Project 1: Mean, Median, and Standard Deviation

loading the dataset

# Import dataset
intimidation_data <- read.csv("intimidation.csv", header = TRUE)
head(intimidation_data)

This calculates mean, median, and standard deviation for each variable using all students.

# Calculate mean, median, and standard deviation for interval/ratio variables
final_stats <- data.frame(
  Variable = "Final",
  Mean = mean(intimidation_data$Final, na.rm = TRUE),
  Median = median(intimidation_data$Final, na.rm = TRUE),
  SD = sd(intimidation_data$Final, na.rm = TRUE)
)

# IntimBF scores  
intimbf_stats <- data.frame(
  Variable = "IntimBF",
  Mean = mean(intimidation_data$IntimBF, na.rm = TRUE),
  Median = median(intimidation_data$IntimBF, na.rm = TRUE),
  SD = sd(intimidation_data$IntimBF, na.rm = TRUE)
)

# IntimAF scores
intimaf_stats <- data.frame(
  Variable = "IntimAF", 
  Mean = mean(intimidation_data$IntimAF, na.rm = TRUE),
  Median = median(intimidation_data$IntimAF, na.rm = TRUE),
  SD = sd(intimidation_data$IntimAF, na.rm = TRUE)
)

#  results
full_dataset_stats <- rbind(final_stats, intimbf_stats, intimaf_stats)
kable(full_dataset_stats, digits = 3)

Variable	Mean	Median	SD
Final	79.388	80.150	9.416
IntimBF	6.991	6.990	0.329
IntimAF	3.934	3.935	0.267

These three variable show the average, middle value, and spread out the data is. Final exam scores vary the most. IntimAF scores are most similar to each other.

This separates students by year level and calculates the same statistics for each group.

# Calculate mean, median, and standard deviation by Year
# Freshman (FR)
fr_data <- filter(intimidation_data, Year == "FR")
fr_stats <- data.frame(
  Year = "FR",
  Variable = c("Final", "IntimBF", "IntimAF"),
  Mean = c(mean(fr_data$Final, na.rm = TRUE),
           mean(fr_data$IntimBF, na.rm = TRUE), 
           mean(fr_data$IntimAF, na.rm = TRUE)),
  Median = c(median(fr_data$Final, na.rm = TRUE),
             median(fr_data$IntimBF, na.rm = TRUE),
             median(fr_data$IntimAF, na.rm = TRUE)),
  SD = c(sd(fr_data$Final, na.rm = TRUE),
         sd(fr_data$IntimBF, na.rm = TRUE),
         sd(fr_data$IntimAF, na.rm = TRUE))
)

# Sophomore (SO)
so_data <- filter(intimidation_data, Year == "SO")
so_stats <- data.frame(
  Year = "SO",
  Variable = c("Final", "IntimBF", "IntimAF"),
  Mean = c(mean(so_data$Final, na.rm = TRUE),
           mean(so_data$IntimBF, na.rm = TRUE),
           mean(so_data$IntimAF, na.rm = TRUE)),
  Median = c(median(so_data$Final, na.rm = TRUE),
             median(so_data$IntimBF, na.rm = TRUE),
             median(so_data$IntimAF, na.rm = TRUE)),
  SD = c(sd(so_data$Final, na.rm = TRUE),
         sd(so_data$IntimBF, na.rm = TRUE),
         sd(so_data$IntimAF, na.rm = TRUE))
)

# Junior (JR)
jr_data <- filter(intimidation_data, Year == "JR")
jr_stats <- data.frame(
  Year = "JR",
  Variable = c("Final", "IntimBF", "IntimAF"),
  Mean = c(mean(jr_data$Final, na.rm = TRUE),
           mean(jr_data$IntimBF, na.rm = TRUE),
           mean(jr_data$IntimAF, na.rm = TRUE)),
  Median = c(median(jr_data$Final, na.rm = TRUE),
             median(jr_data$IntimBF, na.rm = TRUE),
             median(jr_data$IntimAF, na.rm = TRUE)),
  SD = c(sd(jr_data$Final, na.rm = TRUE),
         sd(jr_data$IntimBF, na.rm = TRUE),
         sd(jr_data$IntimAF, na.rm = TRUE))
)

# Senior (SR) - if present in data
sr_data <- filter(intimidation_data, Year == "SR")
if(nrow(sr_data) > 0) {
  sr_stats <- data.frame(
    Year = "SR",
    Variable = c("Final", "IntimBF", "IntimAF"),
    Mean = c(mean(sr_data$Final, na.rm = TRUE),
             mean(sr_data$IntimBF, na.rm = TRUE),
             mean(sr_data$IntimAF, na.rm = TRUE)),
    Median = c(median(sr_data$Final, na.rm = TRUE),
               median(sr_data$IntimBF, na.rm = TRUE),
               median(sr_data$IntimAF, na.rm = TRUE)),
    SD = c(sd(sr_data$Final, na.rm = TRUE),
           sd(sr_data$IntimBF, na.rm = TRUE),
           sd(sr_data$IntimAF, na.rm = TRUE))
  )
  
  by_year_stats <- rbind(fr_stats, so_stats, jr_stats, sr_stats)
} else {
  by_year_stats <- rbind(fr_stats, so_stats, jr_stats)
}

kable(by_year_stats, digits = 3)

Year	Variable	Mean	Median	SD
FR	Final	75.362	74.835	7.099
FR	IntimBF	7.122	7.150	0.277
FR	IntimAF	4.117	4.110	0.228
SO	Final	84.021	84.050	10.708
SO	IntimBF	6.975	6.995	0.281
SO	IntimAF	3.978	3.975	0.203
JR	Final	77.356	78.025	8.941
JR	IntimBF	6.989	7.010	0.290
JR	IntimAF	3.872	3.890	0.256
SR	Final	80.522	77.950	8.705
SR	IntimBF	7.118	6.950	0.389
SR	IntimAF	3.976	3.985	0.246

Sophomores scored highest on final exams. Freshmen had the most intimidation before treatment. All year groups showed less intimidation after treatment.

APA Write Up (.5p)

This study examined three key variables: Final exam scores, Intimidation Before treatment (IntimBF), and Intimidation After treatment (IntimAF). The analysis looked at the entire group of students and then broke down results by each year in college. Looking at all students together, Final exam scores had an average of M = 79.39, SD = 9.42, Mdn = 80.15. Students’ intimidation levels before treatment averaged M = 6.99, SD = 0.33, Mdn = 6.99. After treatment, intimidation levels averaged M = 3.93, SD = 0.27, Mdn = 3.94.

When comparing students by year in college, clear differences appeared. For Final exam scores, Freshmen averaged M = 75.36, SD = 7.10, while Sophomores scored highest with M = 84.02, SD = 10.71. Juniors averaged M = 77.36, SD = 8.94, and Seniors averaged M = 80.52, SD = 8.71. Before treatment, intimidation levels were similar across years: Freshmen (M = 7.12, SD = 0.28), Sophomores (M = 6.98, SD = 0.28), Juniors (M = 6.99, SD = 0.29), and Seniors (M = 7.12, SD = 0.39). After treatment, intimidation dropped for all groups: Freshmen (M = 4.12, SD = 0.23), Sophomores (M = 3.98, SD = 0.20), Juniors (M = 3.87, SD = 0.26), and Seniors (M = 3.98, SD = 0.25).

The results show that Sophomores performed best on final exams, while Freshmen started with the highest intimidation levels. All year groups showed reduced intimidation after treatment.

Project 1

2025-07-25