Loading...
Please wait, while we are loading the content...
Similar Documents
A Unified Asymptotic Distribution Theory for Parametric and Non-Parametric Least Squares
| Content Provider | Semantic Scholar |
|---|---|
| Author | Hansen, Bruce E. |
| Copyright Year | 2015 |
| Abstract | This paper presents simple and general conditions for asymptotic normality of least squares estimators allowing for regressors vectors which expand with the sample size. Our assumptions include series and sieve estimation of regression functions, and any context where the regressor set increases with the sample size. The conditions are quite general, including as special cases the assumptions commonly used for both parametric and nonparametric sieve least squares. Our assumptions allow the regressors to be unbounded, and do not bound the conditional variances. Our assumptions allow the number of regressors K to be either fixed or increasing with sample size. Our conditions bound the allowable rate of growth of K as a function of the number of finite moments, showing that there is an inherent trade-off between the number of moments and the allowable number of regressors. ∗Research supported by the National Science Foundation. I thank Victor Chernozhukov and Xiaohong Chen for helpful and detailed comments. †Department of Economics, 1180 Observatory Drive, University of Wisconsin, Madison, WI 53706. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://econ.ohio-state.edu/seminar/papers/160328_Hansen.pdf |
| Alternate Webpage(s) | https://www.ssc.wisc.edu/~bhansen/preliminary/rnormal4.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
