Question

我正在尝试在R中编写自己的逻辑回归函数。目标是获得一个与glm（）函数具有相同结果的函数，其中family =二项式。我对序数数据有一些疑问。我曾尝试将其分解（通常在使用glm（）函数的情况下进行）。但是，我的函数和glm（）函数的结果不同。有谁知道如何用序数数据解决问题？在此先感谢您：)您可以在下面找到我的代码。

manual_logistic_regression = function(X,y,threshold = 1e-10, max_iter = 100)
  #A function to find logistic regression coefficients 
  #Takes three inputs: 
{
  #A function to return p, given X and beta
  #We'll need this function in the iterative section
  calc_p = function(X,beta)
  {
    beta = as.vector(beta)
    return(exp(X%*%beta) / (1+ exp(X%*%beta))) 
  }  

  #### setup bit ####

  #initial guess for beta
  beta = rep(0,ncol(X))

  #initial value bigger than threshold so that we can enter our while loop 
  diff = 10000 # has to be bigger than threshold

  #counter to ensure we're not stuck in an infinite loop
  iter_count = 0

  #### iterative bit ####
  while(diff > threshold ) #tests for convergence
  {
    #calculate probabilities using current estimate of beta
    p = as.vector(calc_p(X,beta)) #p is changing due to the new beta in each iteration

    #calculate matrix of weights W
    W =  diag(p*(1-p)) #varianz von Y, weil Y 1 oder 0 ist

    #calculate the change in beta
    beta_change = solve(t(X)%*%W%*%X) %*% t(X)%*%(y - p) 

    #update beta
    beta = beta + beta_change

    #calculate how much we changed beta by in this iteration 
    #if this is less than threshold, we'll break the while loop 
    diff = sum(beta_change^2) 

    #see if we've hit the maximum number of iterations
    iter_count = iter_count + 1
    if(iter_count > max_iter) {
      stop("Not converging.")
    }
  }

  #make it pretty 
  coef = c("(Intercept)" = beta[1], x1 = beta[2], x2 = beta[3], x3 = beta[4], x4 = beta[5]) 
  return(coef)
}

#I used the following data sample. I want to regress admit on great, gpa and rank.

mydata <- read.csv("https://stats.idre.ucla.edu/stat/data/binary.csv")
## view the first few rows of the data
head(mydata)
#
#institutions with a rank of 1 have the highest prestige, while those with a rank of 4 have the lowest.

mydata$rank <- factor(mydata$rank)
mylogit <- glm(admit ~ gre + gpa + rank, data = mydata, family = "binomial")

summary(mylogit)



rank<- factor(mydata$rank)
rank
class(rank) # make sure that it is really a factor

manual_logistic_regression(cbind(1,mydata$gre, mydata$gpa, rank),mydata$admit)

在R中编写自己的逻辑回归函数：如何处理序数数据

0 个答案: