Thread View: sci.math.stat
1 messages
1 total messages
Started by Andrew Cuddon, Civil Postg.
Wed, 15 Apr 1992 05:02
ANOVAs for Linear Regression - Q1
Author: Andrew Cuddon, Civil Postg.
Date: Wed, 15 Apr 1992 05:02
Date: Wed, 15 Apr 1992 05:02
25 lines
1593 bytes
1593 bytes
Regards to all, I would appreciate some feedback on a lack of understanding. I have a situation where I would like to determine if a constant term is neccessary for my simple linear regression model. I have become rather confused over how an analysis of variance table is calculated when a CONSTANT term is not included in a linear regression. My model produces R2 value of 0.7 with the constant term being significantly different from zero at the 1% level. In the interests of simplifying the model I re-ran the regression without the constant term and noted an increase in R2 to 0.9. This was fine but I also noted that the REGRESSION SUM OF SQUARES in the ANOVA table increased from 14.6 up to 375.4. This was because the TOTAL SUM OF SQUARES increased from 20.4 up to 381.5. If the two models are from the same data set, how can the TSS be different in each case? I believe this may be something to do with correcting for the mean but I don't really understand what is going on here. Thanks in advance, ============================= Andrew Cuddon CUDDON@ENG2.ENG.MONASH.EDU.AU =============================
Thread Navigation
This is a paginated view of messages in the thread with full content displayed inline.
Messages are displayed in chronological order, with the original post highlighted in green.
Use pagination controls to navigate through all messages in large threads.
Back to All Threads