Exercise 1

install.packages("wooldridge")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)

library(wooldridge)

C2. Use the data in BWGHT to answer this question.

1. How many women are in the sample, and how many report smoking during pregnancy?

   # Load the wooldridge package
   library(wooldridge)
   
   # Access BWGHT dataset
   data("bwght")
   
   # Total women in the sample
   total_women <- nrow(bwght)
   
   # Women who smoked during pregnancy
   smokers <- sum(bwght$cigs > 0, na.rm = TRUE)
   
   total_women

   ## [1] 1388

   smokers

   ## [1] 212

2. What is the average number of cigarettes smoked per day?

   # Average number of cigarettes smoked per day
   avg_cigarettes <- mean(bwght$cigs, na.rm = TRUE)
   avg_cigarettes

   ## [1] 2.087176

3. Average number of cigarettes smoked among pregnant women

   # Average number of cigarettes smoked per day among pregnant women who smoked
   pregnant_smokers <- bwght[bwght$cigs > 0, ]
   avg_cigs_pregnancy <- mean(pregnant_smokers$cigs, na.rm = TRUE)
   avg_cigs_pregnancy

   ## [1] 13.66509

4. Average of father’s education level (fatheduc)

   # Average father's education level
   avg_fatheduc <- mean(bwght$fatheduc, na.rm = TRUE)
   avg_fatheduc

   ## [1] 13.18624

5. Average family income and its standard deviation

   # Average family income and standard deviation
   avg_faminc <- mean(bwght$faminc, na.rm = TRUE)
   std_faminc <- sd(bwght$faminc, na.rm = TRUE)
   
   avg_faminc

   ## [1] 29.02666

   std_faminc

   ## [1] 18.73928

C3. Analysis for MEAP01 Dataset

1. Find the largest and smallest values of math4

   # Access MEAP01 dataset
   data("meap01")
   
   # Largest and smallest values of math4
   max_math4 <- max(meap01$math4, na.rm = TRUE)
   min_math4 <- min(meap01$math4, na.rm = TRUE)
   
   max_math4

   ## [1] 100

   min_math4

   ## [1] 0

2. How many schools have a perfect pass rate on the math test?

   # Number of schools with a perfect pass rate (math4 == 100)
   perfect_pass_rate_schools <- sum(meap01$math4 == 100, na.rm = TRUE)
   total_schools <- nrow(meap01)
   
   # Percentage of schools with a perfect pass rate
   percentage_perfect <- (perfect_pass_rate_schools / total_schools) * 100
   
   perfect_pass_rate_schools

   ## [1] 38

   percentage_perfect

   ## [1] 2.084476

3. How many schools have a math pass rate of exactly 50%?

   # Number of schools with math pass rate of exactly 50%
   exact_50_percent <- sum(meap01$math4 == 50, na.rm = TRUE)
   exact_50_percent

   ## [1] 17

4. Compare average pass rates for math and reading scores

   # Average pass rate for math and reading
   avg_math4 <- mean(meap01$math4, na.rm = TRUE)
   avg_read4 <- mean(meap01$read4, na.rm = TRUE)
   
   avg_math4

   ## [1] 71.909

   avg_read4

   ## [1] 60.06188

5. Find the correlation between math4 and read4

   # Correlation between math4 and read4
   correlation <- cor(meap01$math4, meap01$read4, use = "complete.obs")
   correlation

   ## [1] 0.8427281

6. Find the average of expenditure per pupil (exppp) and its standard deviation

   # Average and standard deviation of expenditure per pupil (exppp)
   avg_exppp <- mean(meap01$exppp, na.rm = TRUE)
   std_exppp <- sd(meap01$exppp, na.rm = TRUE)
   
   avg_exppp

   ## [1] 5194.865

   std_exppp

   ## [1] 1091.89

7. Compare School A and School B’s spending

   # School A spends $6,000 and School B spends $5,500 per student
   school_A <- 6000
   school_B <- 5500
   
   # Percentage difference calculation
   percentage_difference <- 100 * (log(school_A) - log(school_B))
   
   percentage_difference

   ## [1] 8.701138