How does p-value mean for R-square PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Soo Owen posted on Monday, October 01, 2018 - 11:43 am
So, I ran a multivariate regression analysis with 7 continuous variables and dummy predictors. I've got some significant coefficients but I don't know how to interpret the pvalues of R-squares. Below is part of my output. While two dummy variables significantly predict the Y1ACADEV, all predictors explain only 7% of Y1ACADEV. But the p-value for the R-square is not significant (0.118). What does it mean?

Y1ACADEV ON
FIELD -0.025 0.110 -0.223 0.824
PEERSOCIAL -0.314 0.144 -2.184 0.029
BOTH 0.108 0.046 2.380 0.017

R-SQUARE

Observed Two-Tailed
Variable Estimate S.E. Est./S.E. P-Value

Y1ACADEV 0.065 0.042 1.564 0.118
 Bengt O. Muthen posted on Tuesday, October 02, 2018 - 5:41 am
R-square typically has a non-symmetric sampling distribution so you want to use bootstrapping to get non-symmetric CIs and evaluate significance that way instead of p-values which assume symmetric.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: