+ Reply to Thread
Results 1 to 2 of 2

Thread: Longitudinal Regression Issue

  1. #1
    Points: 2,677, Level: 31
    Level completed: 52%, Points required for next Level: 73

    Thanked 0 Times in 0 Posts

    Longitudinal Regression Issue

    Hi there, I am conducting a hierarchical longitudinal regression over an 18 month time span. I have main effects, quadratic terms and interactions for the same variables measured in T1 and T2 (T1 variables entered as controls). The specific issue is that the beta weights associated with the significant variables at both T1 and T2 are changing signs. For example X1*X2 = .101 at T1 and then X1*X2 = -.090 at T2.

    Could this be due to multicollinearity? If so is there any way I can correct this? Any insight would be appreciated!!!

  2. #2
    TS Contributor
    Points: 8,362, Level: 61
    Level completed: 71%, Points required for next Level: 88

    Crete, Greece
    Thanked 35 Times in 34 Posts

    i do not know hierarchiacl longitudinal regression but i know repeated measures anova if you have any more questions. As for this now, one way to deal with collinearity is to standardize all your variables.

+ Reply to Thread


Similar Threads

  1. Puzzling Regression issue.
    By Solaris in forum Regression Analysis
    Replies: 1
    Last Post: 08-27-2010, 01:49 PM
  2. Endogeneity in longitudinal regression analysis
    By jaluoma in forum Regression Analysis
    Replies: 0
    Last Post: 08-11-2010, 09:55 AM
  3. Practical regression issue - correlated regressors
    By statguy_33 in forum Statistics
    Replies: 2
    Last Post: 05-11-2010, 06:53 PM
  4. multiple comparison issue in linear regression
    By nahh in forum Regression Analysis
    Replies: 0
    Last Post: 11-05-2008, 04:41 PM
  5. Significance Issue in Regression
    By Mikica in forum Regression Analysis
    Replies: 9
    Last Post: 08-29-2007, 03:17 PM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats