前言
本文使用隨機(jī)生成的數(shù)據(jù)集進(jìn)行批量單因素logistic回歸分析，并提取P<0.05的變量以供后續(xù)多因素logistic回歸。后續(xù)會繼續(xù)分享一些R語言分析代碼，歡迎大家一起討論學(xué)習(xí)。
構(gòu)建數(shù)據(jù)，Y為因變量，其他為自變量
#0.構(gòu)建數(shù)據(jù)，Y為因變量，其他為自變量
set.seed(1234)#設(shè)置隨機(jī)種子，保證生成數(shù)據(jù)一致
log_data<- data.frame(Y = sample(0:1, 600, replace = T),
sex=sample(1:2, 600, replace = T),
edu=sample(1:4, 600, replace = T),
BMI=rnorm(600, mean = 22, sd = 3),
白蛋白=rnorm(600, mean = 35, sd = 6),
隨機(jī)血糖=rnorm(600, mean = 4.75, sd = 1.2))
summary(log_data)
Y sex edu BMI 白蛋白 隨機(jī)血糖
Min. :0.0000 Min. :1.000 Min. :1.00 Min. :13.21 Min. :16.27 Min. :1.036
1st Qu.:0.0000 1st Qu.:1.000 1st Qu.:2.00 1st Qu.:20.18 1st Qu.:30.94 1st Qu.:3.956
Median :1.0000 Median :1.000 Median :3.00 Median :22.17 Median :34.78 Median :4.816
Mean :0.5017 Mean :1.467 Mean :2.57 Mean :22.05 Mean :35.04 Mean :4.778
3rd Qu.:1.0000 3rd Qu.:2.000 3rd Qu.:4.00 3rd Qu.:23.98 3rd Qu.:39.19 3rd Qu.:5.579
Max. :1.0000 Max. :2.000 Max. :4.00 Max. :30.07 Max. :54.01 Max. :8.377
# 數(shù)據(jù)處理，因子化、數(shù)值化
VarsC<-c("Y","sex","edu")
for(i in VarsC){
log_data[,i] <- as.factor(log_data[,i])
}#利用循環(huán)因子化
summary(log_data)
Y sex edu BMI 白蛋白 隨機(jī)血糖
0:299 1:320 1:145 Min. :13.21 Min. :16.27 Min. :1.036
1:301 2:280 2:142 1st Qu.:20.18 1st Qu.:30.94 1st Qu.:3.956
3:139 Median :22.17 Median :34.78 Median :4.816
4:174 Mean :22.05 Mean :35.04 Mean :4.778
3rd Qu.:23.98 3rd Qu.:39.19 3rd Qu.:5.579
Max. :30.07 Max. :54.01 Max. :8.377
準(zhǔn)備進(jìn)行分析的自變量
#2.準(zhǔn)備進(jìn)行分析的自變量
varsU<-names(log_data[,2:6])#自變量
批量單因素logistic回歸
#3.批量單因素logistic回歸
Result<-c()
for (i in 1:length(varsU)){
fit<-glm(substitute(Y~x,list(x=as.name(varsU[i]))),data=log_data,family=binomial())
fitSum<-summary(fit)
result1<-c()
result1<-rbind(result1,fitSum$coef)
OR<-exp(fitSum$coef[,'Estimate'])
result1<-data.frame(cbind(result1,cbind(OR,exp(confint(fit)))))
result1$Characteristics<-varsU[i] #添加變量名
Result<-rbind(Result,result1[-1,])#[-1,],刪除常數(shù)項
}
提取制表變量重命名，提取有意義的變量
#4.提取制表變量重命名，提取有意義的變量
Uni_log<-data.frame(Result[,c(1,4:8)]) #提取"P","OR","CIlower","CIupper"和變量名
colnames(Uni_log)[2:5]<-c("P","OR","CIlower","CIupper")#變量重命名
ExtractVar<-unique(Uni_log$Characteristics[Uni_log$"P"<0.05])#提取有意義的變量
write.csv(Uni_log,file="Uni_log.csv")#輸出文檔
Uni_log
Estimate P OR CIlower CIupper Characteristics
sex2 0.094662809 0.5631116 1.0992881 0.7975801 1.515763 sex
edu2 0.154180710 0.5141640 1.1667017 0.7342831 1.856362 edu
edu3 -0.146213397 0.5389345 0.8639733 0.5412489 1.377153 edu
edu4 0.156454546 0.4869958 1.1693576 0.7523336 1.819676 edu
BMI 0.021802997 0.4450671 1.0220424 0.9664705 1.081118 BMI
白蛋白 0.004185709 0.7496789 1.0041945 0.9786903 1.030415 白蛋白
隨機(jī)血糖 -0.076032436 0.2659728 0.9267861 0.8100385 1.059365 隨機(jī)血糖
