使用 stargazer 在不同的 table 列中拆分系数
Split coefficients in different table columns with stargazer
我的模型输出具有 32 个系数。我希望它们全部显示在一个 table 中，并想出了在一列中分别显示 16 个系数及其固有估计值和 p 值的想法。有什么方法可以对模型输出进行切片或告诉 stargazer 将输出拆分为不同的列吗？
poisson_model <-
bind_rows(
tibble(
goals = database_mr$goals_team_home,
team = database_mr$club_name_home,
opponent=database_mr$club_name_away,
home=1),
tibble(
goals=database_mr$goals_team_away,
team=database_mr$club_name_away,
opponent=database_mr$club_name_home,
home=0)) %>%
glm(goals ~ home + team +opponent, family=poisson(link=log),data=.)
summary(poisson_model)
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.75216 0.22805 3.298 0.000973 ***
home 0.24096 0.07588 3.176 0.001495 **
teamAdler Weseke II -1.04748 0.24868 -4.212 2.53e-05 ***
teamBVH Dorsten -0.28911 0.19946 -1.449 0.147200
teamFC RW Dorsten -0.87653 0.23168 -3.783 0.000155 ***
teamFenerbahce I. Marl -0.56356 0.20580 -2.738 0.006175 **
teamSC Marl-Hamm -0.14523 0.19169 -0.758 0.448688
teamSC Reken II -0.40481 0.20569 -1.968 0.049057 *
teamSV Altendorf-Ulfkotte -1.25184 0.27720 -4.516 6.30e-06 ***
teamSV Lembeck -0.21607 0.19568 -1.104 0.269518
teamSV Schermbeck II -0.16674 0.18600 -0.896 0.370028
teamTSV Raesfeld 0.02094 0.17866 0.117 0.906682
teamTuS 05 Sinsen II -0.90159 0.24070 -3.746 0.000180 ***
teamTuS Gahlen -0.26630 0.19142 -1.391 0.164171
teamTuS Velen -0.40946 0.20151 -2.032 0.042159 *
teamVfL Ramsdorf 0.07215 0.17726 0.407 0.683973
teamWestfalia Gemen II -0.55929 0.20990 -2.665 0.007709 **
opponentAdler Weseke II 0.59518 0.21831 2.726 0.006405 **
opponentBVH Dorsten 0.05072 0.25027 0.203 0.839389
opponentFC RW Dorsten 0.17760 0.23700 0.749 0.453647
opponentFenerbahce I. Marl 0.10922 0.24428 0.447 0.654802
opponentSC Marl-Hamm 0.50746 0.22592 2.246 0.024691 *
opponentSC Reken II 0.69698 0.21994 3.169 0.001530 **
opponentSV Altendorf-Ulfkotte 1.08930 0.20466 5.322 1.02e-07 ***
opponentSV Lembeck 0.35564 0.22962 1.549 0.121428
opponentSV Schermbeck II -0.26666 0.27163 -0.982 0.326254
opponentTSV Raesfeld -0.08465 0.25771 -0.328 0.742563
opponentTuS 05 Sinsen II 0.58102 0.21870 2.657 0.007891 **
opponentTuS Gahlen -0.81158 0.31450 -2.581 0.009865 **
opponentTuS Velen 0.28034 0.23333 1.201 0.229578
opponentVfL Ramsdorf -0.43481 0.28270 -1.538 0.124030
opponentWestfalia Gemen II 0.59072 0.22016 2.683 0.007293 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Stargazer 为您提供了手动提供系数列表和相应标准误差的选项。你可以 "trick" stargazer with passing 两个模型，然后手动传递系数。这很有效，因为 stargazer 按名称匹配不同模型的系数。缺点是你需要 运行 一个 "fake regression"，你需要调整 obs，rsquared 等。但是，你可以很容易地提取所需的信息并将其添加到 table 中 add.lines.
这是运行使用主队和对方球队的二元指标进行回归并在两列中报告系数的最终结果：
代码：
library(stargazer)
# generate some data
d <- data.frame(score=rpois(1000,1),
home=sample(letters[1:10],1000,replace=T ),
opp=sample(letters[1:10],1000,replace=T ))
head(d)
score home opp
1: 2 c g
2: 1 j g
3: 0 e f
4: 1 f j
5: 0 d i
6: 1 d f
# create a fake model
# note that home needs to include all of your factors
fake <- lm(score ~ home - 1, d)
# rename the coefficients
names(fake$coefficients) <- gsub("home","",names(fake$coefficients))
# run your regression
m <- glm(score ~ home + opp - 1, d, family=poisson(link=log) )
summary(m)
Call:
glm(formula = score ~ home + opp - 1, family = poisson(link = log),
data = d)
Deviance Residuals:
Min 1Q Median 3Q Max
-1.68446 -1.36736 -0.00948 0.60121 2.85408
Coefficients:
Estimate Std. Error z value Pr(>|z|)
homea 0.0286251 0.1407933 0.203 0.8389
homeb -0.1563594 0.1352870 -1.156 0.2478
homec -0.0673791 0.1378263 -0.489 0.6249
homed -0.0425058 0.1383590 -0.307 0.7587
homee -0.0612811 0.1463620 -0.419 0.6754
homef -0.0028756 0.1407210 -0.020 0.9837
homeg -0.0263096 0.1419598 -0.185 0.8530
homeh -0.0421442 0.1371384 -0.307 0.7586
homei 0.0871397 0.1382671 0.630 0.5285
homej -0.0650161 0.1354183 -0.480 0.6311
oppb -0.0102711 0.1459574 -0.070 0.9439
oppc 0.2625987 0.1426320 1.841 0.0656 .
oppd 0.1465768 0.1417666 1.034 0.3012
oppe 0.0123358 0.1384327 0.089 0.9290
oppf -0.0007423 0.1381802 -0.005 0.9957
oppg -0.0035419 0.1481746 -0.024 0.9809
opph 0.0852252 0.1378236 0.618 0.5363
oppi -0.0695733 0.1474909 -0.472 0.6371
oppj -0.0577961 0.1478874 -0.391 0.6959
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for poisson family taken to be 1)
Null deviance: 1124.6 on 1000 degrees of freedom
Residual deviance: 1111.8 on 981 degrees of freedom
AIC: 2624.1
Number of Fisher Scoring iterations: 5
m.s <- summary(m)
## write a function that fixes the names in the glm output
f <- function(x){
names(x) <- gsub("home|opp","", names(x))
return(x)
}
# now you can retrieve variables according to the prefix
m.s$coefficients[grepl("home", rownames(m.s$coefficients)), 1]
homeb homec homed homee homef homeg homeh homei homej
-0.008070675 0.287148469 -0.043331430 0.047798075 0.005438897 0.261008373 0.134444746 0.083937955 0.113310674
stargazer(fake,fake,
# coefficients
coef = list(
f( m.s$coefficients[grepl("home", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("opp", rownames(m.s$coefficients)), 1])
),
# standard errors
se = list(
f( m.s$coefficients[grepl("home", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("opp", rownames(m.s$coefficients)), 2])
),
column.labels = c("home", "opp"),
# calculate pvalue using supplied coeff and se
t.auto = T,
out = "stargazer_d.html",
omit.stat=c("all"),
type = "html")
使用您的数据：
d <- readr::read_rds( "database_match_results_1920.rds")
d <-
bind_rows(
tibble(
goals = database_mr$goals_team_home,
team = database_mr$club_name_home,
opponent=database_mr$club_name_away,
home=1),
tibble(
goals=database_mr$goals_team_away,
team=database_mr$club_name_away,
opponent=database_mr$club_name_home,
home=0))
# create a fake model
# note that team needs to include all of your factors
fake <- lm(goals ~ home + team , d)
# rename the coefficients
names(fake$coefficients) <- gsub("team","",names(fake$coefficients))
#
m <- glm(goals ~ home + team +opponent, family=poisson(link=log),data=d)
m.s <- summary(m)
## write a function that fixes the names in the glm output
f <- function(x){
names(x) <- gsub("team|opponent","", names(x))
return(x)
}
stargazer(fake,fake,
# coefficients
coef = list(
f( m.s$coefficients[grepl("Intercept|home|team", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 1])
),
# standard errors
se = list(
f( m.s$coefficients[grepl("Intercept|home|team", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 2])
),
column.labels = c("team", "opponent"),
# calculate pvalue using supplied coeff and se
t.auto = T,
out = "stargazer_data.html",
omit.stat=c("all"),
type = "html")
有 3 列：
stargazer(fake,fake,fake,
# coefficients
coef = list(
f( m.s$coefficients[grepl("Intercept|home", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("team", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 1])
),
# standard errors
se = list(
f( m.s$coefficients[grepl("Intercept|home", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("team", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 2])
),
column.labels = c("control","team", "opponent"),
# calculate pvalue using supplied coeff and se
t.auto = T,
out = "stargazer_data.html",
omit.stat=c("all"),
type = "html")
我的模型输出具有 32 个系数。我希望它们全部显示在一个 table 中，并想出了在一列中分别显示 16 个系数及其固有估计值和 p 值的想法。有什么方法可以对模型输出进行切片或告诉 stargazer 将输出拆分为不同的列吗？
poisson_model <-
bind_rows(
tibble(
goals = database_mr$goals_team_home,
team = database_mr$club_name_home,
opponent=database_mr$club_name_away,
home=1),
tibble(
goals=database_mr$goals_team_away,
team=database_mr$club_name_away,
opponent=database_mr$club_name_home,
home=0)) %>%
glm(goals ~ home + team +opponent, family=poisson(link=log),data=.)
summary(poisson_model)
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.75216 0.22805 3.298 0.000973 ***
home 0.24096 0.07588 3.176 0.001495 **
teamAdler Weseke II -1.04748 0.24868 -4.212 2.53e-05 ***
teamBVH Dorsten -0.28911 0.19946 -1.449 0.147200
teamFC RW Dorsten -0.87653 0.23168 -3.783 0.000155 ***
teamFenerbahce I. Marl -0.56356 0.20580 -2.738 0.006175 **
teamSC Marl-Hamm -0.14523 0.19169 -0.758 0.448688
teamSC Reken II -0.40481 0.20569 -1.968 0.049057 *
teamSV Altendorf-Ulfkotte -1.25184 0.27720 -4.516 6.30e-06 ***
teamSV Lembeck -0.21607 0.19568 -1.104 0.269518
teamSV Schermbeck II -0.16674 0.18600 -0.896 0.370028
teamTSV Raesfeld 0.02094 0.17866 0.117 0.906682
teamTuS 05 Sinsen II -0.90159 0.24070 -3.746 0.000180 ***
teamTuS Gahlen -0.26630 0.19142 -1.391 0.164171
teamTuS Velen -0.40946 0.20151 -2.032 0.042159 *
teamVfL Ramsdorf 0.07215 0.17726 0.407 0.683973
teamWestfalia Gemen II -0.55929 0.20990 -2.665 0.007709 **
opponentAdler Weseke II 0.59518 0.21831 2.726 0.006405 **
opponentBVH Dorsten 0.05072 0.25027 0.203 0.839389
opponentFC RW Dorsten 0.17760 0.23700 0.749 0.453647
opponentFenerbahce I. Marl 0.10922 0.24428 0.447 0.654802
opponentSC Marl-Hamm 0.50746 0.22592 2.246 0.024691 *
opponentSC Reken II 0.69698 0.21994 3.169 0.001530 **
opponentSV Altendorf-Ulfkotte 1.08930 0.20466 5.322 1.02e-07 ***
opponentSV Lembeck 0.35564 0.22962 1.549 0.121428
opponentSV Schermbeck II -0.26666 0.27163 -0.982 0.326254
opponentTSV Raesfeld -0.08465 0.25771 -0.328 0.742563
opponentTuS 05 Sinsen II 0.58102 0.21870 2.657 0.007891 **
opponentTuS Gahlen -0.81158 0.31450 -2.581 0.009865 **
opponentTuS Velen 0.28034 0.23333 1.201 0.229578
opponentVfL Ramsdorf -0.43481 0.28270 -1.538 0.124030
opponentWestfalia Gemen II 0.59072 0.22016 2.683 0.007293 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Stargazer 为您提供了手动提供系数列表和相应标准误差的选项。你可以 "trick" stargazer with passing 两个模型，然后手动传递系数。这很有效，因为 stargazer 按名称匹配不同模型的系数。缺点是你需要 运行 一个 "fake regression"，你需要调整 obs，rsquared 等。但是，你可以很容易地提取所需的信息并将其添加到 table 中 add.lines.
这是运行使用主队和对方球队的二元指标进行回归并在两列中报告系数的最终结果：
代码：
library(stargazer)
# generate some data
d <- data.frame(score=rpois(1000,1),
home=sample(letters[1:10],1000,replace=T ),
opp=sample(letters[1:10],1000,replace=T ))
head(d)
score home opp
1: 2 c g
2: 1 j g
3: 0 e f
4: 1 f j
5: 0 d i
6: 1 d f
# create a fake model
# note that home needs to include all of your factors
fake <- lm(score ~ home - 1, d)
# rename the coefficients
names(fake$coefficients) <- gsub("home","",names(fake$coefficients))
# run your regression
m <- glm(score ~ home + opp - 1, d, family=poisson(link=log) )
summary(m)
Call:
glm(formula = score ~ home + opp - 1, family = poisson(link = log),
data = d)
Deviance Residuals:
Min 1Q Median 3Q Max
-1.68446 -1.36736 -0.00948 0.60121 2.85408
Coefficients:
Estimate Std. Error z value Pr(>|z|)
homea 0.0286251 0.1407933 0.203 0.8389
homeb -0.1563594 0.1352870 -1.156 0.2478
homec -0.0673791 0.1378263 -0.489 0.6249
homed -0.0425058 0.1383590 -0.307 0.7587
homee -0.0612811 0.1463620 -0.419 0.6754
homef -0.0028756 0.1407210 -0.020 0.9837
homeg -0.0263096 0.1419598 -0.185 0.8530
homeh -0.0421442 0.1371384 -0.307 0.7586
homei 0.0871397 0.1382671 0.630 0.5285
homej -0.0650161 0.1354183 -0.480 0.6311
oppb -0.0102711 0.1459574 -0.070 0.9439
oppc 0.2625987 0.1426320 1.841 0.0656 .
oppd 0.1465768 0.1417666 1.034 0.3012
oppe 0.0123358 0.1384327 0.089 0.9290
oppf -0.0007423 0.1381802 -0.005 0.9957
oppg -0.0035419 0.1481746 -0.024 0.9809
opph 0.0852252 0.1378236 0.618 0.5363
oppi -0.0695733 0.1474909 -0.472 0.6371
oppj -0.0577961 0.1478874 -0.391 0.6959
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for poisson family taken to be 1)
Null deviance: 1124.6 on 1000 degrees of freedom
Residual deviance: 1111.8 on 981 degrees of freedom
AIC: 2624.1
Number of Fisher Scoring iterations: 5
m.s <- summary(m)
## write a function that fixes the names in the glm output
f <- function(x){
names(x) <- gsub("home|opp","", names(x))
return(x)
}
# now you can retrieve variables according to the prefix
m.s$coefficients[grepl("home", rownames(m.s$coefficients)), 1]
homeb homec homed homee homef homeg homeh homei homej
-0.008070675 0.287148469 -0.043331430 0.047798075 0.005438897 0.261008373 0.134444746 0.083937955 0.113310674
stargazer(fake,fake,
# coefficients
coef = list(
f( m.s$coefficients[grepl("home", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("opp", rownames(m.s$coefficients)), 1])
),
# standard errors
se = list(
f( m.s$coefficients[grepl("home", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("opp", rownames(m.s$coefficients)), 2])
),
column.labels = c("home", "opp"),
# calculate pvalue using supplied coeff and se
t.auto = T,
out = "stargazer_d.html",
omit.stat=c("all"),
type = "html")
使用您的数据：
d <- readr::read_rds( "database_match_results_1920.rds")
d <-
bind_rows(
tibble(
goals = database_mr$goals_team_home,
team = database_mr$club_name_home,
opponent=database_mr$club_name_away,
home=1),
tibble(
goals=database_mr$goals_team_away,
team=database_mr$club_name_away,
opponent=database_mr$club_name_home,
home=0))
# create a fake model
# note that team needs to include all of your factors
fake <- lm(goals ~ home + team , d)
# rename the coefficients
names(fake$coefficients) <- gsub("team","",names(fake$coefficients))
#
m <- glm(goals ~ home + team +opponent, family=poisson(link=log),data=d)
m.s <- summary(m)
## write a function that fixes the names in the glm output
f <- function(x){
names(x) <- gsub("team|opponent","", names(x))
return(x)
}
stargazer(fake,fake,
# coefficients
coef = list(
f( m.s$coefficients[grepl("Intercept|home|team", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 1])
),
# standard errors
se = list(
f( m.s$coefficients[grepl("Intercept|home|team", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 2])
),
column.labels = c("team", "opponent"),
# calculate pvalue using supplied coeff and se
t.auto = T,
out = "stargazer_data.html",
omit.stat=c("all"),
type = "html")
有 3 列：
stargazer(fake,fake,fake,
# coefficients
coef = list(
f( m.s$coefficients[grepl("Intercept|home", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("team", rownames(m.s$coefficients)), 1]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 1])
),
# standard errors
se = list(
f( m.s$coefficients[grepl("Intercept|home", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("team", rownames(m.s$coefficients)), 2]),
f( m.s$coefficients[grepl("opponent", rownames(m.s$coefficients)), 2])
),
column.labels = c("control","team", "opponent"),
# calculate pvalue using supplied coeff and se
t.auto = T,
out = "stargazer_data.html",
omit.stat=c("all"),
type = "html")