# https://zhuanlan.zhihu.com/p/700555198 library(tidyverse) library(plyr) data(titanic_train,package = "titanic") # Survived:表示幸存与否的数字(1是幸存,0是死亡) # Pclass:乘客是否住头等舱、二等舱或三等舱 # Sex:性别 # FamSize:船上亲属的总人数 # Fare:每位乘客所付票款 # Embarked:乘客出发港口的特征向量 data<-titanic_train[-c(62,830),] %>% mutate_at(.vars = c("Sex","Pclass","Embarked"),.funs = factor) %>% mutate(FamSize=SibSp+Parch)%>% select(Survived,Pclass,Sex,FamSize,Fare,Embarked) colnames(data) #拆分数据:训练集和测试集 set.seed(111) index <- sort(sample(nrow(data), nrow(data) * 0.7)) train <- data[index,] #训练集 test <- data[-index,] #测试集 train$Fare[train$Fare<1]=1 #有几个值为0,取对数变成负无穷,因此给它赋值1 train$Fare<-log2(train$Fare) # 单因素分析 model<-glm(Survived==0 ~ Pclass,data=train,family = binomial()) summary(model) #模型系数 cbind(coef=coef(model),confint(model)) #变量的OR值 exp(cbind(OR=coef(model),confint(model))) # 从结果来看,相比于头等舱,二等舱和三等舱的人群死亡风险更高 # 批量单因素Logistic回归 uni_glm_model<-function(x){ FML<-as.formula(paste0("Survived== 0 ~",x)) glm1<-glm(FML,data=train,family = binomial) glm2<-summary(glm1) OR<-round(exp(coef(glm1)),2) SE<-round(glm2$coefficients[,2],3) CI2.5<-round(exp(coef(glm1)-1.96*SE),2) CI97.5<-round(exp(coef(glm1)+1.96*SE),2) CI<-paste0(CI2.5,"-",CI97.5) B<-round(glm2$coefficients[,1],3) Z<-round(glm2$coefficients[,3],3) P<-round(glm2$coefficients[,4],3) uni_glm_model<-data.frame("characteristics"=x, B=B, SE=SE, OR=OR, CI=CI, Z=Z, P=P)[-1,] return(uni_glm_model) } uni_glm<-lapply(colnames(train)[2:6],uni_glm_model) uni_glm<-ldply(uni_glm,data.frame) # 多因素分析 # 因为变量不多,就把所有因素纳入到多因素分析。 model_m<-glm(Survived==0 ~ Pclass+Sex+Fare+Embarked+FamSize, data=train, family = binomial()) summary(model_m) # Fare和Embarked变量p值不显著,FamSize变量在单因素分析不显著,但是在多因素分析显著,说明存在混杂因素的影响。 model_both<-step(model_m,direction = "both") mul_glm<-summary(model_both) mul_glm
https://mp.weixin.qq.com/s?__biz=MzI2OTQyMzc5MA==&mid=2247490396&idx=1&sn=b415ea07c997858b5791f08a6e6bb35b&chksm=eae1de9ddd96578bb77a8b15b13c80e377e9483292ec12a248624d9bb2cf2ec291e8cd19bdd7&scene=21#wechat_redirecthttps://blog.csdn.net/weixin_43843918/article/details/135163071
https://zhuanlan.zhihu.com/p/660756933
https://blog.csdn.net/Dr_long1996/article/details/134881348