On the choice of test statistic for conditional moment inequalities

DOI10.1016/J.JECONOM.2017.10.007MaRDI QIDQ1706486zbMATH OpenOpenAlexFDO

Authors Timothy B. Armstrong

Publication date 22 March 2018

Published in Journal of Econometrics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1410.4718

zbMATH Keywords

asymptotic approximationCramer-von Mises (CvM) style testKolmogorov-Smirnov (KS) test

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20)

Abstract: This paper derives asymptotic approximations to the power of Cramer-von Mises (CvM) style tests for inference on a finite dimensional parameter defined by conditional moment inequalities in the case where the parameter is set identified. Combined with power results for Kolmogorov-Smirnov (KS) tests, these results can be used to choose the optimal test statistic, weighting function and, for tests based on kernel estimates, kernel bandwidth. The results show that, in the setting considered here, KS tests are preferred to CvM tests, and that a truncated variance weighting is preferred to bounded weightings.

Recommendations

• Distribution-free tests of conditional moment inequalities
• Testing moment inequalities: selection versus recentering
• Adaptive tests of conditional moment inequalities
• On the Behavior of Conditional Moment Tests in the Presence of Unconsidered Local Alternatives
• New test statistics for hypothesis testing of parameters in conditional moment restriction models
• OPTIMALITY FOR THE INTEGRATED CONDITIONAL MOMENT TEST
• On the Conditional Distribution of Goodness-of-Fit Tests
• Asymptotically optimal tests for conditional distributions

Cites work

• Adaptive tests of conditional moment inequalities
• Asymptotically exact inference in conditional moment inequality~models
• Asymptotically exact nonparametric hypothesis testing in sup-norm and at a fixed point
• Confidence Intervals for Partially Identified Parameters
• Consistent estimation with many moment inequalities
• Consistent model specification tests
• Convergence of stochastic processes
• Identification and inference in ascending auctions with correlated private values
• Inference based on conditional moment inequalities
• Inference on Regressions with Interval Data on a Regressor or Outcome
• Inference on endogenously censored regression models using conditional moment inequalities
• Intersection bounds: estimation and inference
• Local linear regression smoothers and their minimax efficiencies
• Multiscale adaptive inference on conditional moment inequalities
• Multiscale testing of qualitative hypotheses
• Nonparametric goodness-of-fit testing under Gaussian models
• On nonparametric tests of positivity/monotonicity/convexity
• Optimal global rates of convergence for nonparametric regression
• Semiparametric Estimation of the Intercept of a Sample Selection Model
• Testing functional inequalities
• Weighted KS statistics for inference on conditional moment inequalities

Cited in

(7)

• Model selection tests for moment inequality models
• Stochastically weighted average conditional moment tests of functional form
• scientific article; zbMATH DE number 4133303 (Why is no real title available?)
• OPTIMALITY FOR THE INTEGRATED CONDITIONAL MOMENT TEST
• Adaptive tests of conditional moment inequalities
• Asymptotic distribution of test statistics in the analysis of moment structures under inequality constraints
• Inference in ordered response games with complete information

This page was built for publication: On the choice of test statistic for conditional moment inequalities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1706486)