I would like to "flip" the row/columns in a regression table.
The latest stargazer manuals says that now the flip argument also works with regression tables (previously it only worked with summary stats).
However I am unable to make it work. Here is an example with stargazer 5.2.1
library(stargazer)
stargazer(attitude)
linear.1 <- lm(rating ~ complaints + privileges + learning + raises + critical, data=attitude)
linear.2 <- lm(rating ~ complaints + privileges + learning, data=attitude)
## create an indicator dependent variable, and run a probit model
attitude$high.rating <- (attitude$rating > 70)
probit.model <- glm(high.rating ~ learning + critical + advance, data=attitude, family = binomial(link = "probit"))
stargazer(linear.1, linear.2, probit.model, title= "Regression Results", type = 'text', flip = TRUE)
gives :
> stargazer(linear.1, linear.2, probit.model, title="Regression Results", type = 'text', flip = FALSE)
the condition has length > 1 and only the first element will be usednumber of rows of result is not a multiple of vector length (arg 2)number of rows of result is not a multiple of vector length (arg 2)
Regression Results
=============================================================================
Dependent variable:
---------------------------------------------------------
rating high.rating
OLS probit
(1) (2) (3)
-----------------------------------------------------------------------------
complaints 0.692*** 0.682***
(0.149) (0.129)
privileges -0.104 -0.103
(0.135) (0.129)
learning 0.249 0.238* 0.164***
(0.160) (0.139) (0.053)
raises -0.033
The table is just the regular one with variables as columns. Instead, I am looking for something like
Regression Results
=====================================
complaints privileges
-------------------------------------
model1 0.692*** etc
(0.149)
model2 0.14**
(0.049)
model3 0.692
(0.149)
Am I missing something? Thanks!
Here you go, my friend. I hope this helps.
stargazer(coef(summary(linear.1)), coef(summary(linear.2)), coef(summary(probit.model)), title= "Regression Results", type = 'text', flip = TRUE)
Output:
Regression Results
======================================================================
(Intercept) complaints privileges learning raises critical
----------------------------------------------------------------------
Estimate 11.011 0.692 -0.104 0.249 -0.033 0.015
Std. Error 11.704 0.149 0.135 0.160 0.202 0.147
t value 0.941 4.649 -0.769 1.560 -0.165 0.105
Pr(> | t| ) 0.356 0.0001 0.450 0.132 0.870 0.917
----------------------------------------------------------------------
Regression Results
======================================================
(Intercept) complaints privileges learning
------------------------------------------------------
Estimate 11.258 0.682 -0.103 0.238
Std. Error 7.318 0.129 0.129 0.139
t value 1.538 5.296 -0.799 1.707
Pr(> | t| ) 0.136 0.00002 0.432 0.100
------------------------------------------------------
Regression Results
=================================================
(Intercept) learning critical advance
-------------------------------------------------
Estimate -7.476 0.164 -0.001 -0.062
Std. Error 3.570 0.053 0.044 0.042
z value -2.094 3.079 -0.013 -1.472
Pr(> | z| ) 0.036 0.002 0.990 0.141
-------------------------------------------------
>
EDIT after the OPs clarification:
options(stringsAsFactors = F, scipen=999)
model1 <- data.frame(t(coef(summary(linear.1))))
model1$stats <- rownames(model1)
model2 <- data.frame(t(coef(summary(linear.2))))
model2$stats <- rownames(model2)
model3 <- data.frame(t(coef(summary(probit.model))))
model3$stats <- rownames(model3)
x <- dplyr::bind_rows(model1 = model1, model2=model2,
model3 = model3, .id = "Name")
x <- x[,c(1,8,2:7,9 )] #rearranging the terms
stargazer(x, type="text", summary=F)
Output:
=========================================================================================
Name stats X.Intercept. complaints privileges learning raises critical advance
-----------------------------------------------------------------------------------------
1 model1 Estimate 11.011 0.692 -0.104 0.249 -0.033 0.015
2 model1 Std. Error 11.704 0.149 0.135 0.160 0.202 0.147
3 model1 t value 0.941 4.649 -0.769 1.560 -0.165 0.105
4 model1 Pr(> | t| ) 0.356 0.0001 0.450 0.132 0.870 0.917
5 model2 Estimate 11.258 0.682 -0.103 0.238
6 model2 Std. Error 7.318 0.129 0.129 0.139
7 model2 t value 1.538 5.296 -0.799 1.707
8 model2 Pr(> | t| ) 0.136 0.00002 0.432 0.100
9 model3 Estimate -7.476 0.164 -0.001 -0.062
10 model3 Std. Error 3.570 0.053 0.044 0.042
11 model3 z value -2.094 3.079 -0.013 -1.472
12 model3 Pr(> | z| ) 0.036 0.002 0.990 0.141
-----------------------------------------------------------------------------------------