R 中的风险评估模型，以获得某个因素的特定水平的概率

Question

我是一名风险分析师，我的老板给我分配了一项任务，我不知道该怎么做。

现在我想得到在某些特定条件下的概率。例如，数据看起来像这样

sex      hair_color Credit_Score Loan_Status
"Male"    "Red"      "256"        "bad"        
"Female"  "black"    "133"        "bad"        
"Female"  "brown"    "33"         "bad"        
"Male"    "yellow"   "123"        "good"

所以我们想为每个客户预测 Loan_Status。我能做的就是将 "sex"、"hair_color"、"credit_score" 视为因素。并将它们放入 R 中的 glm() 中。

但是我老板想知道"if a new customer who is male, red hair, what's the probability his loan status will be 'good'?"

或"What's the probability of male customers' loan status become 'good'?"

我应该使用什么样的方法？如何获得概率？我正在考虑边际分布，但我不知道这是否有效或我该如何计算它。

我希望我让这个问题容易理解，谁能帮助我，非常感谢你抽出时间

Answer 1

我认为本教程非常适合您的问题：http://www.theanalysisfactor.com/r-tutorial-glm1/

如果你在你的数据上使用它，它看起来像这样：

sex <- factor(c("m", "f", "f", "m"))
hair_color <- factor(c("red", "black", "brown", "yellow"))
credit_score <- c(256, 133, 33, 123)
loan_status <- factor(c("b", "b", "b", "g"))

data <- data.frame(sex, hair_color, credit_score, loan_status)

model <- glm(formula = loan_status ~ sex + hair_color + credit_score, 
         data = data, 
         family = "binomial")

predict(object = model, 
    newdata = data.frame(sex = "f", hair_color = "yellow", credit_score =     100),
    type = "response")

R 中的风险评估模型，以获得某个因素的特定水平的概率

Risk assessment models in R, in order to get the probability of specif levels of a factor

r

risk-analysis

prediction

glm

categorical-data