R：使用移动窗口按组计算标准偏差

Question

我很想分析多家公司的每月股票回报（面板数据）。但是，我正在努力计算公司过去 X 个月的标准差。

基本上，我想在现有的 data.frame 中添加另一列，其中显示了根据公司 X 个月移动窗口的标准偏差。请在下面找到我的数据的简化示例以及我希望实现的目标。

#My data:
company = c("1","1","1","1","1","2","2","2","2","2","2","2","3","3","3","3","4","4","4")
return = c(0.01,0.015,-0.01,0.02,0.023,-0.04,-0.02,-0.01,0.05,0.06,0.03,-0.09,0.2,0.3,-0.04,-0.02,-0.01,0.023,-0.04)
stock = data.frame(company,return)

鉴于这种初始情况，我很想计算另一列中的标准差，例如基于3 次观察。

#Column to be filled with the respective value
stock["std_3obs"] = NA
#However, I do not manage to fill this column accordingly. The following result for a given row is expected:
#row 1 = Not possible, as there are not enough prior observations available
#row 2 = Not possible, as there are not enough prior observations available
#row 3 = sd(c(0.01,0.015,-0.01) = 0.01322876
#row 7 = Not possible, as there are not enough prior observations available
#row 8 = sd(c(-0.040,-0.020,-0.010)) = 0.01527525

提前非常感谢！非常感谢任何帮助！请温柔一点，因为我对 R 还很陌生。

*旁注： 研究这个问题和调整其他解决方案总是会导致这个错误：replacement has X rows, data has Y * where X >>> Y

Answer 1

您可以使用 zoo 包中的滚动功能：

library(dplyr)

stock %>%
  group_by(company) %>%
  mutate(std_3obs = zoo::rollapplyr(return, 3, sd, fill = NA))

#  company return std_3obs
#   <chr>    <dbl>    <dbl>
# 1 1        0.01   NA     
# 2 1        0.015  NA     
# 3 1       -0.01    0.0132
# 4 1        0.02    0.0161
# 5 1        0.023   0.0182
# 6 2       -0.04   NA     
# 7 2       -0.02   NA     
# 8 2       -0.01    0.0153
# 9 2        0.05    0.0379
#10 2        0.06    0.0379
#11 2        0.03    0.0153
#12 2       -0.09    0.0794
#13 3        0.2    NA     
#14 3        0.3    NA     
#15 3       -0.04    0.175 
#16 3       -0.02    0.191 
#17 4       -0.01   NA     
#18 4        0.023  NA     
#19 4       -0.04    0.0315

Answer 2

这是data.table 方法

library(data.table)
setDT(stock)[, std_3obs := frollapply(return, 3, sd), by = company]

输出

> stock[]
    company return   std_3obs
 1:       1  0.010         NA
 2:       1  0.015         NA
 3:       1 -0.010 0.01322876
 4:       1  0.020 0.01607275
 5:       1  0.023 0.01824829
 6:       2 -0.040         NA
 7:       2 -0.020         NA
 8:       2 -0.010 0.01527525
 9:       2  0.050 0.03785939
10:       2  0.060 0.03785939
11:       2  0.030 0.01527525
12:       2 -0.090 0.07937254
13:       3  0.200         NA
14:       3  0.300         NA
15:       3 -0.040 0.17473790
16:       3 -0.020 0.19078784
17:       4 -0.010         NA
18:       4  0.023         NA
19:       4 -0.040 0.03151190