Log in
RegisterRobust Regression? [General Statistics]
posted by Helmut 
– Vienna, Austria, 2009-11-26 15:32 (6049 d 09:32 ago) – Posting: # 4395
Views: 4,440
Dear Naresh!
ad 1) Hopefully a lot of observations (for 6 linear regressors >18).
ad 2) Fine. That's called multiple regression.
ad 4) From your last sentence I guess you think that (some) assumptions of parametric regression do no hold. Have you tried the more common approaches: transformations or weighting? If this doesn't help, you may opt for robust regression. You may try to minimize not the sum of squared residuals (like in OLS), but the sum of absolute residuals, or the median of residuals, or...
I don't see a need for Monte Carlo here.
ad 1) Hopefully a lot of observations (for 6 linear regressors >18).
ad 2) Fine. That's called multiple regression.
ad 4) From your last sentence I guess you think that (some) assumptions of parametric regression do no hold. Have you tried the more common approaches: transformations or weighting? If this doesn't help, you may opt for robust regression. You may try to minimize not the sum of squared residuals (like in OLS), but the sum of absolute residuals, or the median of residuals, or...
I don't see a need for Monte Carlo here.
—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png)
Helmut Schütz
![[image]](https://static.bebac.at/img/CC by.png)
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Complete thread:
- Monte carlo simulation in Regression model yes_naresh 2009-11-26 10:45
![[Mix]](https://static.bebac.at/img/mix.png "open in Mix view")
- Robust Regression?Helmut 2009-11-26 14:32
- Monte carlo simulation in Regression model ElMaestro 2009-11-27 20:01
- robust regression martin 2009-11-28 09:41
Ing. Helmut Schütz