Downloads
We propose a framework for estimation and inference when the model may be misspecified. We rely on a local asymptotic approach where the degree of misspecification is indexed by the sample size. We construct estimators whose mean squared error is minimax in a neighborhood of the reference model, based on simple one-step adjustments. In addition, we provide confidence intervals that contain the true parameter under local misspecification. To interpret the degree of misspecification, we map it to the local power of a specification test of the reference model. Our approach allows for systematic sensitivity analysis when the parameter of interest may be partially or irregularly identified. As illustrations, we study two binary choice models: a cross-sectional model where the error distribution is misspecified, and a dynamic panel data model where the number of time periods is small and the distribution of individual effects is misspecified.
Authors
Research Associate University College London and University of Oxford
Martin is an IFS Research Associate, a Fellow of the Nuffield College and a Professor in the Department of Economics at the University of Oxford.
Professor of Economics University of Chicago
Working Paper details
- DOI
- 10.1920/wp.cem.2020.3720
- Publisher
- The IFS
Suggested citation
Bonhomme, S and Weidner, M. (2020). Minimizing Sensitivity to Model Misspecification. London: The IFS. Available at: https://ifs.org.uk/publications/minimizing-sensitivity-model-misspecification-0 (accessed: 20 April 2024).
More from IFS
Understand this issue
Gender norms, violence and adolescent girls’ trajectories: Evidence from India
24 October 2022
Raising revenue from closing inheritance tax loopholes
18 April 2024
Sure Start achieved its aims, then we threw it away
15 April 2024
Policy analysis
IFS Deputy Director Carl Emmerson appointed to the UK Statistics Authority Methodological Assurance Review Panel
14 April 2023
ABC of SV: Limited Information Likelihood Inference in Stochastic Volatility Jump-Diffusion Models
We develop novel methods for estimation and filtering of continuous-time models with stochastic volatility and jumps using so-called Approximate Bayesian Compu- tation which build likelihoods based on limited information.
12 August 2014
Is there really an NHS productivity crisis?
17 November 2023
Academic research
Sample composition and representativeness on Understanding Society
2 February 2024
Understanding Society: minimising selection biases in data collection using mobile apps
2 February 2024
Robust analysis of short panels
8 January 2024