```{r}
library(readxl)
pols_data <- read_excel("pols_data.xlsx",sheet = 1)
pols_data <- read_excel("pols_data_cov_data.xlsx",sheet = 1)
```

```{r}
library(ggplot2)

pols_reg <- lm(Score ~ PerStudentExpend + PerStudentExpend*DemControl + Income + PercBlack + PercHisp + PercOver18 + PercBach + Choice + RTW, data = pols_data)
summary(pols_reg)

meanpse <- mean(pols_data$PerStudentExpend)
meanDC <- mean(pols_data$DemControl)
meanInc <- mean(pols_data$Income)
meanpB <- mean(pols_data$PercBlack)
meanpH <- mean(pols_data$PercHisp)
meanp18 <- mean(pols_data$PercOver18)
meanpBach <- mean(pols_data$PerBach)
meanChoice <- mean(pols_data$Choice)
meanRTW <- mean(pols_data$RTW)

x <- c(1, meanpse, meanDC, meanInc, meanpB, meanpH, meanp18, meanpBach, meanChoice, meanRTW, meanDC*meanpse)

coefficients <- coef(pols_reg)


# Initialize the sum
total <- 0

# For loop to calculate the sum
for (i in 1:length(x)) {
  total <- total + (coefficients[i] * x[i])
}

# Print the result
print(total)
coefficients[11]

summary(pols_reg)

#cor(pols_data)

mean(pols_data$Score)

residuals <- resid(pols_reg)

hist(residuals, main = "Figure 1: Regression Residuals", 
breaks = 20)

plot(pols_data$PerStudentExpend , pols_data$Score, main = "Figure 1: Scatterplot with Line(s) of Best Fit", 
     xlab = "Per Student Spending", ylab = "Reading Test Score", pch = 19, col = "blue")

# Fit linear model and add line of best fit
fit <- lm(pols_data$Score ~ pols_data$PerStudentExpend)
lm(Score ~ PerStudentExpend + PerStudentExpend*DemControl + Income + PercBlack + PercHisp + PercOver18 + PercBach + Choice + RTW, data = pols_data)
  
abline(fit, col = "red", lwd = 2)
#abline(a = 265, b = -0.5, col = "green", lwd = 2, lty = 2)
# Add the line with intercept 265 and slope -0.5
abline(a = 262.5235, b = -2.047e-04, col = "green", lwd = 2, lty = 2)


```
```{r}
HW5_reg <- lm(Score ~ PerStudentExpend + Income, data = pols_data)
summary(HW5_reg)


library(summarytools)
summary(pols_data$Score)
summary(pols_data$PerStudentExpend)
summary(pols_data$Income)
summary(pols_data$PercBlack)
summary(pols_data$PercHisp)
summary(pols_data$PercOver18)
summary(pols_data$PercBach)
summary(pols_data$Choice)
summary(pols_data$RTW)
summary(pols_data$DemControl)


dfSummary(pols_data$Score)
dfSummary(pols_data$PerStudentExpend)
dfSummary(pols_data$Income)
dfSummary(pols_data$PercBlack)
dfSummary(pols_data$PercHisp)
dfSummary(pols_data$PercOver18)
dfSummary(pols_data$PercBach)
dfSummary(pols_data$Choice)
dfSummary(pols_data$RTW)
dfSummary(pols_data$DemControl)


```

```{r}
plot(pols_data$PerStudentExpend, pols_data$Score, main = "Scatterplot with Line of Best Fit", 
     xlab = "Per Student Spending", ylab = "Test Score", pch = 19, col = "blue")

# Fit linear model and add line of best fit
fit <- lm(pols_data$Score ~ pols_data$PerStudentExpend)
#lm(Score ~ PerStudentExpend + Income, data = pols_data)
  
abline(fit, col = "red", lwd = 2)
```