On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples
The asymptotic distribution of the linear instrumental variables (IV) estimator with empirically selected ridge regression penalty is characterized. The regularization tuning parameter is selected by splitting the observed data into training and test samples and becomes an estimated parameter that j...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Econometrics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2225-1146/8/4/39 |
| _version_ | 1827705045126217728 |
|---|---|
| author | Nandana Sengupta Fallaw Sowell |
| author_facet | Nandana Sengupta Fallaw Sowell |
| author_sort | Nandana Sengupta |
| collection | DOAJ |
| description | The asymptotic distribution of the linear instrumental variables (IV) estimator with empirically selected ridge regression penalty is characterized. The regularization tuning parameter is selected by splitting the observed data into training and test samples and becomes an estimated parameter that jointly converges with the parameters of interest. The asymptotic distribution is a nonstandard mixture distribution. Monte Carlo simulations show the asymptotic distribution captures the characteristics of the sampling distributions and when this ridge estimator performs better than two-stage least squares. An empirical application on returns to education data is presented. |
| first_indexed | 2024-03-10T15:54:51Z |
| format | Article |
| id | doaj.art-51513f44ef64448f8ef2468a09845124 |
| institution | Directory Open Access Journal |
| issn | 2225-1146 |
| language | English |
| last_indexed | 2024-03-10T15:54:51Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Econometrics |
| spelling | doaj.art-51513f44ef64448f8ef2468a098451242023-11-20T15:44:21ZengMDPI AGEconometrics2225-11462020-10-01843910.3390/econometrics8040039On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test SamplesNandana Sengupta0Fallaw Sowell1School of Public Policy, Indian Institute of Technology Delhi, Delhi 110016, IndiaTepper School of Business, Carnegie Mellon University, Pittsburgh, PA 15213, USAThe asymptotic distribution of the linear instrumental variables (IV) estimator with empirically selected ridge regression penalty is characterized. The regularization tuning parameter is selected by splitting the observed data into training and test samples and becomes an estimated parameter that jointly converges with the parameters of interest. The asymptotic distribution is a nonstandard mixture distribution. Monte Carlo simulations show the asymptotic distribution captures the characteristics of the sampling distributions and when this ridge estimator performs better than two-stage least squares. An empirical application on returns to education data is presented.https://www.mdpi.com/2225-1146/8/4/39ridge regressioninstrumental variablesregularizationtraining and test samplesgeneralized method of moments framework |
| spellingShingle | Nandana Sengupta Fallaw Sowell On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples Econometrics ridge regression instrumental variables regularization training and test samples generalized method of moments framework |
| title | On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples |
| title_full | On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples |
| title_fullStr | On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples |
| title_full_unstemmed | On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples |
| title_short | On the Asymptotic Distribution of Ridge Regression Estimators Using Training and Test Samples |
| title_sort | on the asymptotic distribution of ridge regression estimators using training and test samples |
| topic | ridge regression instrumental variables regularization training and test samples generalized method of moments framework |
| url | https://www.mdpi.com/2225-1146/8/4/39 |
| work_keys_str_mv | AT nandanasengupta ontheasymptoticdistributionofridgeregressionestimatorsusingtrainingandtestsamples AT fallawsowell ontheasymptoticdistributionofridgeregressionestimatorsusingtrainingandtestsamples |