RDSURVIV for c-hat

questions concerning analysis/theory using software from the Patuxent Software Archive

RDSURVIV for c-hat

Postby fanny » Wed Nov 24, 2004 10:42 am

I have to use Mark, but before i have to llok if my general model have a good GOF( goodness of fit). I have use program RDSURVIV and my model have a GOF=1.000. I would like now to calculate the variance inflation factors, c-hat, for my general model. To calculate the c-hat i need the chi-square and the degrees freedom. How can i find them in RDSURVIV?
thank you for the help!!!
Posts: 11
Joined: Tue Nov 23, 2004 7:16 am

Postby jhines » Wed Nov 24, 2004 1:56 pm

If the GOF of your model is 1.0, then the GOF of any more general model is 1.0 also. The chi-square and df values in RDSURVIV appear after the listing of observed and expected values. There is an unpooled chi-square value (G Total), and a pooled value (Pearsons chi-square). With sparse data, the pooled value may not appear.

Jim Hines
Posts: 502
Joined: Fri May 16, 2003 9:24 am
Location: Laurel, MD, USA

Postby fanny » Fri Nov 26, 2004 4:11 am

Thank you for the help!
I have not realy understood wich one a have to use for calculate the c-hat.
Is correclty like this?
17,146/14= c-hat

G Total (Degrees of freedom = 106) 56.596
Pr(Larger Chi-square) = 0.9999
With pooling, Degrees of freedom = 14 Pearson Chi-square = 17.146
Pr(Larger Chi-square) = 0.2485

what's the meaning of "with pooling" ? i havent found it in the rdsurvive manual...
Posts: 11
Joined: Tue Nov 23, 2004 7:16 am

Return to analysis help

Who is online

Users browsing this forum: No registered users and 1 guest