A test for bivariate normality with applications in microeconometric models

In this paper, we propose a test for bivariate normality in imperfectly observed models, based on the information matrix test for censored models with bootstrap critical values. In order to evaluate its properties, we run a comprehensive Monte Carlo experiment, in which we use the bivariate probit model and Heckman sample selection model as examples. We find that, while asymptotic critical values can be seriously misleading, the use of bootstrap critical values results in a test that has excellent size and power properties even in small samples. Since this procedure is relatively inexpensive from a computational viewpoint and is easy to generalise to models with arbitrary censoring schemes, we recommend it as an important and valuable testing tool.

[1]  Andrew Chesher,et al.  The information matrix test: Simplified calculation via a score test interpretation , 1983 .

[2]  N. Wermuth,et al.  Tests of Linearity, Multivariate Normality and the Adequacy of Linear Scores , 1994 .

[3]  Tony Lancaster,et al.  THE COVARIANCE MATRIX OF THE INFORMATION MATRIX TEST , 1984 .

[4]  Whitney K. Newey,et al.  Two-Step Series Estimation of Sample Selection Models , 2009 .

[5]  A. Gallant,et al.  Semi-nonparametric Maximum Likelihood Estimation , 1987 .

[6]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

[7]  L. Shenton,et al.  Omnibus test contours for departures from normality based on √b1 and b2 , 1975 .

[8]  David R. Cox,et al.  Testing multivariate normality , 1978 .

[9]  F. Vella,et al.  A Monte Carlo investigation of the sampling behavior of conditional moment tests in Tobit and Probit models , 1999 .

[10]  Adrian Pagan,et al.  Diagnostic Tests for Models Based on Individual Data: A Survey. , 1989 .

[11]  Chris D. Orme,et al.  The small-sample performance of the information-matrix test , 1990 .

[12]  J. MacKinnon,et al.  The power of bootstrap and asymptotic tests , 2006 .

[13]  W. V. D. Ven,et al.  The demand for deductibles in private health insurance: A probit model with sample selection , 1981 .

[14]  Alastair R. Hall,et al.  The Information Matrix Test for the Linear Model , 1987 .

[15]  Whitney K. Newey,et al.  Nonparametric Estimation of Sample Selection Models , 2003 .

[16]  James G. MacKinnon,et al.  THE SIZE DISTORTION OF BOOTSTRAP TESTS , 1999, Econometric Theory.

[17]  Lung-fei Lee,et al.  Tests for the Bivariate Normal Distribution in Econometric Models with Selectivity , 1984 .

[18]  Anil K. Bera,et al.  Testing the Normality Assumption in Limited Dependent Variable Models , 1984 .

[19]  K. Mardia.  Measures of multivariate skewness and kurtosis with applications , 1970 .

[20]  George Tauchen.  Diagnostic testing and evaluation of maximum likelihood models , 1985 .

[21]  Mario Menegatti.  A new interpretation for the precautionary saving motive: a note , 2007 .

[22]  Maria F. O. Martins,et al.  Parametric and semiparametric estimation of sample selection models: an empirical application to the female labour force in Portugal , 2001 .

[23]  James G. MacKinnon,et al.  Graphical Methods for Investigating the Size and Power of Hypothesis Tests , 1998 .

[24]  J. Horowitz.  Bootstrap-based critical values for the information matrix test , 1994 .

[25]  Ruud H Koning,et al.  Testing the Normality Assumption in the Sample Selection Model With an Application to Travel Demand , 2000 .

[26]  Whitney K. Newey,et al.  Maximum Likelihood Specification Testing and Conditional Moment Tests , 1985 .

[27]  Andrew Chesher,et al.  Residual analysis in the grouped and censored normal linear model , 1987 .

[28]  Anthony Murphy,et al.  Score Tests of Normality in Bivariate Probit Models , 2007 .

[29]  J. G. Cragg.  Some Statistical Models for Limited Dependent Variables with Application to the Demand for Durable Goods , 1971 .

[30]  Larry W. Taylor,et al.  The size bias of White's information matrix test , 1987 .

[31]  Smith.  Some Tests for Misspecification in Bivariate Limited Dependent Variables Models , 1985 .

[32]  P. Robinson,et al.  ON THE ASYMPTOTIC PROPERTIES OF ESTIMATORS OF MODELS CONTAINING LIMITED DEPENDENT VARIABLES , 1982 .

[33]  J. MacKinnon,et al.  Bootstrap tests: how many bootstraps? , 2000 .

[34]  James G. MacKinnon,et al.  A New Form of the Information Matrix Test , 1992 .

[35]  Róbert F. Veszteg,et al.  Parametric and Semiparametric Estimation of Sample Selection Models: an Empirical Application to the Female Labour Force in Portugal Lena Veiga Acknowledges the Financial Support from Grant Sponsors: Program Praxis Xxi (fct) and Fep , 2005 .

[36]  J. Doornik,et al.  An Omnibus Test for Univariate and Multivariate Normality , 2008 .

[37]  J. MacKinnon,et al.  Bootstrap Testing in Nonlinear Models , 1999 .

[38]  Joel L. Horowitz,et al.  Testing a Parametric Model Against a Semiparametric Alternative , 1994, Econometric Theory.

[39]  Badi H. Baltagi,et al.  A companion to theoretical econometrics , 2003 .

[40]  James G. MacKinnon,et al.  Improving the Reliability of Bootstrap Tests , 2000 .

[41]  Andrew Chesher,et al.  Asymptotic expansions of the informa-tion matrix test statistic , 1991 .

[42]  J. Heckman.  Shadow prices, market wages, and labor supply , 1974 .

[43]  Richard J. Smith.  On the Use of Distributional Mis-specification Checks in Limited Dependent Variable Models , 1989 .

[44]  L. Shenton,et al.  A Bivariate Model for the Distribution of √b1 and b2 , 1977 .

[45]  Richard J. Smith.  Testing the normality assumption in multivariate simultaneous limited dependent variable models , 1987 .

[46]  Qi Li,et al.  Nonparametric Econometrics: Theory and Practice , 2006 .

[47]  Gabriel Montes-Rojas.  Robust Misspecification Tests for the Heckman's Two-Step Estimator , 2011 .