Modeling quantile regression coefficients functions permits describing thecoefficients of a quantile regression model as parametric functions of the order of thequantile. This approach has numerous advantages over standard quantile regression,in which different quantiles are estimated one at the time: it facilitates estimation andinference, improves the interpretation of the results, and is statistically efficient. Onthe other hand, it poses new challenges in terms of model selection. We describe apenalized approach that can be used to identify a parsimonious model that can fitthe data well. We describe the method, and analyze the dataset that motivated thepresent paper. The proposed approach is implemented in the qrcmNP package in R.
|Titolo della pubblicazione ospite||Book of Short Papers SIS 2018|
|Numero di pagine||6|
|Stato di pubblicazione||Published - 2018|