remove(list = ls())
library(visdat)
library(stargazer)
Please cite as: Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables. R package version 5.2.3. https://CRAN.R-project.org/package=stargazer Day 8
library(help = "datasets")
?Boston No documentation for 'Boston' in specified packages and libraries:
you could try '??Boston'library(MASS)
library(stargazer)
library(visdat)
data("Boston") clean_df <- Boston
vis_dat(clean_df)
stargazer(clean_df, type = "text",
covariate.labels = c("crim", "zn", "nox", "rm", "age", "dis", "rad", "tax", "lstat", "medv"))
=============================================
Statistic N Mean St. Dev. Min Max
---------------------------------------------
crim 506 3.614 8.602 0.006 88.976
zn 506 11.364 23.322 0.000 100.000
nox 506 11.137 6.860 0.460 27.740
rm 506 0.069 0.254 0 1
age 506 0.555 0.116 0.385 0.871
dis 506 6.285 0.703 3.561 8.780
rad 506 68.575 28.149 2.900 100.000
tax 506 3.795 2.106 1.130 12.126
lstat 506 9.549 8.707 1 24
medv 506 408.237 168.537 187 711
ptratio 506 18.456 2.165 12.600 22.000
black 506 356.674 91.295 0.320 396.900
lstat 506 12.653 7.141 1.730 37.970
medv 506 22.533 9.197 5.000 50.000
---------------------------------------------clean_df <- Boston
if ("CONT" %in% names(clean_df)) {
clean_df$CONT <- as.numeric(clean_df$CONT)
}
clean_df <- clean_df[, !(names(clean_df) %in% c("INTG", "CFMG"))]
str(clean_df)'data.frame': 506 obs. of 14 variables:
$ crim : num 0.00632 0.02731 0.02729 0.03237 0.06905 ...
$ zn : num 18 0 0 0 0 0 12.5 12.5 12.5 12.5 ...
$ indus : num 2.31 7.07 7.07 2.18 2.18 2.18 7.87 7.87 7.87 7.87 ...
$ chas : int 0 0 0 0 0 0 0 0 0 0 ...
$ nox : num 0.538 0.469 0.469 0.458 0.458 0.458 0.524 0.524 0.524 0.524 ...
$ rm : num 6.58 6.42 7.18 7 7.15 ...
$ age : num 65.2 78.9 61.1 45.8 54.2 58.7 66.6 96.1 100 85.9 ...
$ dis : num 4.09 4.97 4.97 6.06 6.06 ...
$ rad : int 1 2 2 3 3 3 5 5 5 5 ...
$ tax : num 296 242 242 222 222 222 311 311 311 311 ...
$ ptratio: num 15.3 17.8 17.8 18.7 18.7 18.7 15.2 15.2 15.2 15.2 ...
$ black : num 397 397 393 395 397 ...
$ lstat : num 4.98 9.14 4.03 2.94 5.33 ...
$ medv : num 24 21.6 34.7 33.4 36.2 28.7 22.9 27.1 16.5 18.9 ...clean_df <- Boston %>%
na.omit()
names(clean_df) [1] "crim" "zn" "indus" "chas" "nox" "rm" "age"
[8] "dis" "rad" "tax" "ptratio" "black" "lstat" "medv" fullreg <- lm(crim ~ ., data = clean_df)
stepAIC(fullreg, direction = "backward")Start: AIC=1898.56
crim ~ zn + indus + chas + nox + rm + age + dis + rad + tax +
ptratio + black + lstat + medv
Df Sum of Sq RSS AIC
- age 1 0.27 20400 1896.6
- chas 1 16.71 20417 1897.0
- rm 1 20.43 20420 1897.1
- tax 1 22.29 20422 1897.1
- indus 1 24.30 20424 1897.2
<none> 20400 1898.6
- ptratio 1 87.65 20488 1898.7
- lstat 1 115.18 20515 1899.4
- nox 1 158.47 20558 1900.5
- black 1 174.58 20574 1900.9
- zn 1 237.70 20638 1902.4
- medv 1 447.85 20848 1907.5
- dis 1 508.77 20909 1909.0
- rad 1 1850.44 22250 1940.5
Step: AIC=1896.56
crim ~ zn + indus + chas + nox + rm + dis + rad + tax + ptratio +
black + lstat + medv
Df Sum of Sq RSS AIC
- chas 1 16.54 20417 1895.0
- rm 1 22.14 20422 1895.1
- tax 1 22.16 20422 1895.1
- indus 1 24.30 20424 1895.2
<none> 20400 1896.6
- ptratio 1 87.41 20488 1896.7
- lstat 1 131.43 20532 1897.8
- nox 1 166.37 20567 1898.7
- black 1 174.40 20575 1898.9
- zn 1 239.21 20639 1900.5
- medv 1 447.81 20848 1905.5
- dis 1 559.06 20959 1908.2
- rad 1 1857.98 22258 1938.7
Step: AIC=1894.97
crim ~ zn + indus + nox + rm + dis + rad + tax + ptratio + black +
lstat + medv
Df Sum of Sq RSS AIC
- tax 1 18.81 20436 1893.4
- rm 1 22.76 20440 1893.5
- indus 1 28.82 20446 1893.7
<none> 20417 1895.0
- ptratio 1 84.57 20501 1895.1
- lstat 1 129.63 20546 1896.2
- nox 1 175.96 20593 1897.3
- black 1 178.37 20595 1897.4
- zn 1 241.26 20658 1898.9
- medv 1 483.38 20900 1904.8
- dis 1 563.37 20980 1906.8
- rad 1 1842.82 22260 1936.7
Step: AIC=1893.44
crim ~ zn + indus + nox + rm + dis + rad + ptratio + black +
lstat + medv
Df Sum of Sq RSS AIC
- rm 1 23.0 20459 1892.0
- indus 1 64.4 20500 1893.0
<none> 20436 1893.4
- ptratio 1 87.4 20523 1893.6
- lstat 1 137.9 20574 1894.8
- black 1 178.1 20614 1895.8
- nox 1 181.9 20617 1895.9
- zn 1 222.9 20658 1896.9
- medv 1 465.3 20901 1902.8
- dis 1 556.9 20992 1905.0
- rad 1 4693.4 25129 1996.0
Step: AIC=1892.01
crim ~ zn + indus + nox + dis + rad + ptratio + black + lstat +
medv
Df Sum of Sq RSS AIC
- indus 1 74.0 20533 1891.8
<none> 20459 1892.0
- ptratio 1 88.2 20547 1892.2
- lstat 1 118.9 20577 1892.9
- nox 1 176.9 20636 1894.4
- black 1 202.4 20661 1895.0
- zn 1 233.9 20692 1895.8
- medv 1 458.7 20917 1901.2
- dis 1 572.2 21031 1904.0
- rad 1 4811.3 25270 1996.9
Step: AIC=1891.83
crim ~ zn + nox + dis + rad + ptratio + black + lstat + medv
Df Sum of Sq RSS AIC
<none> 20533 1891.8
- lstat 1 104.7 20637 1892.4
- ptratio 1 119.0 20652 1892.8
- black 1 198.4 20731 1894.7
- zn 1 239.6 20772 1895.7
- nox 1 296.6 20829 1897.1
- medv 1 430.2 20963 1900.3
- dis 1 507.8 21040 1902.2
- rad 1 4739.5 25272 1994.9
Call:
lm(formula = crim ~ zn + nox + dis + rad + ptratio + black +
lstat + medv, data = clean_df)
Coefficients:
(Intercept) zn nox dis rad ptratio
19.683128 0.043293 -12.753708 -0.918318 0.532617 -0.310541
black lstat medv
-0.007922 0.110173 -0.174207