R Markdown
library(wooldridge)
library(rmarkdown)
data("bwght")
head(bwght)
## faminc cigtax cigprice bwght fatheduc motheduc parity male white cigs
## 1 13.5 16.5 122.3 109 12 12 1 1 1 0
## 2 7.5 16.5 122.3 133 6 12 2 1 0 0
## 3 0.5 16.5 122.3 129 NA 12 2 0 0 0
## 4 15.5 16.5 122.3 126 12 12 2 1 0 0
## 5 27.5 16.5 122.3 134 14 12 2 1 1 0
## 6 7.5 16.5 122.3 118 12 14 6 1 0 0
## lbwght bwghtlbs packs lfaminc
## 1 4.691348 6.8125 0 2.6026897
## 2 4.890349 8.3125 0 2.0149031
## 3 4.859812 8.0625 0 -0.6931472
## 4 4.836282 7.8750 0 2.7408400
## 5 4.897840 8.3750 0 3.3141861
## 6 4.770685 7.3750 0 2.0149031
help(bwght)
## starting httpd help server ... done
ilkreg <- lm(bwght~ cigs,data = bwght)
ikincireg<- lm(bwght~ cigs+faminc,data = bwght)
library(stargazer)
##
## Please cite as:
## Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.
## R package version 5.2.2. https://CRAN.R-project.org/package=stargazer
stargazer(list(ilkreg,ikincireg),type = "text")
##
## =====================================================================
## Dependent variable:
## -------------------------------------------------
## bwght
## (1) (2)
## ---------------------------------------------------------------------
## cigs -0.514*** -0.463***
## (0.090) (0.092)
##
## faminc 0.093***
## (0.029)
##
## Constant 119.772*** 116.974***
## (0.572) (1.049)
##
## ---------------------------------------------------------------------
## Observations 1,388 1,388
## R2 0.023 0.030
## Adjusted R2 0.022 0.028
## Residual Std. Error 20.129 (df = 1386) 20.063 (df = 1385)
## F Statistic 32.235*** (df = 1; 1386) 21.274*** (df = 2; 1385)
## =====================================================================
## Note: *p<0.1; **p<0.05; ***p<0.01
data("discrim")
head(discrim)
## psoda pfries pentree wagest nmgrs nregs hrsopen emp psoda2 pfries2 pentree2
## 1 1.12 1.06 1.02 4.25 3 5 16.0 27.5 1.11 1.11 1.05
## 2 1.06 0.91 0.95 4.75 3 3 16.5 21.5 1.05 0.89 0.95
## 3 1.06 0.91 0.98 4.25 3 5 18.0 30.0 1.05 0.94 0.98
## 4 1.12 1.02 1.06 5.00 4 5 16.0 27.5 1.15 1.05 1.05
## 5 1.12 NA 0.49 5.00 3 3 16.0 5.0 1.04 1.01 0.58
## 6 1.06 0.95 1.01 4.25 4 4 15.0 17.5 1.05 0.94 1.00
## wagest2 nmgrs2 nregs2 hrsopen2 emp2 compown chain density crmrte state
## 1 5.05 5 5 15.0 27.0 1 3 4030 0.0528866 1
## 2 5.05 4 3 17.5 24.5 0 1 4030 0.0528866 1
## 3 5.05 4 5 17.5 25.0 0 1 11400 0.0360003 1
## 4 5.05 4 5 16.0 NA 0 3 8345 0.0484232 1
## 5 5.05 3 3 16.0 12.0 0 1 720 0.0615890 1
## 6 5.05 3 4 15.0 28.0 0 1 4424 0.0334823 1
## prpblck prppov prpncar hseval nstores income county lpsoda
## 1 0.1711542 0.0365789 0.0788428 148300 3 44534 18 0.11332869
## 2 0.1711542 0.0365789 0.0788428 148300 3 44534 18 0.05826885
## 3 0.0473602 0.0879072 0.2694298 169200 3 41164 12 0.05826885
## 4 0.0528394 0.0591227 0.1366903 171600 3 50366 10 0.11332869
## 5 0.0344800 0.0254145 0.0738020 249100 1 72287 10 0.11332869
## 6 0.0591327 0.0835001 0.1151341 148000 2 44515 18 0.05826885
## lpfries lhseval lincome ldensity NJ BK KFC RR
## 1 0.05826885 11.90699 10.70401 8.301521 1 0 0 1
## 2 -0.09431065 11.90699 10.70401 8.301521 1 1 0 0
## 3 -0.09431065 12.03884 10.62532 9.341369 1 1 0 0
## 4 0.01980261 12.05292 10.82707 9.029418 1 0 0 1
## 5 NA 12.42561 11.18840 6.579251 1 1 0 0
## 6 -0.05129331 11.90497 10.70358 8.394799 1 1 0 0
help(discrim)
mean(discrim$prpblck)
## [1] NA
sd(discrim$prpblck)
## [1] NA
mean(discrim$income)
## [1] NA
sd(discrim$income)
## [1] NA
sum(is.na(discrim$prpblck))
## [1] 1
sum(is.na(discrim$income))
## [1] 1
mean(discrim$prpblck,na.rm = TRUE)
## [1] 0.1134864
sd(discrim$prpblck,na.rm = TRUE)
## [1] 0.1824165
mean(discrim$income, na.rm = TRUE)
## [1] 47053.78
sd(discrim$income, na.rm = TRUE)
## [1] 13179.29
library(vtable)
## Zorunlu paket yükleniyor: kableExtra
sumtable(discrim, summ=c('notNA(x)', 'countNA(x)', 'mean(x)','sd(x)'),out='return')
## Variable NotNA CountNA Mean Sd
## 1 psoda 402 8 1.045 0.089
## 2 pfries 393 17 0.922 0.106
## 3 pentree 398 12 1.322 0.643
## 4 wagest 390 20 4.616 0.347
## 5 nmgrs 404 6 3.42 1.018
## 6 nregs 388 22 3.608 1.244
## 7 hrsopen 410 0 14.439 2.81
## 8 emp 404 6 17.622 9.423
## 9 psoda2 388 22 1.045 0.094
## 10 pfries2 382 28 0.941 0.109
## 11 pentree2 386 24 1.354 0.65
## 12 wagest2 389 21 4.996 0.253
## 13 nmgrs2 404 6 3.484 1.14
## 14 nregs2 388 22 3.608 1.244
## 15 hrsopen2 399 11 14.466 2.752
## 16 emp2 397 13 17.567 8.607
## 17 compown 410 0 0.344 0.476
## 18 chain 410 0 2.117 1.11
## 19 density 409 1 4561.803 5132.408
## 20 crmrte 409 1 0.053 0.047
## 21 state 410 0 1.193 0.395
## 22 prpblck 409 1 0.113 0.182
## 23 prppov 409 1 0.071 0.067
## 24 prpncar 409 1 0.115 0.117
## 25 hseval 409 1 147399.267 56070.468
## 26 nstores 410 0 3.139 1.809
## 27 income 409 1 47053.785 13179.286
## 28 county 410 0 13.659 8.045
## 29 lpsoda 402 8 0.04 0.085
## 30 lpfries 393 17 -0.088 0.115
## 31 lhseval 409 1 11.829 0.389
## 32 lincome 409 1 10.72 0.284
## 33 ldensity 409 1 7.959 0.996
## 34 NJ 410 0 0.807 0.395
## 35 BK 410 0 0.417 0.494
## 36 KFC 410 0 0.195 0.397
## 37 RR 410 0 0.241 0.428
discrimreg <- lm(psoda~prpblck+income, data = discrim)
summary(discrimreg)
##
## Call:
## lm(formula = psoda ~ prpblck + income, data = discrim)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.29401 -0.05242 0.00333 0.04231 0.44322
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.563e-01 1.899e-02 50.354 < 2e-16 ***
## prpblck 1.150e-01 2.600e-02 4.423 1.26e-05 ***
## income 1.603e-06 3.618e-07 4.430 1.22e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.08611 on 398 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.06422, Adjusted R-squared: 0.05952
## F-statistic: 13.66 on 2 and 398 DF, p-value: 1.835e-06
basitdiscrimreg <- lm(psoda~prpblck, data = discrim)
summary(basitdiscrimreg)
##
## Call:
## lm(formula = psoda ~ prpblck, data = discrim)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.30884 -0.05963 0.01135 0.03206 0.44840
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.03740 0.00519 199.87 < 2e-16 ***
## prpblck 0.06493 0.02396 2.71 0.00702 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.0881 on 399 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.01808, Adjusted R-squared: 0.01561
## F-statistic: 7.345 on 1 and 399 DF, p-value: 0.007015
logdiscrimreg <- lm(log(psoda)~prpblck+log(income), data = discrim)
summary(logdiscrimreg)
##
## Call:
## lm(formula = log(psoda) ~ prpblck + log(income), data = discrim)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.33563 -0.04695 0.00658 0.04334 0.35413
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.79377 0.17943 -4.424 1.25e-05 ***
## prpblck 0.12158 0.02575 4.722 3.24e-06 ***
## log(income) 0.07651 0.01660 4.610 5.43e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.0821 on 398 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.06809, Adjusted R-squared: 0.06341
## F-statistic: 14.54 on 2 and 398 DF, p-value: 8.039e-07
logdiscrimregprpov <- lm(log(psoda)~prpblck+log(income)+prppov, data = discrim)
summary(logdiscrimregprpov)
##
## Call:
## lm(formula = log(psoda) ~ prpblck + log(income) + prppov, data = discrim)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.32218 -0.04648 0.00651 0.04272 0.35622
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.46333 0.29371 -4.982 9.4e-07 ***
## prpblck 0.07281 0.03068 2.373 0.0181 *
## log(income) 0.13696 0.02676 5.119 4.8e-07 ***
## prppov 0.38036 0.13279 2.864 0.0044 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.08137 on 397 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.08696, Adjusted R-squared: 0.08006
## F-statistic: 12.6 on 3 and 397 DF, p-value: 6.917e-08
cor(log(discrim$income), discrim$prppov, use = "complete.obs")
## [1] -0.838467
data("meapsingle")
paged_table(meapsingle)
basitreg3<- lm(math4~pctsgle, data = meapsingle)
summary(basitreg3)
##
## Call:
## lm(formula = math4 ~ pctsgle, data = meapsingle)
##
## Residuals:
## Min 1Q Median 3Q Max
## -47.791 -8.310 1.600 8.092 50.317
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 96.77043 1.59680 60.60 <2e-16 ***
## pctsgle -0.83288 0.07068 -11.78 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 12.48 on 227 degrees of freedom
## Multiple R-squared: 0.3795, Adjusted R-squared: 0.3768
## F-statistic: 138.9 on 1 and 227 DF, p-value: < 2.2e-16
coklureg3<- lm(math4~pctsgle+lmedinc+free, data = meapsingle)
summary(coklureg3)
##
## Call:
## lm(formula = math4 ~ pctsgle + lmedinc + free, data = meapsingle)
##
## Residuals:
## Min 1Q Median 3Q Max
## -34.919 -7.195 0.931 7.313 50.152
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 51.72322 58.47814 0.884 0.377
## pctsgle -0.19965 0.15872 -1.258 0.210
## lmedinc 3.56013 5.04170 0.706 0.481
## free -0.39642 0.07035 -5.635 5.2e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.7 on 225 degrees of freedom
## Multiple R-squared: 0.4598, Adjusted R-squared: 0.4526
## F-statistic: 63.85 on 3 and 225 DF, p-value: < 2.2e-16
cor(meapsingle$free,meapsingle$lmedinc)
## [1] -0.7469703
library(car)
## Zorunlu paket yükleniyor: carData
vif(coklureg3)
## pctsgle lmedinc free
## 5.740981 4.118812 3.188079