Advanced Quantitative Methods - Analysis of Correlates of School Performance

# 1. Explore the use of logarithms of the dependent variable. calschool$log_dependent variable <- log(calschool$dependent variable) regression_log <- lm(log_dependent variable ~ independent variable(s), data = calschool) summary(regression_log) # 2. Convert a continuous variable into a nominal / ordinal variables quantile(calschool$ell, 0.75, na.rm = TRUE) # find the value of ell at 75%, we set this value as the cutoff. calschool$ell_cat[calschool$ell < 50.25] <- 0 calschool$ell_cat[calschool$ell >= 50.25] <- 1 calschool$ell_cat <- factor(calschool$ell_cat) # make ell_cat as a dummy variable that only has value 1 and 0. # Create a dummy variable for mealcat calschool$high_mealcat <- ifelse(calschool$mealcat == 3, 1, 0) calschool$med_mealcat <- ifelse(calschool$mealcat == 2, 1, 0) calschool$low_mealcat <- ifelse(calschool$mealcat == 1, 1, 0) # 3. Create an interaction variable of dummy variables, just multiply these two dummy variable ell_cat*high_mealcat. regression_interaction_high <- lm(dependent variable ~ ell_cat*high_mealcat, data = calschool) summary(regression_interaction_high) #4 Visualization extension: For students who would like to experiment with improved visualizations #First, we will need to install some new packages: install.packages("stargazer") install.packages("lmtest") install.packages("corrplot") 12 install.packages("sjPlot") library(stargazer) library(lmtest) library(corrplot) library(sjPlot) #Then, run this code: # Correlation Matrix Visualization corrmatrix <- cor(calschool, use = "complete.obs") View(corrmatrix) corrplot(corrmatrix, method="circle") # correlation_table_calschool is the name of the correlation matrix we created above corrplot.mixed(corrmatrix, number.cex = 0.8, tl.cex = 0.6) #number.cex changes the size of the number fonts. tl.cex changes the size of the labels corrplot(corrmatrix, type="lower") #Here is some code to improve the formatting of your regression results #Here is the unadjusted regression model (first model that only has independent variable) output using the `sjPlot` package. sjt.lm(regression_1, show.header = TRUE, p.numeric = FALSE, show.se = TRUE, show.fstat = TRUE, string.est = "Estimate", string.ci = "Conf. Int.", string.dv = "Unadjusted Regression Model", depvar.labels = c(" % Free Meals"), pred.labels = c("School wide Academic Performance")) #Here is the adjusted regression model output using the `sjPlot` package. sjt.lm(regression_final, show.header = TRUE, p.numeric = FALSE, show.se = TRUE, digits.se = 3, show.fstat = TRUE, string.est = "Estimate", 13 string.ci = "Conf. Int.", string.dv = "Adjusted Regression Model", depvar.labels = c("% Free Meals"), pred.labels = c("School Wide Academic Performance", "% English learners", "% teachers with full credentials")) #Showing the unadjusted (first model) and adjusted regression (final model) results side by side #stargazer package stargazer(regression_1, regression_final, title="Regression Results", dep.var.labels=c("% Free Meals"), type="text") #sjPlot package: sjt.lm(regression_1, regression_final, show.header = TRUE, p.numeric = FALSE, show.se = TRUE, digits.se = 3, show.fstat = TRUE, group.pred = FALSE, string.est = "Estimate", string.ci = "Conf. Int.", string.dv = "Regression Results", depvar.labels = c("Unadjusted Regression Model", "Adjusted Regression Model"), pred.labels = c("School Wide Academic Performance", "% English Learners", "% teachers with full credentials"))