|
Logistic regression model for BPD as a function of Birth Weight |
|
Study of Low Birth Weight Infants |
|
The GENMOD Procedure |
|
Model Information |
|
|
Data Set |
WORK.LOWBWT |
|
Distribution |
Binomial |
|
Link Function |
Logit |
|
Dependent Variable |
bpd |
|
Observations Used |
223 |
|
Response Profile |
||
|
Ordered |
bpd |
Total |
|
1 |
1 |
76 |
|
2 |
0 |
147 |
|
PROC GENMOD is modeling the probability that bpd='1'. |
|
Criteria For Assessing Goodness Of Fit |
|||
|
Criterion |
DF |
Value |
Value/DF |
|
Deviance |
221 |
223.7206 |
1.0123 |
|
Scaled Deviance |
221 |
223.7206 |
1.0123 |
|
Pearson Chi-Square |
221 |
251.6647 |
1.1388 |
|
Scaled Pearson X2 |
221 |
251.6647 |
1.1388 |
|
Log Likelihood |
|
-111.8603 |
|
|
Algorithm converged. |
|
Analysis Of Parameter Estimates |
|||||||
|
Parameter |
DF |
Estimate |
Standard Error |
Wald 95% Confidence Limits |
Chi-Square |
Pr > ChiSq |
|
|
Intercept |
1 |
4.0343 |
0.6958 |
2.6706 |
5.3980 |
33.62 |
<.0001 |
|
weight |
1 |
-0.4229 |
0.0641 |
-0.5485 |
-0.2973 |
43.55 |
<.0001 |
|
Scale |
0 |
1.0000 |
0.0000 |
1.0000 |
1.0000 |
|
|
|