Misspecification Testing in a Class of Conditional Distributional Models

Rothe, Christoph; Wied, Dominik

doi:10.1080/01621459.2012.736903

Cited by 64 publications

(74 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to our test, their test has a slower rate of convergence, cannot distinguish Pittman local alternatives and depends on bandwidth selection procedures, which might be impractical. Our test is close in spirit to the empirical process based goodness‐of‐fit tests of H 0 by Andrews (), Rothe and Wied () and Delgado and Stute (); however, their results require i.i.d. data, while our test not only can be applied to time series, but also is able to detect misspecification in dynamic structure.…”

Section: Introductionsupporting

confidence: 77%

Specification tests for nonlinear dynamic models

Kheifets

2015

The Econometrics Journal

View full text Add to dashboard Cite

SummaryWe propose a new adequacy test and a graphical evaluation tool for nonlinear dynamic models. The proposed techniques can be applied in any set-up where parametric conditional distribution of the data is specified and, in particular, to models involving conditional volatility, conditional higher moments, conditional quantiles, asymmetry, Value at Risk models, duration models, diffusion models, etc. Compared to other tests, the new test properly controls the nonlinear dynamic behaviour in conditional distribution and does not rely on smoothing techniques that require a choice of several tuning parameters. The test is based on a new kind of multivariate empirical process of contemporaneous and lagged probability integral transforms. We establish weak convergence of the process under parameter uncertainty and local alternatives. We justify a parametric bootstrap approximation that accounts for parameter estimation effects often ignored in practice. Monte Carlo experiments show that the test has good finite-sample size and power properties. Using the new test and graphical tools, we check the adequacy of various popular heteroscedastic models for stock exchange index data.

show abstract

Section: Introductionsupporting

confidence: 77%

Specification tests for nonlinear dynamic models

Kheifets

2015

The Econometrics Journal

View full text Add to dashboard Cite

show abstract

“…Given our focus on the bottom of the wage distribution, this aspect is rather critical. Although the two approaches are theoretically equivalent (Koenker et al, 2013), empirical evidence suggests that DR generally provides a better fit to wage distribution data than quantile regression (Rothe and Wied, 2013;Van Kerm et al, 2016).…”

Section: Distributional Analysesmentioning

confidence: 99%

Minimum Wages and the Gender GAP in Pay: New Evidence from the United Kingdom and Ireland

Bargain

Doorley

Kerm

2018

Review of Income and Wealth

View full text Add to dashboard Cite

Women are disproportionately in low‐paid work compared to men so, in the absence of rationing effects on their employment, they should benefit the most from minimum wage policies. This study examines the change in the gender wage gap around the introduction of minimum wages in Ireland and the United Kingdom (U.K.). Using survey data for the two countries, we develop a decomposition of the change in the gender differences in wage distributions around the date of introduction of minimum wages. We separate out “price” effects attributed to minimum wages from “employment composition” effects. A significant reduction of the gender gap at low wages is observed after the introduction of the minimum wage in Ireland, while there is hardly any change in the U.K. Counterfactual simulations show that the difference between countries may be attributed to gender differences in non‐compliance with the minimum wage legislation in the U.K.

show abstract

“…The limit distribution and bootstrap consistency results in Corollaries 5.3 and 5.4 are new. They have already been applied in several studies (Chernozhukov, Fernández-Val, and Kowalski (2011), Rothe (2012), and Rothe and Wied (2012)). Note that unlike Theorem 5.2 and Corollary 5.4, Corollary 5.3 does not rely on compactness of the region Y j X j .…”

Section: Inference Theory For Counterfactual Estimators Based On Distmentioning

confidence: 99%

“…Rothe and Wied (2012) proposed new specification tests for conditional distribution models. Applying their tests to a similar data set, they rejected the quantile regression model, but not the distribution regression model.…”

mentioning

confidence: 99%

Inference on Counterfactual Distributions

2013

Econometrica

424

View full text Add to dashboard Cite

Counterfactual distributions are important ingredients for policy analysis and decomposition analysis in empirical economics. In this article we develop modeling and inference tools for counterfactual distributions based on regression methods. The counterfactual scenarios that we consider consist of ceteris paribus changes in either the distribution of covariates related to the outcome of interest or the conditional distribution of the outcome given covariates. For either of these scenarios we derive joint functional central limit theorems and bootstrap validity results for regression-based estimators of the status quo and counterfactual outcome distributions. These results allow us to construct simultaneous confidence sets for function-valued effects of the counterfactual changes, including the effects on the entire distribution and quantile functions of the outcome as well as on related functionals. These confidence sets can be used to test functional hypotheses such as no-effect, positive effect, or stochastic dominance. Our theory applies to general counterfactual changes and covers the main regression methods including classical , quantile, duration, and distribution regressions. We illustrate the results with an empirical application to wage decompositions using data for the United States. As a part of developing the main results, we introduce distribution regression as a comprehensive and flexible tool for modeling and estimating the entire conditional distribution. We show that distribution regression encompasses the Cox duration regression and represents a useful alternative to quantile regression. We establish functional central limit theorems and bootstrap validity results for the empirical distribution regression process and various related functionals. of the counterfactual operator, exchangeable bootstrap, unconditional quantile and distribution effects

show abstract

Misspecification Testing in a Class of Conditional Distributional Models

Cited by 64 publications

References 33 publications

Specification tests for nonlinear dynamic models

Specification tests for nonlinear dynamic models

Minimum Wages and the Gender GAP in Pay: New Evidence from the United Kingdom and Ireland

Inference on Counterfactual Distributions

Contact Info

Product

Resources

About