按组对面板数据进行 Beta 估计
Beta estimation over panel data by group
我之前发现了一些关于这个主题的问题，尤其是这个 and R: Rolling / moving avg by group ，但是，这两个问题都没有为我面临的问题提供确切的解决方案。我目前正在尝试使用线性回归估计面板数据的 CAPM beta。所以我有不同的基金（在下面的例子中我使用了 3 个基金组），我想分别计算每行的 beta。更抽象地说：我正在尝试通过按组移动 window 进行线性回归，以根据 window 中的数据估计每一行的系数。
install.packages("zoo","dplyr")
library(zoo);library(dplyr)
# Create dataframe
fund <- as.numeric(c(1,1,1,1,1,1,1,1,3,3,3,3,3,3,2,2,2,2,2,2,2))
return<- as.numeric(c(1:21))
benchmark <- as.numeric(c(1,13,14,20,14,32,4,1,5,7,1,0,7,1,-2,1,6,-7,9,10,9))
riskfree<-as.numeric(c(1,5,1,2,1,6,4,7,5,-5,10,0,3,1,2,1,6,7,8,9,10))
date <- as.Date(c("2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2011-02-28","2010-07-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30"))
funddata<-data.frame(date,fund,return,benchmark,riskfree)
# Creating variables of interest
funddata["ret_riskfree"]<-as.numeric(funddata$return-funddata$riskfree)
funddata["benchmark_riskfree"]<-as.numeric(funddata$benchmark-funddata$riskfree)
我想对 "fund" 列指示的每个组的两列 df[6:7] 进行滚动回归。计算应该单独进行，因此每个基金组的 beta 列中的前两行将始终显示 "NA"。最后，我想要一个包含所有基金组和所有 beta 值的完整数据框。
我设法想出了一个可以工作但非常混乱的新代码，它需要在执行前按基金和日期对数据进行排序。我欢迎任何关于如何让它变得更好的建议。
funddata <- funddata[order(funddata$fund, funddata$date),]
beta_func <- function(x, benchmark_riskfree, ret_riskfree) {
a <- coef(lm(as.formula(paste(ret_riskfree, "~", benchmark_riskfree,-1)),
data = x))
return(a)
}
beta_list<-list()
for (i in c(1:3)){beta_list[[paste(i, sep="_")]]<- (rollapplyr(funddata[(funddata$fund==i),6:7], width = 3,
FUN = function(x) beta_func(as.data.frame(x), "benchmark_riskfree" , "ret_riskfree"),
by.column = FALSE,fill=NA))}
beta_list<-unlist(beta_list, recursive=FALSE)
funddata$beta<-beta_list
正如我在上面的评论中提到的那样，由于我无法 100% 重现您想要的输出，因此该解决方案可能有点偏差。尽管如此，您要实现的功能仍然存在。看看它，让我知道您是否可以使用它或者我可以进一步开发它。
编辑： 下面的代码没有重现上面指定的所需输出，但结果却是 OP 所寻找的。
这里是：
# Datasource
fund <- as.numeric(c(1,1,1,1,1,1,1,1,3,3,3,3,3,3,2,2,2,2,2,2,2))
return<- as.numeric(c(1:21))
benchmark <- as.numeric(c(1,13,14,20,14,32,4,1,5,7,1,0,7,1,-2,1,6,-7,9,10,9))
riskfree<-as.numeric(c(1,5,1,2,1,6,4,7,5,-5,10,0,3,1,2,1,6,7,8,9,10))
date <- as.Date(c("2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2011-02-28","2010-07-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30"))
funddata<-data.frame(date,fund,return,benchmark,riskfree)
# Creating variables of interest
funddata["ret_riskfree"]<-as.numeric(funddata$return-funddata$riskfree)
funddata["benchmark_riskfree"]<-as.numeric(funddata$benchmark-funddata$riskfree)
# Target check #################################################################
# Subset last three rows in original dataframe
df_check <- funddata[funddata$fund == 1,]
df_check <- tail(df_check,3)
# Run regression check
mod_check <- lm(df_check$ret_riskfree~df_check$benchmark_riskfree)
coef(mod_check)
# My suggestion ################################################################
# The following function takes three arguments:
# 1. a dataframe, myDf
# 2. a column that you'd like to myDf on
# 3. a window length for a sliding window, myWin
fun_rollreg <- function(myDf, subCol, varY, varX, myWin){
df_main <- myDf
# Make an empty data frame to store results in
df_data <- data.frame()
# Identify unique funds
unFunds <- unique(unlist(df_main[subCol]))
# Loop through your subset
for (fundx in unFunds){
# Subset
df <- df_main
df <- df[df$fund == fundx,]
# Keep a copy of the original until later
df_new <- df
# Specify a container for your beta estimates
betas <- c()
# Specify window length
wlength <- myWin
# Retrieve some data dimensions to loop on
rows = dim(df)[1]
periods <- rows - wlength
# Loop through each subset of the data
# and run regression
for (i in rows:(rows - periods)){
# Split dataframe in subsets
# according to the window length
df1 <- df[(i-(wlength-1)):i,]
# Run regression
beta <- coef(lm(df1[[varY]]~df1[[varX]]))[2]
# Keep regression ressults
betas[[i]] <- beta
}
# Add regression data to dataframe
df_new <- data.frame(df, betas)
# Keep the new dataset for later concatenation
df_data <- rbind(df_data, df_new)
}
return(df_data)
}
# Run the function:
df_roll <- fun_rollreg(myDf = funddata, subCol = 'fund',
varY <- 'ret_riskfree', varX <- 'benchmark_riskfree',
myWin = 3)
# Show the results
print(head(df_roll,8))
对于新数据框 (fund = 1) 的前 8 行，结果如下：
date fund return benchmark riskfree ret_riskfree benchmark_riskfree betas
1 2010-07-30 1 1 1 1 0 0 NA
2 2010-08-31 1 2 13 5 -3 8 NA
3 2010-09-30 1 3 14 1 2 13 0.10465116
4 2010-10-31 1 4 20 2 2 18 0.50000000
5 2010-11-30 1 5 14 1 4 13 -0.20000000
6 2010-12-31 1 6 32 6 0 26 -0.30232558
7 2011-01-30 1 7 4 4 3 0 -0.11538462
8 2011-02-28 1 8 1 7 1 -6 -0.05645161
我之前发现了一些关于这个主题的问题，尤其是这个
install.packages("zoo","dplyr")
library(zoo);library(dplyr)
# Create dataframe
fund <- as.numeric(c(1,1,1,1,1,1,1,1,3,3,3,3,3,3,2,2,2,2,2,2,2))
return<- as.numeric(c(1:21))
benchmark <- as.numeric(c(1,13,14,20,14,32,4,1,5,7,1,0,7,1,-2,1,6,-7,9,10,9))
riskfree<-as.numeric(c(1,5,1,2,1,6,4,7,5,-5,10,0,3,1,2,1,6,7,8,9,10))
date <- as.Date(c("2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2011-02-28","2010-07-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30"))
funddata<-data.frame(date,fund,return,benchmark,riskfree)
# Creating variables of interest
funddata["ret_riskfree"]<-as.numeric(funddata$return-funddata$riskfree)
funddata["benchmark_riskfree"]<-as.numeric(funddata$benchmark-funddata$riskfree)
我想对 "fund" 列指示的每个组的两列 df[6:7] 进行滚动回归。计算应该单独进行，因此每个基金组的 beta 列中的前两行将始终显示 "NA"。最后，我想要一个包含所有基金组和所有 beta 值的完整数据框。 我设法想出了一个可以工作但非常混乱的新代码，它需要在执行前按基金和日期对数据进行排序。我欢迎任何关于如何让它变得更好的建议。
funddata <- funddata[order(funddata$fund, funddata$date),]
beta_func <- function(x, benchmark_riskfree, ret_riskfree) {
a <- coef(lm(as.formula(paste(ret_riskfree, "~", benchmark_riskfree,-1)),
data = x))
return(a)
}
beta_list<-list()
for (i in c(1:3)){beta_list[[paste(i, sep="_")]]<- (rollapplyr(funddata[(funddata$fund==i),6:7], width = 3,
FUN = function(x) beta_func(as.data.frame(x), "benchmark_riskfree" , "ret_riskfree"),
by.column = FALSE,fill=NA))}
beta_list<-unlist(beta_list, recursive=FALSE)
funddata$beta<-beta_list
正如我在上面的评论中提到的那样，由于我无法 100% 重现您想要的输出，因此该解决方案可能有点偏差。尽管如此，您要实现的功能仍然存在。看看它，让我知道您是否可以使用它或者我可以进一步开发它。
编辑： 下面的代码没有重现上面指定的所需输出，但结果却是 OP 所寻找的。
这里是：
# Datasource
fund <- as.numeric(c(1,1,1,1,1,1,1,1,3,3,3,3,3,3,2,2,2,2,2,2,2))
return<- as.numeric(c(1:21))
benchmark <- as.numeric(c(1,13,14,20,14,32,4,1,5,7,1,0,7,1,-2,1,6,-7,9,10,9))
riskfree<-as.numeric(c(1,5,1,2,1,6,4,7,5,-5,10,0,3,1,2,1,6,7,8,9,10))
date <- as.Date(c("2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2011-02-28","2010-07-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30",
"2010-07-30","2010-08-31","2010-09-30","2010-10-31","2010-11-30","2010-12-31","2011-01-30"))
funddata<-data.frame(date,fund,return,benchmark,riskfree)
# Creating variables of interest
funddata["ret_riskfree"]<-as.numeric(funddata$return-funddata$riskfree)
funddata["benchmark_riskfree"]<-as.numeric(funddata$benchmark-funddata$riskfree)
# Target check #################################################################
# Subset last three rows in original dataframe
df_check <- funddata[funddata$fund == 1,]
df_check <- tail(df_check,3)
# Run regression check
mod_check <- lm(df_check$ret_riskfree~df_check$benchmark_riskfree)
coef(mod_check)
# My suggestion ################################################################
# The following function takes three arguments:
# 1. a dataframe, myDf
# 2. a column that you'd like to myDf on
# 3. a window length for a sliding window, myWin
fun_rollreg <- function(myDf, subCol, varY, varX, myWin){
df_main <- myDf
# Make an empty data frame to store results in
df_data <- data.frame()
# Identify unique funds
unFunds <- unique(unlist(df_main[subCol]))
# Loop through your subset
for (fundx in unFunds){
# Subset
df <- df_main
df <- df[df$fund == fundx,]
# Keep a copy of the original until later
df_new <- df
# Specify a container for your beta estimates
betas <- c()
# Specify window length
wlength <- myWin
# Retrieve some data dimensions to loop on
rows = dim(df)[1]
periods <- rows - wlength
# Loop through each subset of the data
# and run regression
for (i in rows:(rows - periods)){
# Split dataframe in subsets
# according to the window length
df1 <- df[(i-(wlength-1)):i,]
# Run regression
beta <- coef(lm(df1[[varY]]~df1[[varX]]))[2]
# Keep regression ressults
betas[[i]] <- beta
}
# Add regression data to dataframe
df_new <- data.frame(df, betas)
# Keep the new dataset for later concatenation
df_data <- rbind(df_data, df_new)
}
return(df_data)
}
# Run the function:
df_roll <- fun_rollreg(myDf = funddata, subCol = 'fund',
varY <- 'ret_riskfree', varX <- 'benchmark_riskfree',
myWin = 3)
# Show the results
print(head(df_roll,8))
对于新数据框 (fund = 1) 的前 8 行，结果如下：
date fund return benchmark riskfree ret_riskfree benchmark_riskfree betas
1 2010-07-30 1 1 1 1 0 0 NA
2 2010-08-31 1 2 13 5 -3 8 NA
3 2010-09-30 1 3 14 1 2 13 0.10465116
4 2010-10-31 1 4 20 2 2 18 0.50000000
5 2010-11-30 1 5 14 1 4 13 -0.20000000
6 2010-12-31 1 6 32 6 0 26 -0.30232558
7 2011-01-30 1 7 4 4 3 0 -0.11538462
8 2011-02-28 1 8 1 7 1 -6 -0.05645161