컨텐츠 시작
학술대회/행사
초록검색
| 제출번호(No.) | 0254 |
|---|---|
| 분류(Section) | Special Session |
| 분과(Session) | Structured nonparametric and high-dimensional statistics (SS-15) |
| 영문제목 (Title(Eng.)) |
Adaptive discrete smoothing for (high-dimensional and nonlinear) panel data |
| 저자(Author(s)) |
Martin Spindler1, Xi Chen2, Victor Chernozhukov3, Ye Luo4 University of Hamburg1, NYU2, MIT3, University of Hong Kong4 |
| 초록본문(Abstract) | In this paper we develop a data-driven smoothing technique for non-linear panel data models. We allow for individual specific (non-linear) functions and estimation with econometric or machine learning methods by using weighted observations from other individuals. The weights are determined by a data-driven way and depend on the similarity between the corresponding functions and are measured based on initial estimates. The key feature of such a procedure is that it clusters individuals based on the distance / similarity between them, estimated in a first stage. Our estimation method can be combined with various statistical estimation procedures, in particular modern machine learning methods which are in particular fruitful in the high-dimensional case and with complex, heterogeneous data. The methods can also be applied for estimation of Random Coefficient models and for estimation of nonparametric functions with many categorical variables (\textquotedblleft cells\textquotedblright). The theoretical properties of the proposed estimator are derived which improve on many classical methods. We conduct a simulation study which shows that the prediction can be greatly improved by using our estimator. Finally, we analyze a big data set from didichuxing.com, a leading company in transportation industry, to analyze and predict the gap between supply and demand based on a large set of covariates. Our estimator clearly performs much better in out-of-sample prediction compared to existing non-linear panel data estimators. |
| 분류기호 (MSC number(s)) |
62Hxx |
| 키워드(Keyword(s)) | nonparametric econometrics, nonlinear panel data, discrete smoothing, incidental parameter problem, clustering |
| 강연 형태 (Language of Session (Talk)) |
English |