New Goodness-of-Fit Diagnostics for Conditional Discrete Response Models

34 Pages Posted: 6 Nov 2013

See all articles by Igor Kheifets

Igor Kheifets

New Economic School (NES)

Carlos Velasco

Universidad Carlos III de Madrid - Department of Economics

Date Written: November 5, 2013

Abstract

This paper proposes new specification tests for conditional models with discrete responses. In particular, we can test the static and dynamic ordered choice model specifications, which is key to apply efficient maximum likelihood methods, to obtain consistent estimates of partial effects and to get appropriate predictions of the probability of future events. The traditional approach is based on probability integral transforms of a jittered discrete data which leads to continuous uniform iid series under the true conditional distribution. We investigate in this paper an alternative transformation based only on original discrete data. We show analytically and in simulations that our approach dominates the traditional approach in terms of power. We apply the new tests to models of the monetary policy conducted by the Federal Reserve.

Keywords: Specification tests, Count data, Dynamic discrete choice models, Conditional probability integral transform

JEL Classification: C12, C22, C52

Suggested Citation

Kheifets, Igor and Velasco, Carlos, New Goodness-of-Fit Diagnostics for Conditional Discrete Response Models (November 5, 2013). Cowles Foundation Discussion Paper No. 1924. Available at SSRN: https://ssrn.com/abstract=2350152 or http://dx.doi.org/10.2139/ssrn.2350152

Igor Kheifets (Contact Author)

New Economic School (NES) ( email )

100A Novaya Street
Moscow, Skolkovo 143026
Russia

Carlos Velasco

Universidad Carlos III de Madrid - Department of Economics ( email )

Calle Madrid 126
Getafe, 28903
Spain
+34-91 6249646 (Phone)
+34-91 6249875 (Fax)

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
46
Abstract Views
325
PlumX Metrics