尝试使用 R 中的 plm 在 stata 中重现 xtreg
Trying to reproduce xtreg in stata with plm in R
如果不使用 Stata 中的 fe 选项，我似乎无法在 R 中匹配 Stata 中的 xtreg 命令。
当我进行标准回归或具有固定效应的面板模型时，Stata 和 R 中的系数相同。
示例数据：
library("plm" )
z <- Cigar[ Cigar$year %in% c( 63, 73) , ]
#saving so I can use in Stata
foreign::write.dta( z , "C:/Users/matthewr/Desktop/temp.dta")
所以我在 R 中得到了相同的系数：
coef( lm( sales ~ pop , data= z2 ) )
这在 Stata 中
use "C:/Users/matthewr/Desktop/temp.dta" , clear
reg sales pop
当我设置面板并使用固定效果选项时它起作用了。
z2 <- pdata.frame( z , index=c("state", "year") )
coef( plm( sales ~ pop , data= z2 , model="within" ) ) # matches xtreg , fe
在 Stata 中匹配这个
xtset state year
xtreg sales pop, fe
当我没有使用固定效果选项时，我不知道如何匹配 Stata
我试图在 R 中匹配这个结果，但不能
这是我想要重现的结果：
系数：-.0006838
xtreg sales pop
Stata xtreg y x相当于xtreg y x, re，所以你要的是计算随机效应
summary(plm(sales ~ pop, data=z, model="random", index=c("state", "year")))$coe
# Estimate Std. Error z-value Pr(>|z|)
# (Intercept) 1.311398e+02 6.499511330 20.176878 1.563130e-90
# pop -6.837769e-04 0.001077432 -0.634636 5.256658e-01
数据：
xtreg sales pop, re
sales | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
pop | -.0006838 .0010774 -0.63 0.526 -.0027955 .001428
_cons | 131.1398 6.499511 20.18 0.000 118.401 143.8787
@jay.sf 已回答您的问题。我只是添加了其他内容，尽管它可能无法直接回答您的问题。 Stata xtreg 和 R plm 都有一些选项，我觉得 RStata 包可能是一个方便的工具来尝试不同的选项并比较 Stata 和 [=15= 的结果] 直接在 RStudio 中。我认为这可能会有所帮助。 Stata 路径仅适用于我的计算机。
library("plm" )
library(RStata)
data("Cigar", package = "plm")
z <- Cigar[ Cigar$year %in% c( 63, 73) , ]
options("RStata.StataPath" = "\"C:\Program Files (x86)\Stata14\StataSE-64\"")
options("RStata.StataVersion" = 14)
# Stata fe
stata_do1 <- '
xtset state year
xtreg sales pop, fe
'
stata(stata_do1, data.out = TRUE, data.in = z)
#> .
#> . xtset state year
#> panel variable: state (strongly balanced)
#> time variable: year, 63 to 73, but with gaps
#> delta: 1 unit
#> . xtreg sales pop, fe
#>
#> Fixed-effects (within) regression Number of obs = 92
#> Group variable: state Number of groups = 46
#>
#> R-sq: Obs per group:
#> within = 0.0118 min = 2
#> between = 0.0049 avg = 2.0
#> overall = 0.0048 max = 2
#>
#> F(1,45) = 0.54
#> corr(u_i, Xb) = -0.3405 Prob > F = 0.4676
#>
#> ------------------------------------------------------------------------------
#> sales | Coef. Std. Err. t P>|t| [95% Conf. Interval]
#> -------------+----------------------------------------------------------------
#> pop | -.0032108 .0043826 -0.73 0.468 -.0120378 .0056162
#> _cons | 141.5186 18.06909 7.83 0.000 105.1256 177.9116
#> -------------+----------------------------------------------------------------
#> sigma_u | 34.093409
#> sigma_e | 15.183908
#> rho | .83448264 (fraction of variance due to u_i)
#> ------------------------------------------------------------------------------
#> F test that all u_i=0: F(45, 45) = 8.91 Prob > F = 0.0000
# R
z2 <- pdata.frame( z , index=c("state", "year") )
coef( plm( sales ~ pop , data= z2 , model="within" ) )
#> pop
#> -0.003210817
# Stata re
stata_do2 <- '
xtset state year
xtreg sales pop, re
'
stata(stata_do2, data.out = TRUE, data.in = z)
#> .
#> . xtset state year
#> panel variable: state (strongly balanced)
#> time variable: year, 63 to 73, but with gaps
#> delta: 1 unit
#> . xtreg sales pop, re
#>
#> Random-effects GLS regression Number of obs = 92
#> Group variable: state Number of groups = 46
#>
#> R-sq: Obs per group:
#> within = 0.0118 min = 2
#> between = 0.0049 avg = 2.0
#> overall = 0.0048 max = 2
#>
#> Wald chi2(1) = 0.40
#> corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.5257
#>
#> ------------------------------------------------------------------------------
#> sales | Coef. Std. Err. z P>|z| [95% Conf. Interval]
#> -------------+----------------------------------------------------------------
#> pop | -.0006838 .0010774 -0.63 0.526 -.0027955 .001428
#> _cons | 131.1398 6.499511 20.18 0.000 118.401 143.8787
#> -------------+----------------------------------------------------------------
#> sigma_u | 30.573218
#> sigma_e | 15.183908
#> rho | .80214841 (fraction of variance due to u_i)
#> ------------------------------------------------------------------------------
# R random
coef(plm(sales ~ pop,
data=z,
model="random",
index=c("state", "year")))
#> (Intercept) pop
#> 1.311398e+02 -6.837769e-04
由 reprex package (v0.3.0)
于 2020-01-27 创建
如果不使用 Stata 中的 fe 选项，我似乎无法在 R 中匹配 Stata 中的 xtreg 命令。
当我进行标准回归或具有固定效应的面板模型时，Stata 和 R 中的系数相同。
示例数据：
library("plm" )
z <- Cigar[ Cigar$year %in% c( 63, 73) , ]
#saving so I can use in Stata
foreign::write.dta( z , "C:/Users/matthewr/Desktop/temp.dta")
所以我在 R 中得到了相同的系数：
coef( lm( sales ~ pop , data= z2 ) )
这在 Stata 中
use "C:/Users/matthewr/Desktop/temp.dta" , clear
reg sales pop
当我设置面板并使用固定效果选项时它起作用了。
z2 <- pdata.frame( z , index=c("state", "year") )
coef( plm( sales ~ pop , data= z2 , model="within" ) ) # matches xtreg , fe
在 Stata 中匹配这个
xtset state year
xtreg sales pop, fe
当我没有使用固定效果选项时，我不知道如何匹配 Stata 我试图在 R 中匹配这个结果，但不能 这是我想要重现的结果： 系数：-.0006838
xtreg sales pop
Stata xtreg y x相当于xtreg y x, re，所以你要的是计算随机效应
summary(plm(sales ~ pop, data=z, model="random", index=c("state", "year")))$coe
# Estimate Std. Error z-value Pr(>|z|)
# (Intercept) 1.311398e+02 6.499511330 20.176878 1.563130e-90
# pop -6.837769e-04 0.001077432 -0.634636 5.256658e-01
数据：
xtreg sales pop, re
sales | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
pop | -.0006838 .0010774 -0.63 0.526 -.0027955 .001428
_cons | 131.1398 6.499511 20.18 0.000 118.401 143.8787
@jay.sf 已回答您的问题。我只是添加了其他内容，尽管它可能无法直接回答您的问题。 Stata xtreg 和 R plm 都有一些选项，我觉得 RStata 包可能是一个方便的工具来尝试不同的选项并比较 Stata 和 [=15= 的结果] 直接在 RStudio 中。我认为这可能会有所帮助。 Stata 路径仅适用于我的计算机。
library("plm" )
library(RStata)
data("Cigar", package = "plm")
z <- Cigar[ Cigar$year %in% c( 63, 73) , ]
options("RStata.StataPath" = "\"C:\Program Files (x86)\Stata14\StataSE-64\"")
options("RStata.StataVersion" = 14)
# Stata fe
stata_do1 <- '
xtset state year
xtreg sales pop, fe
'
stata(stata_do1, data.out = TRUE, data.in = z)
#> .
#> . xtset state year
#> panel variable: state (strongly balanced)
#> time variable: year, 63 to 73, but with gaps
#> delta: 1 unit
#> . xtreg sales pop, fe
#>
#> Fixed-effects (within) regression Number of obs = 92
#> Group variable: state Number of groups = 46
#>
#> R-sq: Obs per group:
#> within = 0.0118 min = 2
#> between = 0.0049 avg = 2.0
#> overall = 0.0048 max = 2
#>
#> F(1,45) = 0.54
#> corr(u_i, Xb) = -0.3405 Prob > F = 0.4676
#>
#> ------------------------------------------------------------------------------
#> sales | Coef. Std. Err. t P>|t| [95% Conf. Interval]
#> -------------+----------------------------------------------------------------
#> pop | -.0032108 .0043826 -0.73 0.468 -.0120378 .0056162
#> _cons | 141.5186 18.06909 7.83 0.000 105.1256 177.9116
#> -------------+----------------------------------------------------------------
#> sigma_u | 34.093409
#> sigma_e | 15.183908
#> rho | .83448264 (fraction of variance due to u_i)
#> ------------------------------------------------------------------------------
#> F test that all u_i=0: F(45, 45) = 8.91 Prob > F = 0.0000
# R
z2 <- pdata.frame( z , index=c("state", "year") )
coef( plm( sales ~ pop , data= z2 , model="within" ) )
#> pop
#> -0.003210817
# Stata re
stata_do2 <- '
xtset state year
xtreg sales pop, re
'
stata(stata_do2, data.out = TRUE, data.in = z)
#> .
#> . xtset state year
#> panel variable: state (strongly balanced)
#> time variable: year, 63 to 73, but with gaps
#> delta: 1 unit
#> . xtreg sales pop, re
#>
#> Random-effects GLS regression Number of obs = 92
#> Group variable: state Number of groups = 46
#>
#> R-sq: Obs per group:
#> within = 0.0118 min = 2
#> between = 0.0049 avg = 2.0
#> overall = 0.0048 max = 2
#>
#> Wald chi2(1) = 0.40
#> corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.5257
#>
#> ------------------------------------------------------------------------------
#> sales | Coef. Std. Err. z P>|z| [95% Conf. Interval]
#> -------------+----------------------------------------------------------------
#> pop | -.0006838 .0010774 -0.63 0.526 -.0027955 .001428
#> _cons | 131.1398 6.499511 20.18 0.000 118.401 143.8787
#> -------------+----------------------------------------------------------------
#> sigma_u | 30.573218
#> sigma_e | 15.183908
#> rho | .80214841 (fraction of variance due to u_i)
#> ------------------------------------------------------------------------------
# R random
coef(plm(sales ~ pop,
data=z,
model="random",
index=c("state", "year")))
#> (Intercept) pop
#> 1.311398e+02 -6.837769e-04
由 reprex package (v0.3.0)
于 2020-01-27 创建