Timeline for Test for bias in the residuals of regressions
Current License: CC BY-SA 4.0
20 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 13, 2020 at 11:48 | answer | added | Florian Hartig | timeline score: 1 | |
| Sep 2, 2020 at 21:28 | history | edited | Naiky | CC BY-SA 4.0 |
deleted 7 characters in body
|
| Aug 31, 2020 at 20:26 | history | edited | Naiky | CC BY-SA 4.0 |
deleted 20 characters in body
|
| Aug 31, 2020 at 17:00 | history | edited | Naiky | CC BY-SA 4.0 |
added 4 characters in body
|
| Aug 31, 2020 at 16:14 | history | edited | Naiky | CC BY-SA 4.0 |
added 56 characters in body
|
| Aug 28, 2020 at 14:12 | history | edited | Naiky | CC BY-SA 4.0 |
added 32 characters in body
|
| Aug 27, 2020 at 23:03 | history | edited | Naiky | CC BY-SA 4.0 |
added 48 characters in body
|
| Aug 27, 2020 at 21:46 | history | edited | Naiky | CC BY-SA 4.0 |
added 1 character in body
|
| Aug 27, 2020 at 21:34 | history | edited | Naiky | CC BY-SA 4.0 |
added 12 characters in body
|
| Aug 27, 2020 at 21:28 | history | edited | Naiky | CC BY-SA 4.0 |
deleted 133 characters in body; edited title
|
| Aug 27, 2020 at 20:57 | comment | added | user54285 | My understanding of bias is this is error in the parameters (the slopes in regression). Which is different then whether the error term has time patterns in it I believe (but again I might not understand this correctly). AC is usually seen not to cause bias, but only impact the Standard Errors (there are some exceptions in some time series approaches that use lags, there autocorrelation can cause bias in the parameters). | |
| Aug 27, 2020 at 20:55 | comment | added | user54285 | serial correlation includes MA patterns I believe while I think autocorrelation is only AR patterns - although I could be wrong at that. There are many tests for white noise - which is the absence of AR and MA effects. In ARIMA Ljung Box tests for this. In regression I think Breusch-Godfrey is preferred because their are doubts about of the validity of Ljung Box. This link from this board is useful in that light. stats.stackexchange.com/questions/148004/… | |
| Aug 27, 2020 at 15:03 | comment | added | Naiky | "not white noise" will have biased residuals if the model is linear and the data is not, right? If i tried to fit a straight line to data 3000000230, the residuals of the fit would be biased. | |
| Aug 27, 2020 at 15:01 | comment | added | Naiky | I had not heard of "serial correlation" but it seems that it is the same as autocorrelation. How would you use that to approach the question? | |
| Aug 27, 2020 at 14:59 | comment | added | Naiky | Hi thanks for replying! by white noise i mean "random fluctuations around a mean value". What are the tests for that? | |
| Aug 26, 2020 at 23:53 | comment | added | user54285 | what does 'mostly white noise" mean.:) There are tests if a model is white noise or not. The issue here btw is serial correlation not bias as I understand that term. I don't think that something that is not white noise is biased. | |
| Aug 26, 2020 at 21:00 | history | edited | Naiky | CC BY-SA 4.0 |
added 534 characters in body
|
| Aug 26, 2020 at 20:50 | history | edited | Naiky | CC BY-SA 4.0 |
added 62 characters in body
|
| Aug 26, 2020 at 20:22 | review | First posts | |||
| Aug 27, 2020 at 2:57 | |||||
| Aug 26, 2020 at 20:21 | history | asked | Naiky | CC BY-SA 4.0 |