hw4
2024-10-22
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
# Load necessary libraries
library(wooldridge)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# Load the DISCRIM dataset from the wooldridge package
data("discrim", package = "wooldridge")
# View the first few rows of the dataset to understand the variables
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# Calculate the mean and standard deviation for prpblck and income
summary_stats <- discrim %>%
summarise(mean_prpblck = mean(prpblck),
sd_prpblck = sd(prpblck),
mean_income = mean(income),
sd_income = sd(income))
print(summary_stats)## mean_prpblck sd_prpblck mean_income sd_income
## 1 NA NA NA NA# Run the OLS regression for psoda on prpblck and income
model <- lm(psoda ~ prpblck + income, data = discrim)
# Print the summary of the model
summary(model)##
## 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# Run the simple regression of psoda on prpblck
simple_model <- lm(psoda ~ prpblck, data = discrim)
# Print the summary of the simple model
summary(simple_model)##
## 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# Run the log-log model
log_model <- lm(log(psoda) ~ prpblck + log(income), data = discrim)
# Print the summary of the log-log model
summary(log_model)##
## 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# Add prppov to the model
model_with_prppov <- lm(log(psoda) ~ prpblck + log(income) + prppov, data = discrim)
# Print the summary of the new model
summary(model_with_prppov)##
## 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# Calculate the correlation between log(income) and prppov
cor(log(discrim$income), discrim$prppov)## [1] NA# Check for multicollinearity using VIF
library(car)## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recodevif(model_with_prppov)## prpblck log(income) prppov
## 1.922160 3.518721 4.915220Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.