A regression test of semiparametric index model specifications
This paper presents a straightforward regression test of parametric and semiparametric index models against more general semiparametric and nonparametric alternative models. The test is based on the regression coefficient of the restricted model residuals on the fitted values of the more general mod...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Working Paper |
| Published: |
MIT Center for Energy and Environmental Policy Research
2009
|
| Online Access: | http://hdl.handle.net/1721.1/50189 |
| _version_ | 1826206091770331136 |
|---|---|
| author | Rodriguez, Diego Stoker, Thomas M. |
| author2 | Massachusetts Institute of Technology. Center for Energy and Environmental Policy Research. |
| author_facet | Massachusetts Institute of Technology. Center for Energy and Environmental Policy Research. Rodriguez, Diego Stoker, Thomas M. |
| author_sort | Rodriguez, Diego |
| collection | MIT |
| description | This paper presents a straightforward regression test of parametric and semiparametric index models against more general semiparametric and nonparametric alternative models. The test is based on the regression coefficient of the restricted model residuals on the fitted values of the more general model. A goodness-of-fit interpretation is shown for the regression coefficient, and the test is based on the squared "t-statistic" of the coefficient estimate, where the variance of the coefficient has been adjusted for the use of nonparametric estimators. An asymptotic theory is given for the situation where kernel estimators are used to estimate unknown regression functions, and the variance adjustment terms are given for this case. The methods are applied to the empirical problem of characterizing environmental effects on housing prices in the Boston Housing data, where a partial index model is found to be preferable to a standard log-linear equation, yet not rejected against general nonparametric regression. Various issues in the asymptotic theory and other features of the test are discussed. |
| first_indexed | 2024-09-23T13:23:57Z |
| format | Working Paper |
| id | mit-1721.1/50189 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T13:23:57Z |
| publishDate | 2009 |
| publisher | MIT Center for Energy and Environmental Policy Research |
| record_format | dspace |
| spelling | mit-1721.1/501892019-04-12T23:31:07Z A regression test of semiparametric index model specifications Rodriguez, Diego Stoker, Thomas M. Massachusetts Institute of Technology. Center for Energy and Environmental Policy Research. This paper presents a straightforward regression test of parametric and semiparametric index models against more general semiparametric and nonparametric alternative models. The test is based on the regression coefficient of the restricted model residuals on the fitted values of the more general model. A goodness-of-fit interpretation is shown for the regression coefficient, and the test is based on the squared "t-statistic" of the coefficient estimate, where the variance of the coefficient has been adjusted for the use of nonparametric estimators. An asymptotic theory is given for the situation where kernel estimators are used to estimate unknown regression functions, and the variance adjustment terms are given for this case. The methods are applied to the empirical problem of characterizing environmental effects on housing prices in the Boston Housing data, where a partial index model is found to be preferable to a standard log-linear equation, yet not rejected against general nonparametric regression. Various issues in the asymptotic theory and other features of the test are discussed. Funded by a grant from the MIT Center for Energy and Environmental Policy Research. 2009-12-15T23:58:27Z 2009-12-15T23:58:27Z 1993 Working Paper 93011 http://hdl.handle.net/1721.1/50189 35719553 MIT-CEEPR (Series) ; 93-011WP. 50 p application/pdf MIT Center for Energy and Environmental Policy Research |
| spellingShingle | Rodriguez, Diego Stoker, Thomas M. A regression test of semiparametric index model specifications |
| title | A regression test of semiparametric index model specifications |
| title_full | A regression test of semiparametric index model specifications |
| title_fullStr | A regression test of semiparametric index model specifications |
| title_full_unstemmed | A regression test of semiparametric index model specifications |
| title_short | A regression test of semiparametric index model specifications |
| title_sort | regression test of semiparametric index model specifications |
| url | http://hdl.handle.net/1721.1/50189 |
| work_keys_str_mv | AT rodriguezdiego aregressiontestofsemiparametricindexmodelspecifications AT stokerthomasm aregressiontestofsemiparametricindexmodelspecifications AT rodriguezdiego regressiontestofsemiparametricindexmodelspecifications AT stokerthomasm regressiontestofsemiparametricindexmodelspecifications |