Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/241928 
Year of Publication: 
2020
Series/Report no.: 
cemmap working paper No. CWP53/20
Publisher: 
Centre for Microdata Methods and Practice (cemmap), London
Abstract: 
Conditional distribution functions are important statistical objects for the analysis of a wide class of problems in econometrics and statistics. We propose flexible Gaussian representations for conditional distribution functions and give a concave likelihood formulation for their global estimation. We obtain solutions that satisfy the monotonicity property of conditional distribution functions, including under general misspecification and in finite samples. A Lasso-type penalized version of the corresponding maximum likelihood estimator is given that expands the scope of our estimation analysis to models with sparsity. Inference and estimation results for conditional distribution, quantile and density functions implied by our representations are provided and illustrated with an empirical example and numerical simulations.
Subjects: 
Conditional distribution estimation
conditional quantiles
Gaussian representations
maximum likelihood
misspecification
monotonicity
convex programming
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.