Local Sensitivity and Diagnostic Tests

In this paper we confront sensitivity analysis with diagnostic testing.Every model is misspecified, but a model is useful if the parameters of interest (the focus) are not sensitive to small perturbations in the underlying assumptions. The study of the e ect of these violations on the focus is called sensitivity analysis.Diagnostic testing, on the other hand, attempts to find out whether a nuisance parameter is large or small.Both aspects are important, but traditional applied econometrics tends to use only diagnostics and forget about sensitivity analysis.We develop a theory of sensitivity in a maximum likelihood framework, propose a sensitivity test, give conditions under which the diagnostic and sensitivity tests are asymptotically independent, and demonstrate with three core examples that this independence is the rule rather than the exception, thus underlying the importance of sensitivity analysis.

[1]  J. Doob.  Stochastic processes , 1953 .

[2]  J. A. Díaz-García,et al.  SENSITIVITY ANALYSIS IN LINEAR REGRESSION , 2022 .

[3]  N. Kiefer,et al.  LOCAL ASYMPTOTIC SPECIFICATION ERROR ANALYSIS , 1984 .

[4]  Jan R. Magnus,et al.  Consistent maximum-likelihood estimation with dependent observations: The general (non-normal) case and the normal case , 1986 .

[5]  R. Cook.  Influential Observations in Linear Regression , 1979 .

[6]  Karim M. Abadir,et al.  Notation in Econometrics: A Proposal for a Standard , 2002 .

[7]  Jan R. Magnus,et al.  The sensitivity of OLS when the variance matrix is (partially) unknown , 1999 .

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

[9]  Leslie Godfrey.  Misspecification Tests in Econometrics: The Lagrange Multiplier Principle and Other Approaches , 1988 .

[10]  Whitney K. Newey,et al.  Higher Order Properties of Gmm and Generalized Empirical Likelihood Estimators , 2003 .

[11]  Dietrich von Rosen,et al.  Local influence assessment in the growth curve model with unstructured covariance , 1997 .

[12]  Shuangzhe Liu,et al.  On local influence for elliptical linear models , 2000 .

[13]  Paul A. Ruud,et al.  An Introduction to Classical Econometric Theory , 2000 .

[14]  Heleno Bolfarine,et al.  Local influence in elliptical linear regression models , 1997 .

[15]  Anil K. Bera,et al.  A test for normality of observations and regression residuals , 1987 .

[16]  C. Manski.  MAXIMUM SCORE ESTIMATION OF THE STOCHASTIC UTILITY MODEL OF CHOICE , 1975 .

[17]  Anil K. Bera,et al.  Efficient tests for normality, homoscedasticity and serial independence of regression residuals , 1980 .

[18]  P. Bickel.  Efficient and Adaptive Estimation for Semiparametric Models , 1993 .

[19]  Lei Shi,et al.  Local influence in ridge regression , 1999 .

[20]  Jack P. C. Kleijnen,et al.  Sensitivity analysis and related analyses: A review of some statistical techniques , 1997 .

[21]  R. Cook.  Assessment of Local Influence , 1986 .

[22]  James G. MacKinnon,et al.  Implicit Alternatives and the Local Power of Test Statistics , 1987 .

[23]  W. Fung,et al.  Assessment of local influence in multivariate regression analysis , 1997 .

[24]  D. Pollard,et al.  Cube Root Asymptotics , 1990 .

[25]  R. Fisher.  The Advanced Theory of Statistics , 1943, Nature.

[26]  John M. Wilson,et al.  Advances in Sensitivity Analysis and Parametric Programming , 1998, J. Oper. Res. Soc..

[27]  Wolfgang Polasek,et al.  Regression Diagnostics for General Linear Regression Models , 1984 .

[28]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

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

[30]  Edward E. Leamer,et al.  Global Sensitivity Results for Generalized Least Squares Estimates , 1984 .

[31]  Bernd Schwarzmann,et al.  A connection between local-influence analysis and residual diagnostics , 1991 .

[32]  J. Magnus,et al.  ON THE FIRST–ORDER EFFICIENCY AND ASYMPTOTIC NORMALITY OF MAXIMUM LIKELIHOOD ESTIMATORS OBTAINED FROM DEPENDENT OBSERVATIONS , 1986 .

[33]  Jan R. Magnus,et al.  On the sensitivity of the usual t- and F-tests to covariance misspecification , 2000 .

[34]  Joseph A. C. Delaney.  Sensitivity analysis , 2018, The African Continental Free Trade Area: Economic and Distributional Effects.

[35]  Shuangzhe Liu,et al.  Local influence in multivariate elliptical linear regression models , 2002 .

[36]  J. Hausman.  Specification tests in econometrics , 1978 .

[37]  S. Chatterjee.  Sensitivity analysis in linear regression , 1988 .

[38]  G Molenberghs,et al.  Sensitivity Analysis for Nonrandom Dropout: A Local Influence Approach , 2001, Biometrics.

[39]  James Durbin,et al.  Errors in variables , 1954 .

[40]  K. Do,et al.  Efficient and Adaptive Estimation for Semiparametric Models. , 1994 .

[41]  S. Weisberg,et al.  Residuals and Influence in Regression , 1982 .

[42]  Jan F. Kiviet,et al.  Testing strategies for model specification , 1986 .

[43]  J. Magnus.  Maximum likelihood estimation of the GLS model with unknown parameters in the disturbance covariance matrix , 1978 .

[44]  H. Theil.  Specification Errors and the Estimation of Economic Relationships , 1957 .

[45]  Ramon C. Littell,et al.  Local Influence of Predictors in Multiple Linear Regression , 2003, Technometrics.

[46]  S. Weisberg,et al.  Residuals and Influence in Regression , 1982 .

[47]  D. Andrews,et al.  Hypothesis testing with a restricted parameter space , 1998 .

[48]  A. Holly.  Advances in Econometrics: Specification tests: an overview , 1987 .