This preview shows page 1. Sign up to view the full content.
Unformatted text preview: imilar way as in logistic
regression.
o −e
ri = i√ i , i = 1, 2, . . . , K
ei
where oi is the observed value and ei is the expected
frequency.
ei computed as nπi
ˆ
Compared with oi = yi .
Similar to ideas in a oneway contingency tables
Chisquare statistic: applies if each category has a
unique set of covariates
K
2 ri2 X=
i =1 UNM Odds ratio
Suppose we have a covariate X , where X = 0 factor is
absent and X = 1 factor is present.
Since
πj
log
= β0j + β1j X ; j = 2, . . . , K
π1
If πjp (πja ) is the response probability associated to factor
present (absent).
For X = 0,
πj
log
= β0j
π1
and for X = 1,
log πj
π1 = β0j + β1j
UNM Odds ratio for exposure for response j
ORj...
View
Full
Document
This note was uploaded on 01/27/2014 for the course STAT 574 taught by Professor Gabrielhuerta during the Fall '13 term at New Mexico.
 Fall '13
 GabrielHuerta

Click to edit the document details