> library(foreign)
> ds <- read.dta("c:/bpd.dta")
> attach(ds)
> weight <- weight/100
> model1 <- glm(bpd ~ weight, family=binomial(link="logit"))
> summary(model1)
Call:
glm(formula = bpd ~ weight, family = binomial(link = "logit"))
Deviance Residuals:
Min 1Q Median 3Q Max
-1.9916 -0.7993 -0.4096 0.9242 2.4802
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 4.03429 0.69571 5.799 6.68e-09 ***
weight -0.42291 0.06408 -6.600 4.11e-11 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 286.14 on 222 degrees of freedom
Residual deviance: 223.72 on 221 degrees of freedom
AIC: 227.72
Number of Fisher Scoring iterations: 4
Logistic Regression Model for BPD as a function of Birth Weight , Gestational Age, and Toxemia
> model2 <- glm(bpd ~ gestage + toxemia + weight,
+ family=binomial(link="logit"))
> summary(model2)
Call:
glm(formula = bpd ~ gestage + toxemia + weight, family = binomial(link = "logit"))
Deviance Residuals:
Min 1Q Median 3Q Max
-1.8400 -0.7029 -0.3352 0.7261 2.9902
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 13.93608 2.98255 4.673 2.98e-06 ***
gestage -0.38854 0.11489 -3.382 0.00072 ***
toxemia -1.34379 0.60750 -2.212 0.02697 *
weight -0.26436 0.08123 -3.254 0.00114 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 286.14 on 222 degrees of freedom
Residual deviance: 203.71 on 219 degrees of freedom
AIC: 211.71
Number of Fisher Scoring iterations: 5