کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
5057750 | 1476606 | 2017 | 4 صفحه PDF | دانلود رایگان |
- Recent models use both the factors and idiosyncratic components estimated from a big dataset.
- We derive the distribution of the OLS estimates of these model parameters.
- HAC standard errors must be adjusted to allow for the factor and idiosyncratic estimation error.
- This is in contrast to existing results in the literature where estimation error vanishes when TâNâ0.
This paper shows that HAC standard errors must be adjusted when constructing confidence intervals in regressions involving both the factors and idiosyncratic components estimated from a big dataset. This result is in contrast to the seminal result of Bai and Ng (2006) where the assumption that TâNâ0 is sufficient to eliminate the effect of estimation error, where T and N are the time-series and cross-sectional dimensions. Simulations show vast improvements in the coverage rates of the adjusted confidence intervals over the unadjusted ones.
Journal: Economics Letters - Volume 157, August 2017, Pages 71-74