Logistic and Discriminant
#########################################
######################################### Logistic Regression
######################################### by South African Hearth Disease Data
#install.packages("ElemStatLearn")
library(ElemStatLearn)
data(SAheart)
# 전처리 과정
heart <-SAheart[,c(1:3,5,7:10)]
# 로지스틱 분석
heartfit<-glm( chd~.,data=heart, family = binomial)
summary(heartfit)##
## Call:
## glm(formula = chd ~ ., family = binomial, data = heart)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.7517 -0.8378 -0.4552 0.9292 2.4434
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.1295997 0.9641558 -4.283 1.84e-05 ***
## sbp 0.0057607 0.0056326 1.023 0.30643
## tobacco 0.0795256 0.0262150 3.034 0.00242 **
## ldl 0.1847793 0.0574115 3.219 0.00129 **
## famhistPresent 0.9391855 0.2248691 4.177 2.96e-05 ***
## obesity -0.0345434 0.0291053 -1.187 0.23529
## alcohol 0.0006065 0.0044550 0.136 0.89171
## age 0.0425412 0.0101749 4.181 2.90e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 596.11 on 461 degrees of freedom
## Residual deviance: 483.17 on 454 degrees of freedom
## AIC: 499.17
##
## Number of Fisher Scoring iterations: 4#########################################
######################################### Discriminant Analysis
######################################### by South African Hearth Disease Data
# 판별분석 모형식
require(MASS)## Loading required package: MASSdisc.fit <- lda(factor(chd) ~., data = heart)
# 분류표
pred_chd <- predict(disc.fit, newdata = heart[,1:7])
result <- table(heart$chd, pred_chd$class)
# 정분류율
accuracy <- (result[1, 1] + result[2, 2]) / sum(result) * 100