Multivariate Regression with Monotone Missing Observation of the Dependent Variables

V.M. Raats, B.B. van der Genugten, J.J.A. Moors

Research output: Working paperDiscussion paperOther research output

247 Downloads (Pure)

Abstract

Multivariate regression is discussed, where the observations of the dependent variables are (monotone) missing completely at random; the explanatory variables are assumed to be completely observed.We discuss OLS-, GLS- and a certain form of E(stimated) GLS-estimation.It turns out that (E)GLS-estimation uses the preceding dependent variables in a well-structured way.In case of normality, ML-estimation coincides with (E)GLS-estimation.We include (sets of) MANOVA-tables enabling us to perform exact tests on the coecients based on a (new) generalized Wilks' distribution.Only the very special case of the constant as sole explanatory variable has been treated in the literature so far: our model incorporates this missing data problem.
Original languageEnglish
Place of PublicationTilburg
PublisherEconometrics
Number of pages32
Volume2002-63
Publication statusPublished - 2002

Publication series

NameCentER Discussion Paper
Volume2002-63

Fingerprint

Missing Observations
Multivariate Regression
Monotone
Dependent
Missing Completely at Random
Multivariate Analysis of Variance
Exact Test
Missing Data
Normality
Tables

Keywords

  • testing
  • sampling
  • least squares
  • maximum likelihood
  • multivariate regression

Cite this

Raats, V. M., van der Genugten, B. B., & Moors, J. J. A. (2002). Multivariate Regression with Monotone Missing Observation of the Dependent Variables. (CentER Discussion Paper; Vol. 2002-63). Tilburg: Econometrics.
Raats, V.M. ; van der Genugten, B.B. ; Moors, J.J.A. / Multivariate Regression with Monotone Missing Observation of the Dependent Variables. Tilburg : Econometrics, 2002. (CentER Discussion Paper).
@techreport{7b771e123bc3492e8cd171c49f07ad07,
title = "Multivariate Regression with Monotone Missing Observation of the Dependent Variables",
abstract = "Multivariate regression is discussed, where the observations of the dependent variables are (monotone) missing completely at random; the explanatory variables are assumed to be completely observed.We discuss OLS-, GLS- and a certain form of E(stimated) GLS-estimation.It turns out that (E)GLS-estimation uses the preceding dependent variables in a well-structured way.In case of normality, ML-estimation coincides with (E)GLS-estimation.We include (sets of) MANOVA-tables enabling us to perform exact tests on the coecients based on a (new) generalized Wilks' distribution.Only the very special case of the constant as sole explanatory variable has been treated in the literature so far: our model incorporates this missing data problem.",
keywords = "testing, sampling, least squares, maximum likelihood, multivariate regression",
author = "V.M. Raats and {van der Genugten}, B.B. and J.J.A. Moors",
note = "Pagination: 32",
year = "2002",
language = "English",
volume = "2002-63",
series = "CentER Discussion Paper",
publisher = "Econometrics",
type = "WorkingPaper",
institution = "Econometrics",

}

Raats, VM, van der Genugten, BB & Moors, JJA 2002 'Multivariate Regression with Monotone Missing Observation of the Dependent Variables' CentER Discussion Paper, vol. 2002-63, Econometrics, Tilburg.

Multivariate Regression with Monotone Missing Observation of the Dependent Variables. / Raats, V.M.; van der Genugten, B.B.; Moors, J.J.A.

Tilburg : Econometrics, 2002. (CentER Discussion Paper; Vol. 2002-63).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Multivariate Regression with Monotone Missing Observation of the Dependent Variables

AU - Raats, V.M.

AU - van der Genugten, B.B.

AU - Moors, J.J.A.

N1 - Pagination: 32

PY - 2002

Y1 - 2002

N2 - Multivariate regression is discussed, where the observations of the dependent variables are (monotone) missing completely at random; the explanatory variables are assumed to be completely observed.We discuss OLS-, GLS- and a certain form of E(stimated) GLS-estimation.It turns out that (E)GLS-estimation uses the preceding dependent variables in a well-structured way.In case of normality, ML-estimation coincides with (E)GLS-estimation.We include (sets of) MANOVA-tables enabling us to perform exact tests on the coecients based on a (new) generalized Wilks' distribution.Only the very special case of the constant as sole explanatory variable has been treated in the literature so far: our model incorporates this missing data problem.

AB - Multivariate regression is discussed, where the observations of the dependent variables are (monotone) missing completely at random; the explanatory variables are assumed to be completely observed.We discuss OLS-, GLS- and a certain form of E(stimated) GLS-estimation.It turns out that (E)GLS-estimation uses the preceding dependent variables in a well-structured way.In case of normality, ML-estimation coincides with (E)GLS-estimation.We include (sets of) MANOVA-tables enabling us to perform exact tests on the coecients based on a (new) generalized Wilks' distribution.Only the very special case of the constant as sole explanatory variable has been treated in the literature so far: our model incorporates this missing data problem.

KW - testing

KW - sampling

KW - least squares

KW - maximum likelihood

KW - multivariate regression

M3 - Discussion paper

VL - 2002-63

T3 - CentER Discussion Paper

BT - Multivariate Regression with Monotone Missing Observation of the Dependent Variables

PB - Econometrics

CY - Tilburg

ER -

Raats VM, van der Genugten BB, Moors JJA. Multivariate Regression with Monotone Missing Observation of the Dependent Variables. Tilburg: Econometrics. 2002. (CentER Discussion Paper).