Data :

  • Midterms/Finals Exam Performance : Fall (2023), Winter (2024), Spring (2024)

    • Spring 2024 includes specific inf. regarding which MCQ response a student chose (e.g. A, B, C, D)

    • Others : Inc. only binary resp (1 – correct, 0 – incorrect)

Objective : Data Cleaning & Preperation

1 Read Data

setwd("/Users/isaiahmireles/Desktop/Misconceptions")

# Midterm : 
# F23 
F23_M_VA <- 
  read.csv("F23_Midterm_Version_Set_Scores/Midterm_Version_A_scores.csv")
F23_M_VB <- 
  read.csv("F23_Midterm_Version_Set_Scores/Midterm_Version_B_scores.csv")

# W24 
W24_M_VA <- 
  read.csv("W24_Midterm_Version_Set_Scores/Midterm_Version_A_scores.csv")
W24_M_VB <- 
  read.csv("W24_Midterm_Version_Set_Scores/Midterm_Version_B_scores.csv")

# S24 
S24_M <- 
  read.csv("24S-STATS-10-LEC-4_Midterm/S24_Midterm_student_responses copy.csv")

# ------------------------------------------------------------------------------- #

# Final :
# F23
F23_F_VA <- 
  read.csv("F23_Final_Exam_Version_Set_Scores/Final_Exam_Version_A_scores.csv")
F23_F_VB <- 
  read.csv("F23_Final_Exam_Version_Set_Scores/Final_Exam_Version_B_scores.csv")

# W24 
W24_F_VA <- 
  read.csv("W24_Final_Exam_Version_Set_Scores/Final_Exam_Version_A_scores.csv")
W24_F_VB <- 
  read.csv("W24_Final_Exam_Version_Set_Scores/Final_Exam_Version_B_scores.csv")

# S24 
S24_F_VA <- 
  read.csv("S24_Final_Exam_Version_Set_Scores/Final_Exam_Version_A_scores.csv")
S24_F_VB <- 
  read.csv("S24_Final_Exam_Version_Set_Scores/Final_Exam_Version_B_scores.csv")

Roughly, how many students all together?

n_std_F <-
  F23_F_VA |> nrow() + F23_F_VB |> nrow() + W24_F_VA |> nrow() + W24_F_VB |> nrow() + S24_F_VA |> nrow() + S24_F_VB |> nrow()  
n_std_F
## [1] 1520
  • here we assume 1 observation per row^

2 Repeated observations, Messy Data

2.1 F23 Cohort

2.1.1 F23 Midterm

library(tidyverse)
F23_M_VA |> distinct(SID) |> nrow()
## [1] 301
F23_M_VA |> nrow() # meaning : repeated obs.
## [1] 420
# which idx ? 
idx_v <- 
  F23_M_VA |>
  mutate(idx = row_number()) |>
  group_by(SID) |>
  filter(n() > 1) |>
  ungroup() |> # tell SID to f-off
  pull(idx) # make it into a vec. 

# damn
F23_M_VA[idx_v,] |> nrow()
## [1] 121
# 121 repeated obs.

  • problem(s) :

    • There are many “unidentified student”

    • one named/identified repeated obs.

# 22 unique scores 
F23_M_VA[idx_v,] |> distinct(Total.Score) 
##    Total.Score
## 1           32
## 2           29
## 3           31
## 4           27
## 5           13
## 6           23
## 7           17
## 8           30
## 9           25
## 10          33
## 11          34
## 12          18
## 13          26
## 14          21
## 15          22
## 16          16
## 17          24
## 18          15
## 19          28
## 20          19
## 21          20
## 22          NA

2.1.2 F23 Final

# ------------------------------------------------------------------------------- #
F23_F_VA |> distinct(SID) |> nrow()
## [1] 300
F23_F_VA |> nrow() # meaning - repeated obs.
## [1] 301
# which idx ? 
idx_v <- 
  F23_F_VA |>
  mutate(idx = row_number()) |>
  group_by(SID) |>
  filter(n() > 1) |>
  ungroup() |> # tell SID to f-off
  pull(idx) # make it into a vec. 

# F23_F_VA[idx_v,] |> select(SID, First.Name, Last.Name)

# ------------------------------------------------------------------------------- #
F23_F_VB |> distinct(SID) |> nrow()
## [1] 300
F23_F_VB |> nrow() # meaning - repeated obs.
## [1] 301
# which idx ? 
idx_v <- 
  F23_F_VB |>
  mutate(idx = row_number()) |>
  group_by(SID) |>
  filter(n() > 1) |>
  ungroup() |> # tell SID to f-off
  pull(idx) # make it into a vec.

# same person : SID match
# F23_F_VB[idx_v,] |> select(SID, First.Name, Last.Name)

3 anonymize

# Put the raw Fall 2023 data frames into a list.
F23_raw_lst <- list(
  F23_F_VA = F23_F_VA,
  F23_M_VA = F23_M_VA,
  F23_M_VB = F23_M_VB,
  F23_F_VB = F23_F_VB
)

# Create one unique student ID mapping across all Fall 2023 data.
F23_student_key <- F23_raw_lst |>
  bind_rows() |>
  distinct(SID) |>
  mutate(
    student = paste0("student_", row_number())
  )

# Add the same student ID mapping to every data frame.
F23_lst <- F23_raw_lst |>
  map(
    \(df) {
      df |>
        left_join(F23_student_key, by = "SID") |>
        select(-c(First.Name, Last.Name, SID, Email, Submission.ID))
    }
  )