Timeline for HAC standard errors or robust standard errors?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 11, 2017 at 10:35 | comment | added | Achim Zeileis | Good point. I'm not sure whether the HAC-based inference in this scenario will really be better than the standard inference. My gut feeling is that it won't be. Would be worth trying in a simulation, I guess. | |
| Jan 11, 2017 at 6:36 | comment | added | Richard Hardy | Achim, I am not 100% sure about the case of modelling for inference. If we want high power of our tests, we want to avoid high variance of estimators, so leaving some small patterns in the data unaccounted four sounds like a reasonable solution. I am thinking of Galit Smhueli "To Explain or To Predict" and Rob J. Hyndman's blog post on the same topic where BIC is recommended for model selection in explanatory modelling. | |
| Jan 10, 2017 at 23:53 | comment | added | Achim Zeileis | @mugen The term robust standard errors is sometimes used as an umbrella term for HC, HAC, and other sandwich standard errors. However, more often than not robust standard errors means the HC0 standard errors, originally developed by Eicker and Huber, and later popularized by White. Not least due to the "robust" option in Stata (that computes these basic HC0 standard errors) this latter interpretation is quite widely used. | |
| Jan 10, 2017 at 23:48 | comment | added | Achim Zeileis | @RichardHardy The question is whether you want a model for predictions or for inference about certain parameters. In the former case, model selection based on some performance measure (AIC, BIC, cross-validation, etc.) will be preferable but then you won't care about significances. In the latter case you will want to capture autocorrelation in the "right" way even if some other model performs slightly better in predictions. | |
| Jan 10, 2017 at 2:26 | comment | added | Richard Hardy | Achim, what about deliberately choosing a model that has some remaining autocorrelation (because accounting for it fully raises AIC or BIC) and then using autocorrelation-robust standard errors for inference? It does makes sense to me, but I am not entirely sure. | |
| Jan 9, 2017 at 23:07 | comment | added | mugen | Both the question and your answer mention HAC and robust standard errors in simultaneous. Can the term be used interchangeably or does your answer apply to both? Could you please disambiguate technical jargon? Thanks! | |
| Jan 9, 2017 at 21:54 | history | answered | Achim Zeileis | CC BY-SA 3.0 |