Can the effects of using all suitable lags of an instrument comparable to that of an additional basic instrument in instrumental variable regression analysis of heteroskedastic linear models?
It is found that using all suitable lags of one instrument can increase the efficiency of finite sample IV estimator tremendously.The former is about 10% more efficient than the latter.The efficiency gains by using all suitable lags of one instrument is approximately about 1.1 times of what can be...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2010
|
| Subjects: | |
| Online Access: | https://repo.uum.edu.my/id/eprint/5083/1/Yip.pdf |
| Summary: | It is found that using all suitable lags of one instrument can increase the efficiency of finite sample IV estimator tremendously.The former is about 10% more efficient than the latter.The efficiency gains by using all suitable lags of one
instrument is approximately about 1.1 times of what can be obtained by the inclusion of a similarly powerful instrument. |
|---|