Views:
Transcription
1 JSM Survey Researh Methods Seton Is t MAR or NMAR? Mhal Sverhkov Bureau of Labor Statsts 2 Massahusetts Avenue, NE, Sute 1950, Washngton, DC , Sverhkov.Mhael@bls.gov Abstrat Most methods that deal wth the estmaton of response probabltes assume ether expltly or mpltly that the mssng data are mssng at random (MAR). However, n many pratal stuatons ths assumpton s not vald, sne the probablty of respondng often depends on the outome value or on latent varables related to the outome. The ase where the mssng data are not MAR (NMAR) an be treated by postulatng a parametr model for the dstrbuton of the outomes under full response and a model for the response probabltes. The two models defne a parametr model for the jont dstrbuton of the outome and the response ndator, and therefore the parameters of ths model an be estmated by maxmzaton of the lkelhood orrespondng to ths dstrbuton. Modelng the dstrbuton of the outomes under full response, however, an be problemat sne no data are avalable from ths dstrbuton. Sverhkov (2008) proposed a new approah that permts estmatng the parameters of the model for the response probabltes wthout modellng the dstrbuton of the outomes under full response. The approah utlzes relatonshps between the populaton, the sample and the sample-omplement dstrbuton derved n Pfeffermann and Sverhkov (1999) and Sverhkov and Pfeffermann (2004). The present paper nvestgates how ths approah an be used for testng whether response s MAR or NMAR. Key words: sample dstrbuton, omplement-sample dstrbuton, predton under nformatve samplng and non-response, estmatng equatons, mssng nformaton prnple, non-parametr estmaton 1. Introduton There s almost no survey wthout nonresponse, but n prate most methods that deal wth ths problem assume ether expltly or mpltly that the mssng data are mssng at random (MAR, Rubn, 1976; Lttle, 1982). However, n many pratal stuatons ths assumpton s not vald, sne the probablty of respondng often depends dretly on the outome value. In ths ase, the use of methods that assume that the nonresponse s MAR an lead to large bases of populaton parameter estmators and large mputaton bas. The ase where the mssng data are not MAR (NMAR) an be treated by postulatng a parametr model for the dstrbuton of the outomes before non-response and a model for the response mehansm. These two models defne a parametr model for the jont dstrbuton of the outomes and response ndators, and therefore the parameters of these models an be estmated by maxmzaton of the lkelhood based on ths jont dstrbuton. See, Greenlees et al. (1982), Rubn (1987), Lttle (1993), Beaumont (2000), Lttle and Rubn (2002) and Qn et al. (2002). Modelng the dstrbuton of the outomes before non-response an be problemat sne t refers to the partly unobserved data. Qn et al. (2002) suggests usng a non-parametr model for ths dstrbuton (empral lkelhood approah). Sverhkov (2008) suggests an alternatve approah that allows one to estmate the parameters of the response model by ndependent parametr or non-parametr estmaton of the outomes dstrbuton after non-response (whh an be done by 2306
2 JSM Survey Researh Methods Seton use of lass statstal nferenes sne the latter refers to the observed data) and then by solvng estmatng equatons obtaned from the ensus lkelhood funton of the response ndators. The dervaton of these estmatng equatons utlzes the relatonshps between the populaton, the sample and the sample-omplement dstrbutons, as n Pfeffermann and Sverhkov (1999, 2003), Sverhkov and Pfeffermann (2004). Even under ths approah one needs to assume a model for the response mehansm whh annot be heked from the observed data n ase of NMAR. Therefore t s mportant to know whether the response s MAR or NMAR. The present paper nvestgates how the Sverhkov (2008) approah an be used for testng whether response s MAR or NMAR. 2. Notaton Let Y denote the value of an outome varable Y assoated wth unt belongng to a sample S {1,..., n}, drawn from a fnte populaton U {1,..., N}. Let X denote the orrespondng values of ovarates X ( X1,..., X K ). In what follows we assume that the populaton outome values are ndependent realzatons from dstrbutons wth unknown probablty densty funtons (pdf), f ( Y X ). We use the abbrevaton pdf for the probablty densty funton when Y s ontnuous and the probablty funton when Y s dsrete. Let R {1,..., n r } defne the sample of respondents (the sample wth observed outome values), and R { nr 1,..., n} defne the sample of nonrespondents. The response proess s assumed to our stohastally, ndependently between unts. The observed sample of respondents an be vewed therefore as the result of a two-phase samplng proess where n the frst phase the sample S s seleted from U wth known nluson probabltes Pr( S) and n the seond phase the sample R s self seleted wth unknown response probabltes (Särndal and Swensson, 1987). Denote by p( Y, X) Pr( R Y, X, S) and let u and v be any random vetors suh that ( u, v ) and response ndators, R ( R 1 f R and 0 otherwse), are ndependent gven ( Y, X, S). For example, u and v are funtons of ( Y, X ), or the responses are ompletely defned by ( Y, X ). In what follows we use the followng relatonshps between populaton and sample dstrbuton (Pfeffermann and Sverhkov 1999, 2003 and Sverhkov and Pfeffermann 2004) whh an be wrtten n terms of response probabltes as, E( p ( Y, X ) u v, R) E( u v, S), (2.1) E( p ( Y, X ) v, R) E( u v, R ) E{[ p ( Y, X ) ] u v, R) E{[ p ( Y, X ) ] v, R). (2.2) Note that (2.1) mples E[ p ( Y, X ) R] / E[ p( Y, X ) S]. (2.3) Remark 2.1 In the followng setons we onentrate on estmaton of the response probabltes p( Y, X ). Note that f the response probabltes or ther estmates are known then the sample respondents an be onsdered as a sample from the fnte populaton wth known, p( Y, X), or estmated seleton probabltes, ˆ pˆ( Y, X). Then populaton model parameters (or fnte populaton parameters) an be estmated as f there were no non-response wth these new nluson probabltes, see Särndal and Swensson (1987). One an use these probabltes for mputaton also usng the relatonshp between the sample and sampleomplement dstrbutons derved n Sverhkov and Pfeffermann (2004), 2307
3 JSM Survey Researh Methods Seton f ( u v, R ) [ p ( Y, X ) ] f ( u v, R) E{[ p ( Y, X ) ] v, R}. (2.4) 3. Estmaton of the Response Probabltes when Non-Response s NMAR Let p( Y, X ; ) Pr( R Y, X, S; ) be a parametr set of pdf s and suppose that p( Y, X ; ) s dfferentable wth respet to (vetor) parameter. For smplty we onsder the followng senaro: The ovarates are observed for all nonrespondents,.e. Observed Data={ Y, R, X, k S}. k Under ths senaro, f the mssng data were later observed, ould be estmated by solvng the lkelhood equatons, log p( Y, X ; ) log[1 p( Y, X ; )] 0 R R. (3.1) Smlarly to the Mssng Informaton Prnple (Cplln et al, 1955, Orhard and Woodbury 1972), sne the outome values are mssng for j R, we propose to solve nstead, log p( Y, X ; ) log[1 p( Y, X ; )] 0 E[ Observed Data],.e., R R log p( Y, X ; ) log[1 p( Y, X ; )] 0 E[ { Y, R, X k, k S}] R R log p( Y, X ; ) log[1 p( Y, X ; )] E[ R,{ X k, k S}] R R R log p( Y, X ; ) p( Y, X ; ) p R log[1 p( Y, X ; )] E{[ p ( Y, X ; ) ] X, R} (3.2a) R E{[ p ( Y, X ; ) ] X, R} ( Y, X ; ) p( Y, X ; ) p ( Y, X ; ) f ( Y X, R) dy p ( Y, X ; ) f ( Y X, R) dy. (3.2b) R The thrd equaton follows from (2.2) where we assume for smplty that p( Y, X; ) and ( X k, k S) are ndependent gven X. Note that the seond sum n (3.2a) and (3.2b) predts the unobserved seond sum n (3.1). Note also that f p( Y, X; ) s a funton of X and only (mssng data are MAR) then (3.2b) redues to a ommon system of log-lkelhood equatons, log p( X ; ) log[1 p( X ; )] 0. (3.3) R R Estmatng funtons (3.2b) suggest the followng two-step estmaton proedure: Step 1. Ft the model fr( Y X) f ( Y X, R). Note that ths pdf refers to the respondents sample and therefore an be dentfed and estmated from the observed data usng lass statstal nferene. Step 2. Approxmate (3.2b) by replang fr( Y X ) by ts estmate, f ˆ r( Y X ), and solve (3.2b) for. 2308
4 JSM Survey Researh Methods Seton Note that nstead of estmaton of f r n (3.2b) one an estmate the expetatons n (3.2a) nonparametrally, and after substtutng the estmates n (3.2a) solve them for. For example, for dsrete X -s and an arbtrary funton g, E[ g( Y, X, ) X x, j R] an be estmated by the j j j respetve mean, 1 g( Y j, X j, ). For ontnuous X -s let mx (, ) be an jr: X jx jr: X jx estmator of E( g( Y, X, ) X x, j R), for example the Nadaraya-Watson estmator, mx (, ) jr j j j K[( x X j ) / h] g( Y j, X j, ), where h and K are a sale-fator and a kernel. K[( x X ) / h] jr j Estmatng the respetve ondtonal expetatons n the seond sum of (3.2a) by mx (, ) one obtans the followng estmatng equatons, p( Yk, X k; ) p( Y, X ; ) K[( X k X j ) / h] p ( Yk, X k; ) kr p ( Y, X ; ) 0, (3.4) 1 K[( X X ) / h][ p ( Y, X ; ) ] R whh defnes an estmator of. jr k j k k kr Estmatng equatons (3.4) do not requre any knowledge of the model for the respondents. On the other hand one an expet that the estmates obtaned by solvng (3.4) wll be less stable than the estmates obtaned from (3.2b) by the above two step estmaton proedure when the model for the respondents an be ftted well. See Sverhkov (2008) for the detals. 4. Is t MAR or NMAR? The proposed approah requres knowledge of the parametr form of the response model whh refers to the unobserved data n the ase of NMAR. On the other hand, f response s MAR, the propensty sore, px ( ; ) Pr( R X, S; ), an be estmated from the observed data for example by solvng a ommon system of log-lkelhood equatons (3.3). Note that the latter estmator muh more stable than the estmators assumng NMAR. Therefore t s very mportant to know whether response s MAR or NMAR. We suggest usng the followng proedure for testng the latter: Step 1. Ft the model for propensty sore, px ( ; ) Pr( R X, S; ), and estmate the parameter from the observed data assumng MAR. Step 2. Defne a lass of models for p( Y, X; ) Pr( R Y, X, S; ),, n suh way that for some, p( Y, X ; ) px ( ; ). It reommended to use models that nlude the Y- omponent n a smple form, for example, f logt[ p( X; )] g( X; ) then one an onsder logt[ p( Y, X; )] g(x ; ) Y, (, ), so n ths ase for (,0), p( Y, X ; ) px ( ; ). Step 3. Obtan estmatng equatons (3.2a) based on the lass of models defned n Step 2. Step 4.1. Solve them and hek whether Y-omponent s sgnfant (n whh ase the response s for sure NMAR ) or not (the response s MAR or not very nformatve ). 2309
5 JSM Survey Researh Methods Seton The latter an be done by a bootstrap proedure: one an take B smple random samples wth replaement from the orgnal sample and repeat steps 1 4 above n order to get a varane estmate for the Y-omponent. Remark 4.1. Sne the parametr famly defned n Step 2 does not neessarly nlude the true response probablty Pr( R Y, X, S), even f the Y-omponent s nsgnfant we annot onlude for sure that response s MAR. Nevertheless, we reommend to use propensty sore assumng MAR n ths ase. If response s very nformatve then one an expet that the Y- omponent wll be sgnfant even n a smplfed model. Instead of Step 4.1 one an do Step 4.2. Substtute from Step 2 nto (3.2a-b) obtaned n Steps 1-3 and hek whether the result s sgnfantly non-zero (response s NMAR) or not (response seems to be MAR sne orresponds to the propensty sore). The latter an also be done by use of a bootstrap. Aknowledgements The opnons expressed n ths paper are those of the author and do not neessarly represent the poles of the Bureau of Labor Statsts. Referenes Beaumont, J.F. (2000). An estmaton method for nongnorable nonresponse, Survey Methodology, 26, Ceplln, R., Snsalo, M., and Smth, C.A.B. (1955). The estmaton of gene frequenes n a random matng populaton, Annals of Human Genets, 20, Greenlees, J.S. Reee, W.S. and Zeshang, K.D. (1982). Imputaton of mssng values when the probablty of response depends on the varable beng mputed, Journal of the Ameran Statstal Assoaton, 77, Lttle, R.J.A. (1982). Models for nonresponse n sample surveys, Journal of the Ameran Statstal Assoaton 77, Lttle, R.J.A. (1993) Pattern-mxture models for multvarate nomplete data, Journal of the Ameran Statstal Assoaton, 88, Lttle, R.J.A. and Rubn, D.B. (2002). Statstal analyss wth mssng data, New York: Wley. Rubn, D.B. (1976). Inferene and mssng data, Bometrka 63, Rubn, D.B. (1987). Multple mputaton for nonresponse n surveys, New York: Wley Qn, J., Leung, D. and Shao, J. (2002). Estmaton wth Survey data under nongnorable nonresponse or nformatve samplng, Journal of the Ameran Statstal Assoaton 97, Orhard, T., and Woodbury, M.A. (1972). A mssng nformaton prnple: theory and applaton, Proeedngs of the 6 th Berkeley Symposum on Mathematal Statsts and Probablty, 1, Pfeffermann, D., and Sverhkov, M. (1999). Parametr and sem-parametr estmaton of regresson models ftted to survey data, Sankhya 61, Pfeffermann, D., and Sverhkov, M. (2003). Fttng generalzed lnear models under nformatve probablty samplng, In: Analyss of Survey Data, eds. C. J. Sknner and R. L. Chambers. New York: John Wley & Sons. pp
6 JSM Survey Researh Methods Seton Sarndal C.E., and Swensson B. (1987). A general vew of estmaton for two fases of seleton wth applatons to two-phase samplng and nonresponse, Internatonal Statstal Revew 55, Sverhkov, M., and Pfeffermann, D. (2004). Predton of fnte populaton totals based on the sample dstrbuton, Survey Methodology 30,
The corresponding link function is the complementary log-log link The logistic model is comparable with the probit model if
SK300 and SK400 Lnk funtons for bnomal GLMs Autumn 08 We motvate the dsusson by the beetle eample GLMs for bnomal and multnomal data Covers the followng materal from hapters 5 and 6: Seton 5.6., 5.6.3,
More informationClustering through Mixture Models
lusterng through Mxture Models General referenes: Lndsay B.G. 995 Mxture models: theory geometry and applatons FS- BMS Regonal onferene Seres n Probablty and Statsts. MLahlan G.J. Basford K.E. 988 Mxture
More informationParametric fractional imputation for missing data analysis. Jae Kwang Kim Survey Working Group Seminar March 29, 2010
Parametrc fractonal mputaton for mssng data analyss Jae Kwang Km Survey Workng Group Semnar March 29, 2010 1 Outlne Introducton Proposed method Fractonal mputaton Approxmaton Varance estmaton Multple mputaton
More informationEfficient nonresponse weighting adjustment using estimated response probability
Effcent nonresponse weghtng adjustment usng estmated response probablty Jae Kwang Km Department of Appled Statstcs, Yonse Unversty, Seoul, 120-749, KOREA Key Words: Regresson estmator, Propensty score,
More informationMaximum Likelihood Estimation of Binary Dependent Variables Models: Probit and Logit. 1. General Formulation of Binary Dependent Variables Models
ECO 452 -- OE 4: Probt and Logt Models ECO 452 -- OE 4 Maxmum Lkelhood Estmaton of Bnary Dependent Varables Models: Probt and Logt hs note demonstrates how to formulate bnary dependent varables models
More informationAnalysis of Mixed Correlated Bivariate Negative Binomial and Continuous Responses
Avalable at http://pvamu.edu/aam Appl. Appl. Math. ISSN: 1932-9466 Vol. 8, Issue 2 (Deember 2013), pp. 404 415 Applatons and Appled Mathemats: An Internatonal Journal (AAM) Analyss of Mxed Correlated Bvarate
More informationSTK4900/ Lecture 4 Program. Counterfactuals and causal effects. Example (cf. practical exercise 10)
STK4900/9900 - Leture 4 Program 1. Counterfatuals and ausal effets 2. Confoundng 3. Interaton 4. More on ANOVA Setons 4.1, 4.4, 4.6 Supplementary materal on ANOVA Example (f. pratal exerse 10) How does
More informationComputation of Higher Order Moments from Two Multinomial Overdispersion Likelihood Models
Computaton of Hgher Order Moments from Two Multnomal Overdsperson Lkelhood Models BY J. T. NEWCOMER, N. K. NEERCHAL Department of Mathematcs and Statstcs, Unversty of Maryland, Baltmore County, Baltmore,
More informationMaximum Likelihood Estimation of Binary Dependent Variables Models: Probit and Logit. 1. General Formulation of Binary Dependent Variables Models
ECO 452 -- OE 4: Probt and Logt Models ECO 452 -- OE 4 Mamum Lkelhood Estmaton of Bnary Dependent Varables Models: Probt and Logt hs note demonstrates how to formulate bnary dependent varables models for
More informationCorrelation and Regression without Sums of Squares. (Kendall's Tau) Rudy A. Gideon ABSTRACT
Correlaton and Regson wthout Sums of Squa (Kendall's Tau) Rud A. Gdeon ABSTRACT Ths short pee provdes an ntroduton to the use of Kendall's τ n orrelaton and smple lnear regson. The error estmate also uses
More informationMachine Learning: and 15781, 2003 Assignment 4
ahne Learnng: 070 and 578, 003 Assgnment 4. VC Dmenson 30 onts Consder the spae of nstane X orrespondng to all ponts n the D x, plane. Gve the VC dmenson of the followng hpothess spaes. No explanaton requred.
More informationtechnische universiteit eindhoven Analysis of one product /one location inventory control models prof.dr. A.G. de Kok 1
TU/e tehnshe unverstet endhoven Analyss of one produt /one loaton nventory ontrol models prof.dr. A.G. de Kok Aknowledgements: I would lke to thank Leonard Fortun for translatng ths ourse materal nto Englsh
More informationPrediction of the reliability of genomic breeding values for crossbred performance
Vandenplas et al. Genet Sel Evol 217 49:43 DOI 1.1186/s12711-17-318-1 Genets Seleton Evoluton RESERCH RTICLE Open ess Predton of the relablty of genom breedng values for rossbred performane Jéréme Vandenplas
More informationTHE ROYAL STATISTICAL SOCIETY 2006 EXAMINATIONS SOLUTIONS HIGHER CERTIFICATE
THE ROYAL STATISTICAL SOCIETY 6 EXAMINATIONS SOLUTIONS HIGHER CERTIFICATE PAPER I STATISTICAL THEORY The Socety provdes these solutons to assst canddates preparng for the eamnatons n future years and for
More informationMATH 829: Introduction to Data Mining and Analysis The EM algorithm (part 2)
1/16 MATH 829: Introducton to Data Mnng and Analyss The EM algorthm (part 2) Domnque Gullot Departments of Mathematcal Scences Unversty of Delaware Aprl 20, 2016 Recall 2/16 We are gven ndependent observatons
More informationFAULT DETECTION AND IDENTIFICATION BASED ON FULLY-DECOUPLED PARITY EQUATION
Control 4, Unversty of Bath, UK, September 4 FAUL DEECION AND IDENIFICAION BASED ON FULLY-DECOUPLED PARIY EQUAION C. W. Chan, Hua Song, and Hong-Yue Zhang he Unversty of Hong Kong, Hong Kong, Chna, Emal:
More informationEcon107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4)
I. Classcal Assumptons Econ7 Appled Econometrcs Topc 3: Classcal Model (Studenmund, Chapter 4) We have defned OLS and studed some algebrac propertes of OLS. In ths topc we wll study statstcal propertes
More informationThe Multiple Classical Linear Regression Model (CLRM): Specification and Assumptions. 1. Introduction
ECONOMICS 5* -- NOTE (Summary) ECON 5* -- NOTE The Multple Classcal Lnear Regresson Model (CLRM): Specfcaton and Assumptons. Introducton CLRM stands for the Classcal Lnear Regresson Model. The CLRM s also
More informationLecture 3 Stat102, Spring 2007
Lecture 3 Stat0, Sprng 007 Chapter 3. 3.: Introducton to regresson analyss Lnear regresson as a descrptve technque The least-squares equatons Chapter 3.3 Samplng dstrbuton of b 0, b. Contnued n net lecture
More informationWeighted Estimating Equations with Response Propensities in Terms of Covariates Observed only for Responders
Weghted Estmatng Equatons wth Response Propenstes n Terms of Covarates Observed only for Responders Erc V. Slud, U.S. Census Bureau, CSRM Unv. of Maryland, Mathematcs Dept. NISS Mssng Data Workshop, November
More informationInterval Valued Neutrosophic Soft Topological Spaces
8 Interval Valued Neutrosoph Soft Topologal njan Mukherjee Mthun Datta Florentn Smarandah Department of Mathemats Trpura Unversty Suryamannagar gartala-7990 Trpura Indamal: anjan00_m@yahooon Department
More informationComparison of Regression Lines
STATGRAPHICS Rev. 9/13/2013 Comparson of Regresson Lnes Summary... 1 Data Input... 3 Analyss Summary... 4 Plot of Ftted Model... 6 Condtonal Sums of Squares... 6 Analyss Optons... 7 Forecasts... 8 Confdence
More informationPrimer on High-Order Moment Estimators
Prmer on Hgh-Order Moment Estmators Ton M. Whted July 2007 The Errors-n-Varables Model We wll start wth the classcal EIV for one msmeasured regressor. The general case s n Erckson and Whted Econometrc
More informationCredit Card Pricing and Impact of Adverse Selection
Credt Card Prcng and Impact of Adverse Selecton Bo Huang and Lyn C. Thomas Unversty of Southampton Contents Background Aucton model of credt card solctaton - Errors n probablty of beng Good - Errors n
More informationPsychology 282 Lecture #24 Outline Regression Diagnostics: Outliers
Psychology 282 Lecture #24 Outlne Regresson Dagnostcs: Outlers In an earler lecture we studed the statstcal assumptons underlyng the regresson model, ncludng the followng ponts: Formal statement of assumptons.
More informationBOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS. M. Krishna Reddy, B. Naveen Kumar and Y. Ramu
BOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS M. Krshna Reddy, B. Naveen Kumar and Y. Ramu Department of Statstcs, Osmana Unversty, Hyderabad -500 007, Inda. nanbyrozu@gmal.com, ramu0@gmal.com
More informationChapter 2 - The Simple Linear Regression Model S =0. e i is a random error. S β2 β. This is a minimization problem. Solution is a calculus exercise.
Chapter - The Smple Lnear Regresson Model The lnear regresson equaton s: where y + = β + β e for =,..., y and are observable varables e s a random error How can an estmaton rule be constructed for the
More informationj) = 1 (note sigma notation) ii. Continuous random variable (e.g. Normal distribution) 1. density function: f ( x) 0 and f ( x) dx = 1
Random varables Measure of central tendences and varablty (means and varances) Jont densty functons and ndependence Measures of assocaton (covarance and correlaton) Interestng result Condtonal dstrbutons
More informationECONOMICS 351*-A Mid-Term Exam -- Fall Term 2000 Page 1 of 13 pages. QUEEN'S UNIVERSITY AT KINGSTON Department of Economics
ECOOMICS 35*-A Md-Term Exam -- Fall Term 000 Page of 3 pages QUEE'S UIVERSITY AT KIGSTO Department of Economcs ECOOMICS 35* - Secton A Introductory Econometrcs Fall Term 000 MID-TERM EAM ASWERS MG Abbott
More informationChapter 11: Simple Linear Regression and Correlation
Chapter 11: Smple Lnear Regresson and Correlaton 11-1 Emprcal Models 11-2 Smple Lnear Regresson 11-3 Propertes of the Least Squares Estmators 11-4 Hypothess Test n Smple Lnear Regresson 11-4.1 Use of t-tests
More informationSee Book Chapter 11 2 nd Edition (Chapter 10 1 st Edition)
Count Data Models See Book Chapter 11 2 nd Edton (Chapter 10 1 st Edton) Count data consst of non-negatve nteger values Examples: number of drver route changes per week, the number of trp departure changes
More informationSTAT 3008 Applied Regression Analysis
STAT 3008 Appled Regresson Analyss Tutoral : Smple Lnear Regresson LAI Chun He Department of Statstcs, The Chnese Unversty of Hong Kong 1 Model Assumpton To quantfy the relatonshp between two factors,
More informationParametric fractional imputation for missing data analysis
Secton on Survey Research Methods JSM 2008 Parametrc fractonal mputaton for mssng data analyss Jae Kwang Km Wayne Fuller Abstract Under a parametrc model for mssng data, the EM algorthm s a popular tool
More informatione i is a random error
Chapter - The Smple Lnear Regresson Model The lnear regresson equaton s: where + β + β e for,..., and are observable varables e s a random error How can an estmaton rule be constructed for the unknown
More informationHere is the rationale: If X and y have a strong positive relationship to one another, then ( x x) will tend to be positive when ( y y)
Secton 1.5 Correlaton In the prevous sectons, we looked at regresson and the value r was a measurement of how much of the varaton n y can be attrbuted to the lnear relatonshp between y and x. In ths secton,
More informationController Design for Networked Control Systems in Multiple-packet Transmission with Random Delays
Appled Mehans and Materals Onlne: 03-0- ISSN: 66-748, Vols. 78-80, pp 60-604 do:0.408/www.sentf.net/amm.78-80.60 03 rans eh Publatons, Swtzerland H Controller Desgn for Networed Control Systems n Multple-paet
More informationAdmissibility Estimation of Pareto Distribution Under Entropy Loss Function Based on Progressive Type-II Censored Sample
Pure and Appled Matheats Journal 06; 5(6): 86-9 http://wwwsenepublshnggroupo/j/paj do: 0648/jpaj0605063 ISSN: 36-9790 (Prnt); ISSN: 36-98 (Onlne) Adssblty Estaton of Pareto Dstrbuton Under Entropy Loss
More informationLimited Dependent Variables
Lmted Dependent Varables. What f the left-hand sde varable s not a contnuous thng spread from mnus nfnty to plus nfnty? That s, gven a model = f (, β, ε, where a. s bounded below at zero, such as wages
More informationInterval Estimation in the Classical Normal Linear Regression Model. 1. Introduction
ECONOMICS 35* -- NOTE 7 ECON 35* -- NOTE 7 Interval Estmaton n the Classcal Normal Lnear Regresson Model Ths note outlnes the basc elements of nterval estmaton n the Classcal Normal Lnear Regresson Model
More informationLinear Regression Analysis: Terminology and Notation
ECON 35* -- Secton : Basc Concepts of Regresson Analyss (Page ) Lnear Regresson Analyss: Termnology and Notaton Consder the generc verson of the smple (two-varable) lnear regresson model. It s represented
More informationCharged Particle in a Magnetic Field
Charged Partle n a Magnet Feld Mhael Fowler 1/16/08 Introduton Classall, the fore on a harged partle n eletr and magnet felds s gven b the Lorentz fore law: v B F = q E+ Ths velot-dependent fore s qute
More informationDO NOT OPEN THE QUESTION PAPER UNTIL INSTRUCTED TO DO SO BY THE CHIEF INVIGILATOR. Introductory Econometrics 1 hour 30 minutes
25/6 Canddates Only January Examnatons 26 Student Number: Desk Number:...... DO NOT OPEN THE QUESTION PAPER UNTIL INSTRUCTED TO DO SO BY THE CHIEF INVIGILATOR Department Module Code Module Ttle Exam Duraton
More informationCS 2750 Machine Learning. Lecture 5. Density estimation. CS 2750 Machine Learning. Announcements
CS 750 Machne Learnng Lecture 5 Densty estmaton Mlos Hauskrecht mlos@cs.ptt.edu 539 Sennott Square CS 750 Machne Learnng Announcements Homework Due on Wednesday before the class Reports: hand n before
More informationChapter 4: Regression With One Regressor
Chapter 4: Regresson Wth One Regressor Copyrght 2011 Pearson Addson-Wesley. All rghts reserved. 1-1 Outlne 1. Fttng a lne to data 2. The ordnary least squares (OLS) lne/regresson 3. Measures of ft 4. Populaton
More informationSample Correlation Coef cients Based on Survey Data Under Regression Imputation
Sample Correlaton Coef cents Based on Survey ata Under Regresson Imputaton Jun Shao Hansheng Wang Regresson mputaton s commonly used to compensate for tem nonresponse when auxlary data are avalable. It
More informationFinite Mixture Models and Expectation Maximization. Most slides are from: Dr. Mario Figueiredo, Dr. Anil Jain and Dr. Rong Jin
Fnte Mxture Models and Expectaton Maxmzaton Most sldes are from: Dr. Maro Fgueredo, Dr. Anl Jan and Dr. Rong Jn Recall: The Supervsed Learnng Problem Gven a set of n samples X {(x, y )},,,n Chapter 3 of
More information4.3 Poisson Regression
of teratvely reweghted least squares regressons (the IRLS algorthm). We do wthout gvng further detals, but nstead focus on the practcal applcaton. > glm(survval~log(weght)+age, famly="bnomal", data=baby)
More informationStatistics for Economics & Business
Statstcs for Economcs & Busness Smple Lnear Regresson Learnng Objectves In ths chapter, you learn: How to use regresson analyss to predct the value of a dependent varable based on an ndependent varable
More informationComplement of an Extended Fuzzy Set
Internatonal Journal of Computer pplatons (0975 8887) Complement of an Extended Fuzzy Set Trdv Jyot Neog Researh Sholar epartment of Mathemats CMJ Unversty, Shllong, Meghalaya usmanta Kumar Sut ssstant
More informationIntroduction to Regression
Introducton to Regresson Dr Tom Ilvento Department of Food and Resource Economcs Overvew The last part of the course wll focus on Regresson Analyss Ths s one of the more powerful statstcal technques Provdes
More informationChapter 13: Multiple Regression
Chapter 13: Multple Regresson 13.1 Developng the multple-regresson Model The general model can be descrbed as: It smplfes for two ndependent varables: The sample ft parameter b 0, b 1, and b are used to
More informationPredictive Analytics : QM901.1x Prof U Dinesh Kumar, IIMB. All Rights Reserved, Indian Institute of Management Bangalore
Sesson Outlne Introducton to classfcaton problems and dscrete choce models. Introducton to Logstcs Regresson. Logstc functon and Logt functon. Maxmum Lkelhood Estmator (MLE) for estmaton of LR parameters.
More informationLinear regression. Regression Models. Chapter 11 Student Lecture Notes Regression Analysis is the
Chapter 11 Student Lecture Notes 11-1 Lnear regresson Wenl lu Dept. Health statstcs School of publc health Tanjn medcal unversty 1 Regresson Models 1. Answer What Is the Relatonshp Between the Varables?.
More informationβ0 + β1xi and want to estimate the unknown
SLR Models Estmaton Those OLS Estmates Estmators (e ante) v. estmates (e post) The Smple Lnear Regresson (SLR) Condtons -4 An Asde: The Populaton Regresson Functon B and B are Lnear Estmators (condtonal
More informationEstimation: Part 2. Chapter GREG estimation
Chapter 9 Estmaton: Part 2 9. GREG estmaton In Chapter 8, we have seen that the regresson estmator s an effcent estmator when there s a lnear relatonshp between y and x. In ths chapter, we generalzed the
More informationHidden Markov Models & The Multivariate Gaussian (10/26/04)
CS281A/Stat241A: Statstcal Learnng Theory Hdden Markov Models & The Multvarate Gaussan (10/26/04) Lecturer: Mchael I. Jordan Scrbes: Jonathan W. Hu 1 Hdden Markov Models As a bref revew, hdden Markov models
More informationThe Geometry of Logit and Probit
The Geometry of Logt and Probt Ths short note s meant as a supplement to Chapters and 3 of Spatal Models of Parlamentary Votng and the notaton and reference to fgures n the text below s to those two chapters.
More informationRockefeller College University at Albany
Rockefeller College Unverst at Alban PAD 705 Handout: Maxmum Lkelhood Estmaton Orgnal b Davd A. Wse John F. Kenned School of Government, Harvard Unverst Modfcatons b R. Karl Rethemeer Up to ths pont n
More informationSystems of Equations (SUR, GMM, and 3SLS)
Lecture otes on Advanced Econometrcs Takash Yamano Fall Semester 4 Lecture 4: Sstems of Equatons (SUR, MM, and 3SLS) Seemngl Unrelated Regresson (SUR) Model Consder a set of lnear equatons: $ + ɛ $ + ɛ
More information3.1 Expectation of Functions of Several Random Variables. )' be a k-dimensional discrete or continuous random vector, with joint PMF p (, E X E X1 E X
Statstcs 1: Probablty Theory II 37 3 EPECTATION OF SEVERAL RANDOM VARIABLES As n Probablty Theory I, the nterest n most stuatons les not on the actual dstrbuton of a random vector, but rather on a number
More informationBiostatistics 360 F&t Tests and Intervals in Regression 1
Bostatstcs 360 F&t Tests and Intervals n Regresson ORIGIN Model: Y = X + Corrected Sums of Squares: X X bar where: s the y ntercept of the regresson lne (translaton) s the slope of the regresson lne (scalng
More information8 : Learning in Fully Observed Markov Networks. 1 Why We Need to Learn Undirected Graphical Models. 2 Structural Learning for Completely Observed MRF
10-708: Probablstc Graphcal Models 10-708, Sprng 2014 8 : Learnng n Fully Observed Markov Networks Lecturer: Erc P. Xng Scrbes: Meng Song, L Zhou 1 Why We Need to Learn Undrected Graphcal Models In the
More informationAn Evaluation on Feature Selection for Text Clustering
An Evaluaton on Feature Seleton for Text Clusterng Tao Lu Department of Informaton Sene, anka Unversty, Tann 30007, P. R. Chna Shengpng Lu Department of Informaton Sene, Pekng Unversty, Beng 0087, P. R.
More informationProperties of Least Squares
Week 3 3.1 Smple Lnear Regresson Model 3. Propertes of Least Squares Estmators Y Y β 1 + β X + u weekly famly expendtures X weekly famly ncome For a gven level of x, the expected level of food expendtures
More informationChapter 15 Student Lecture Notes 15-1
Chapter 15 Student Lecture Notes 15-1 Basc Busness Statstcs (9 th Edton) Chapter 15 Multple Regresson Model Buldng 004 Prentce-Hall, Inc. Chap 15-1 Chapter Topcs The Quadratc Regresson Model Usng Transformatons
More informationPolynomial Regression Models
LINEAR REGRESSION ANALYSIS MODULE XII Lecture - 6 Polynomal Regresson Models Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Test of sgnfcance To test the sgnfcance
More informationJAB Chain. Long-tail claims development. ASTIN - September 2005 B.Verdier A. Klinger
JAB Chan Long-tal clams development ASTIN - September 2005 B.Verder A. Klnger Outlne Chan Ladder : comments A frst soluton: Munch Chan Ladder JAB Chan Chan Ladder: Comments Black lne: average pad to ncurred
More informationCHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE
CHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE Analytcal soluton s usually not possble when exctaton vares arbtrarly wth tme or f the system s nonlnear. Such problems can be solved by numercal tmesteppng
More informationA KULLBACK-LEIBLER MEASURE OF CONDITIONAL SEGREGATION
orkng Paper Departamento de Eonomía Eonom Seres 0-5 Unversdad Carlos III de Madrd June 200 Calle Madrd, 26 28903 Getafe (Span) Fax (34) 96249875 A KULLACK-LEILER MEASURE OF CONDIIONAL SEGREGAION Rardo
More informationImproving the Performance of Fading Channel Simulators Using New Parameterization Method
Internatonal Journal of Eletrons and Eletral Engneerng Vol. 4, No. 5, Otober 06 Improvng the Performane of Fadng Channel Smulators Usng New Parameterzaton Method Omar Alzoub and Moheldn Wanakh Department
More informationThe density of the time to ruin in the classical Poisson risk model
The densty of the tme to run n the lassal Posson rsk model Davd C.M. Dkson and Gordon E. Wllmot Abstrat We derve an expresson for the densty of the tme to run n the lassal rsk model by nvertng ts Laplae
More informationA New Method of Construction of Robust Second Order Rotatable Designs Using Balanced Incomplete Block Designs
Open Journal of Statsts 9-7 http://d.do.org/.6/os..5 Publshed Onlne January (http://www.srp.org/ournal/os) A ew Method of Construton of Robust Seond Order Rotatable Desgns Usng Balaned Inomplete Blok Desgns
More informationMarginal Effects in Probit Models: Interpretation and Testing. 1. Interpreting Probit Coefficients
ECON 5 -- NOE 15 Margnal Effects n Probt Models: Interpretaton and estng hs note ntroduces you to the two types of margnal effects n probt models: margnal ndex effects, and margnal probablty effects. It
More informationLOGIT ANALYSIS. A.K. VASISHT Indian Agricultural Statistics Research Institute, Library Avenue, New Delhi
LOGIT ANALYSIS A.K. VASISHT Indan Agrcultural Statstcs Research Insttute, Lbrary Avenue, New Delh-0 02 amtvassht@asr.res.n. Introducton In dummy regresson varable models, t s assumed mplctly that the dependent
More informationThe Similar Structure Method for Solving Boundary Value Problems of a Three Region Composite Bessel Equation
The Smlar Struture Method for Solvng Boundary Value Problems of a Three Regon Composte Bessel Equaton Mngmng Kong,Xaou Dong Center for Rado Admnstraton & Tehnology Development, Xhua Unversty, Chengdu 69,
More informationDepartment of Quantitative Methods & Information Systems. Time Series and Their Components QMIS 320. Chapter 6
Department of Quanttatve Methods & Informaton Systems Tme Seres and Ther Components QMIS 30 Chapter 6 Fall 00 Dr. Mohammad Zanal These sldes were modfed from ther orgnal source for educatonal purpose only.
More informationEconomics 130. Lecture 4 Simple Linear Regression Continued
Economcs 130 Lecture 4 Contnued Readngs for Week 4 Text, Chapter and 3. We contnue wth addressng our second ssue + add n how we evaluate these relatonshps: Where do we get data to do ths analyss? How do
More informationThe written Master s Examination
he wrtten Master s Eamnaton Opton Statstcs and Probablty SPRING 9 Full ponts may be obtaned for correct answers to 8 questons. Each numbered queston (whch may have several parts) s worth the same number
More informationEstimation of the Probability of Success Based on Communication History
Workng paper, presented at 7-th Valenca Meetng n Bayesan Statstcs, June 22 Estmaton of the Probablty of Success Based on Communcaton Hstory Arkady E Shemyakn Unversty of St Thomas, Sant Paul, Mnnesota,
More informationStatistical Parametric Speech Synthesis with Joint Estimation of Acoustic and Excitation Model Parameters
Statstal Parametr Speeh Synthess wth Jont Estmaton of Aoust and Extaton odel Parameters Rannery aa, Hega en, J F Gales Toshba Researh Europe Ltd, Cambrdge Researh Laboratory, Cambrdge, UK {rannerymaa,hegazen,mfg}@rltoshbaouk
More informationStatistics for Business and Economics
Statstcs for Busness and Economcs Chapter 11 Smple Regresson Copyrght 010 Pearson Educaton, Inc. Publshng as Prentce Hall Ch. 11-1 11.1 Overvew of Lnear Models n An equaton can be ft to show the best lnear
More informationA note on regression estimation with unknown population size
Statstcs Publcatons Statstcs 6-016 A note on regresson estmaton wth unknown populaton sze Mchael A. Hdroglou Statstcs Canada Jae Kwang Km Iowa State Unversty jkm@astate.edu Chrstan Olver Nambeu Statstcs
More informationLaboratory 3: Method of Least Squares
Laboratory 3: Method of Least Squares Introducton Consder the graph of expermental data n Fgure 1. In ths experment x s the ndependent varable and y the dependent varable. Clearly they are correlated wth
More informationCALCULUS CLASSROOM CAPSULES
CALCULUS CLASSROOM CAPSULES SESSION S86 Dr. Sham Alfred Rartan Valley Communty College salfred@rartanval.edu 38th AMATYC Annual Conference Jacksonvlle, Florda November 8-, 202 2 Calculus Classroom Capsules
More informationGravity Drainage Prior to Cake Filtration
1 Gravty Dranage Pror to ake Fltraton Sott A. Wells and Gregory K. Savage Department of vl Engneerng Portland State Unversty Portland, Oregon 97207-0751 Voe (503) 725-4276 Fax (503) 725-4298 ttp://www.e.pdx.edu/~wellss
More informationUNIVERSITY OF TORONTO Faculty of Arts and Science. December 2005 Examinations STA437H1F/STA1005HF. Duration - 3 hours
UNIVERSITY OF TORONTO Faculty of Arts and Scence December 005 Examnatons STA47HF/STA005HF Duraton - hours AIDS ALLOWED: (to be suppled by the student) Non-programmable calculator One handwrtten 8.5'' x
More informationChapter 14 Simple Linear Regression
Chapter 4 Smple Lnear Regresson Chapter 4 - Smple Lnear Regresson Manageral decsons often are based on the relatonshp between two or more varables. Regresson analss can be used to develop an equaton showng
More informationT E C O L O T E R E S E A R C H, I N C.
T E C O L O T E R E S E A R C H, I N C. B rdg n g En g neern g a nd Econo mcs S nce 1973 THE MINIMUM-UNBIASED-PERCENTAGE ERROR (MUPE) METHOD IN CER DEVELOPMENT Thrd Jont Annual ISPA/SCEA Internatonal Conference
More informationsince [1-( 0+ 1x1i+ 2x2 i)] [ 0+ 1x1i+ assumed to be a reasonable approximation
Econ 388 R. Butler 204 revsons Lecture 4 Dummy Dependent Varables I. Lnear Probablty Model: the Regresson model wth a dummy varables as the dependent varable assumpton, mplcaton regular multple regresson
More informationOn an Extension of Stochastic Approximation EM Algorithm for Incomplete Data Problems. Vahid Tadayon 1
On an Extenson of Stochastc Approxmaton EM Algorthm for Incomplete Data Problems Vahd Tadayon Abstract: The Stochastc Approxmaton EM (SAEM algorthm, a varant stochastc approxmaton of EM, s a versatle tool
More informationDurban Watson for Testing the Lack-of-Fit of Polynomial Regression Models without Replications
Durban Watson for Testng the Lack-of-Ft of Polynomal Regresson Models wthout Replcatons Ruba A. Alyaf, Maha A. Omar, Abdullah A. Al-Shha ralyaf@ksu.edu.sa, maomar@ksu.edu.sa, aalshha@ksu.edu.sa Department
More informationChapter 9: Statistical Inference and the Relationship between Two Variables
Chapter 9: Statstcal Inference and the Relatonshp between Two Varables Key Words The Regresson Model The Sample Regresson Equaton The Pearson Correlaton Coeffcent Learnng Outcomes After studyng ths chapter,
More informationChapter 20 Duration Analysis
Chapter 20 Duraton Analyss Duraton: tme elapsed untl a certan event occurs (weeks unemployed, months spent on welfare). Survval analyss: duraton of nterest s survval tme of a subject, begn n an ntal state
More information4 Analysis of Variance (ANOVA) 5 ANOVA. 5.1 Introduction. 5.2 Fixed Effects ANOVA
4 Analyss of Varance (ANOVA) 5 ANOVA 51 Introducton ANOVA ANOVA s a way to estmate and test the means of multple populatons We wll start wth one-way ANOVA If the populatons ncluded n the study are selected
More informationInner Product. Euclidean Space. Orthonormal Basis. Orthogonal
Inner Product Defnton 1 () A Eucldean space s a fnte-dmensonal vector space over the reals R, wth an nner product,. Defnton 2 (Inner Product) An nner product, on a real vector space X s a symmetrc, blnear,
More informationStatistics for Managers Using Microsoft Excel/SPSS Chapter 13 The Simple Linear Regression Model and Correlation
Statstcs for Managers Usng Mcrosoft Excel/SPSS Chapter 13 The Smple Lnear Regresson Model and Correlaton 1999 Prentce-Hall, Inc. Chap. 13-1 Chapter Topcs Types of Regresson Models Determnng the Smple Lnear
More information8/25/17. Data Modeling. Data Modeling. Data Modeling. Patrice Koehl Department of Biological Sciences National University of Singapore
8/5/17 Data Modelng Patrce Koehl Department of Bologcal Scences atonal Unversty of Sngapore http://www.cs.ucdavs.edu/~koehl/teachng/bl59 koehl@cs.ucdavs.edu Data Modelng Ø Data Modelng: least squares Ø
More informationNon-Mixture Cure Model for Interval Censored Data: Simulation Study ABSTRACT
Malaysan Journal of Mathematcal Scences 8(S): 37-44 (2014) Specal Issue: Internatonal Conference on Mathematcal Scences and Statstcs 2013 (ICMSS2013) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES Journal
More informationBivariate Analysis of Number of Services to Conception and Days Open in Norwegian Red Using a Censored Threshold-Linear Model
Bvarate Analyss of Number of Serves to Conepton and Days Open n Norwegan Red Usng a Censored Threshold-Lnear Model Y. M. Chang, I. M. Andersen-Ranberg, B. Herngstad,3, D. Ganola,3, and G. Klemetsdal 3
More informationREPLICATION VARIANCE ESTIMATION UNDER TWO-PHASE SAMPLING IN THE PRESENCE OF NON-RESPONSE
STATISTICA, anno LXXIV, n. 3, 2014 REPLICATION VARIANCE ESTIMATION UNDER TWO-PHASE SAMPLING IN THE PRESENCE OF NON-RESPONSE Muqaddas Javed 1 Natonal College of Busness Admnstraton and Economcs, Lahore,
More information