In DrSeacow/DBSStats2Labs:

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#"
)

library(DBSStats2Labs)

Typing manually (as opposed to copy-pasting) helps me remember code better. This webpage will be split into parts 1 (the assignment itself) and 2 (following along with the exercises).

PART 1: Generalization Assignment

library(readxl)
library(dplyr)
library(tidyr)

lab1data <- read_xlsx("C:/Users/m3gad/OneDrive/Documents/R/DBSStats2Labs/Lab1_data.xlsx", col_names = TRUE, range = "B3:M13")

#What follows here is extremely sloppy, I understand and apologize. I regretfully could not figure out how to use the (col =) and (names = "") using pivot_long with a dataset containing multiple layered variables as is such in this assignment. Figuring out this alternative took far too much time and stress...thankfully, I was (barely albeit successfully) able to resist tampering with the raw data in Excel, a last-resort measure that I find quite unsavory since that's a large part of what we're trying to avoid by using R in the first place. Given the time and effort spent on this disastrously sloppy code- since it yields the long-form dataset with accurate formatting that we're aiming for, and I did so without tampering with the raw data, I think I'll leave it at this and call it somewhat of a success. 

c1 <- lab1data[1,]
c2 <- lab1data[2,]
c3 <- lab1data[3,]
c4 <- lab1data[4,]
c5 <- lab1data[5,]
c6 <- lab1data[6,]
c7 <- lab1data[7,]
c8 <- lab1data[8,]
c9 <- lab1data[9,]
c10 <- lab1data[10,]

lab1d <- t(c(c1, c2, c3, c4, c5, c6, c7, c8, c9, c10))

lab1study <- data.frame(participant = rep(1:10, each = 12),
                        context = rep(rep(c("Noisy", "Quiet"), each = 6), 10),
                        time = rep(rep(c("Morning", "Afternoon", "Evening"), each = 2), 20),
                        condition = rep(c("A", "B"), 60),
                        scores = t(lab1d))

lab1study

#Struggle-report: Again, I was thankfully able to avoid tampering with the raw data. I ended up not looking at the solution video, so by that metric, I scored a 10/10. However, there was an enormous amount of googling involved, so if the score were really "help needed" then I deserve a -100/10.

PART 2: Follow along with exercise

wide_data <- data.frame(person = 1:5,
                        Morning = c(1, 3, 2, 4, 3),
                        Afternoon = c(3, 4, 5, 4, 7),
                        Evening = c(7, 8, 7, 6, 9))
knitr::kable(wide_data)

long_data <- data.frame(person = rep(1:5, each = 3),
                       time_of_day = rep(c("Morning", "Afternoon", "Evening"), 5),
                       counts = c(1, 3, 7, 3, 4, 8, 2, 5, 7, 4, 4, 6, 3, 7, 9))
knitr::kable(long_data)

person <- rep(1:5, 3)
time_of_day <- rep(c("Morning", "Afternoon", "Evening"), each = 5)
counts <- c(1, 3, 7, 3, 4, 8, 2, 5, 7, 4, 4, 6, 3, 7, 9)
test <- data.frame(person, time_of_day, counts)

library(tidyr)
pivot_longer(data = wide_data,
             cols = !person,
             names_to = "time_of_day",
             values_to = "counts")

proprietary_data <- "1, 3, 7; 3, 4, 8; 2, 5, 7; 4, 4, 6; 3, 7, 9"

library(dplyr)

subjects <- unlist(strsplit(proprietary_data, split = ";"))
subjects
subjects <- strsplit(subjects, split = ",")
subjects

subjects <- t(data.frame(subjects))
subjects

colnames(subjects) <- c("Morning", "Afternoon", "Evening")
subjects

row.names(subjects) <- 1:5

subjects <- as.data.frame(subjects) %>% 
  mutate(person = 1:5)

pivot_longer(data = subjects,
             cols = 1:3,
             names_to = "time_of_day",
             values_to = "counts")

dv <- rnorm(10,0,1)
t.test(dv)

subject_data <- matrix(rbinom(50*10,1,0.5), ncol = 10, nrow = 50)
subject_means <- rowMeans(subject_data)
t.test(subject_means, mu=0.5)

subject_number <- rep(1:25, each=10)

day <- rep(rep(c("Wednesday", "Sunday"), each = 5), 25)

measurement_number <- rep(1:5, 2*25)

weights <- rnorm(250, 100, 25)

weight_data <- data.frame(subject_number,
                          day,
                          measurement_number,
                          weights)
head(weight_data)

#Alternatively

weight_data <- data.frame(subject_number = rep(1:25, each = 10),
                          day = rep(rep(c("Wednesday", "Sunday"), each = 5), 25),
                          measurement_number = rep(1:5, 2*25),
                          weights = rnorm(250, 100, 25))

subject_means <- weight_data %>%
  group_by(subject_number, day) %>%
  summarize(mean_weight = mean(weights), .groups = "drop")

head(subject_means)

t.test(mean_weight~day, paired=TRUE, data = subject_means)

subjects <- rep(1:10, each = 50)
room <- rep(c("Noisy","Quiet"), each = 50*5)
words <- rep(1:50, 10)
correct <- rbinom(500, 1, 0.5)

recall_data <- tibble(subjects,
                      room,
                      words,
                      correct)

recall_data

count_data <- recall_data %>%
  group_by(subjects, room) %>%
  summarize(number_correct = sum(correct), .groups = "drop")

count_data

t.test(number_correct~room, var.equal=TRUE, data=count_data)

Linear regression

people <- tibble(height = rnorm(100, 90, 10),
                 day = sample(1:31, 100, replace = TRUE))
people

lm.out <- lm(height~day, data = people)
lm.out

summary(lm.out)

One-way ANOVA

second level header

This is plain text.

weight_data <- tibble(subject_number = rep(1:25, each = 5*7),
                      day = rep(rep(c("S", "M", "T", "W", "Th", "F", "Sa"),
                                    each = 5), 25),
                      measurement_number = rep(1:5, 7*25),
                      weights = rnorm(25*5*7, 100, 25))

subject_means <- weight_data %>%
  group_by(subject_number, day) %>%
  summarize(mean_weight = mean(weights), .groups = "drop")

subject_means

aov.out <- aov(mean_weight ~ day, data = subject_means)
summary(aov.out)

Regression and ANOVA are run similarly

subject_means <- weight_data %>%
  group_by(subject_number, day) %>%
  summarize(mean_weight = mean(weights), .groups="drop")

subject_means

lm.out <- lm(mean_weight ~ day, data = subject_means)
summary(lm.out)

Factorial ANOVA

weight_data <- tibble(subject_number = rep(1:25, each = 4*7),
                      day = rep(rep(c("S","M","T","W","Th","F","Sa"),
                                    each = 4), 25),
                      time_of_day = rep(c("Morning", "Morning", "Evening", "Evening"), 7*25),
                      measurement_number = rep(rep(1:2, 2), 7*25),
                      weights = rnorm(25*4*7, 100, 25))

subject_means <- weight_data %>%
  group_by(subject_number, day, time_of_day) %>%
  summarize(mean_weight = mean(weights), .groups = "drop")

subject_means

aov.out <- aov(mean_weight ~ day*time_of_day, data = subject_means)
summary(aov.out)

Switching from Factorial ANOVA to multiple regression

subject_means <- weight_data %>% 
  group_by(subject_number, day, time_of_day) %>%
  summarize(mean_weight = mean(weights), .groups = "drop")

subject_means$day <- as.factor(subject_means$day)
subject_means$time_of_day <- as.factor(subject_means$time_of_day)

subject_means

lm.out <- lm(mean_weight ~ day*time_of_day, data = subject_means)
summary(lm.out)

anova(lm.out)