Timeline for What are common statistical sins?
Current License: CC BY-SA 2.5
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 17, 2010 at 16:29 | history | edited | John D. Cook | CC BY-SA 2.5 |
added 13 characters in body
|
| Nov 16, 2010 at 22:18 | comment | added | Dikran Marsupial | Yes (I was using biased in a colloquial rather than a statistical sense to mean the model was systematically biased towards observations in high-variance regions of the feature space - mea culpa!) - it would be more accurate to say that the higher variance means there is an increased chance of getting a poor model using a finite dataset. That seems a reasonable answer to your question. I don't really view unbiasedness as being that much of a comfort - what is important is that the model should give good predictions on the data I actually have and often the variance is more important. | |
| Nov 16, 2010 at 12:39 | comment | added | Rob Hyndman | No, it is unbiased, but the variance is larger than if you used a more efficient method for the reasons you explain. Yes, the prediction intervals are wrong. | |
| Nov 16, 2010 at 9:31 | comment | added | Dikran Marsupial | If the data are heteroscedastic you can end up with very innacurate out of sample predictions because the regression model will try too hard to minimise the error on samples in areas with high variance and not hard enough on samples from areas of low variance. This means you can end up with a very badly biased model. It also means that the error bars on the predictions will be wrong. | |
| Nov 16, 2010 at 3:18 | comment | added | Rob Hyndman | What's inappropriate about least squares estimation when the data are non-normal or heteroskedastic? It is not fully efficient, but it is still unbiased and consistent. | |
| Nov 16, 2010 at 2:53 | history | edited | russellpierce | CC BY-SA 2.5 |
added 89 characters in body
|
| S Nov 15, 2010 at 21:39 | history | answered | jebyrnes | CC BY-SA 2.5 | |
| S Nov 15, 2010 at 21:39 | history | made wiki | Post Made Community Wiki |