Load libraries and data

library(tidyverse)
library(knitr)
library(gridExtra)

# Helper functions used throughout ------------------------------------------
# p-values: scientific notation when very small, otherwise 3 decimals
fmt_p <- function(p) ifelse(p < 0.001, formatC(p, format = "e", digits = 2),
                            sprintf("%.3f", p))
# significance stars
stars <- function(p) ifelse(p < 0.001, "***",
                     ifelse(p < 0.01,  "**",
                     ifelse(p < 0.05,  "*", "")))
dataset_url <- "https://raw.githubusercontent.com/miayulia/Sleep-and-Health-Lifestyle-Analysis/main/Sleep_health_and_lifestyle_dataset.csv"

# Try the URL first; if it fails, fall back to a local copy of the CSV
# (download it from Kaggle and put it in the same folder as this file).
sleep_raw <- tryCatch(
  read_csv(dataset_url, show_col_types = FALSE),
  error = function(e) read_csv("Sleep_health_and_lifestyle_dataset.csv",
                               show_col_types = FALSE)
)

cat("Rows:", nrow(sleep_raw), " Columns:", ncol(sleep_raw), "\n")
## Rows: 374  Columns: 13
names(sleep_raw)
##  [1] "Person ID"               "Gender"                 
##  [3] "Age"                     "Occupation"             
##  [5] "Sleep Duration"          "Quality of Sleep"       
##  [7] "Physical Activity Level" "Stress Level"           
##  [9] "BMI Category"            "Blood Pressure"         
## [11] "Heart Rate"              "Daily Steps"            
## [13] "Sleep Disorder"

Preprocessing and variable selection (13 to 6 variables)

# Original 13 variables -> keep six core variables and give them short names
sleep <- sleep_raw %>%
  mutate(`BMI Category` = ifelse(`BMI Category` == "Normal Weight",
                                 "Normal", `BMI Category`),
         `BMI Category` = factor(`BMI Category`,
                                 levels = c("Normal", "Overweight", "Obese"))) %>%
  select(Activity = `Physical Activity Level`,
         Quality  = `Quality of Sleep`,
         Duration = `Sleep Duration`,
         Stress   = `Stress Level`,
         Age      = Age,
         BMI      = `BMI Category`)

excluded <- setdiff(names(sleep_raw),
                    c("Physical Activity Level", "Quality of Sleep",
                      "Sleep Duration", "Stress Level", "Age", "BMI Category"))
cat("Variables kept (", ncol(sleep), "):", paste(names(sleep), collapse = ", "), "\n")
## Variables kept ( 6 ): Activity, Quality, Duration, Stress, Age, BMI
cat("Variables excluded (", length(excluded), "):", paste(excluded, collapse = ", "), "\n")
## Variables excluded ( 7 ): Person ID, Gender, Occupation, Blood Pressure, Heart Rate, Daily Steps, Sleep Disorder
cat("\nMissing values per kept variable:\n")
## 
## Missing values per kept variable:
print(colSums(is.na(sleep)))
## Activity  Quality Duration   Stress      Age      BMI 
##        0        0        0        0        0        0
cat("\nBMI category counts (after merging 'Normal Weight' into 'Normal'):\n")
## 
## BMI category counts (after merging 'Normal Weight' into 'Normal'):
print(table(sleep$BMI))
## 
##     Normal Overweight      Obese 
##        216        148         10

Descriptive statistics

var_labels <- c(Activity = "Physical activity (min/day)",
                Quality  = "Sleep quality (1-10)",
                Duration = "Sleep duration (hours)",
                Stress   = "Stress level (1-10)",
                Age      = "Age (years)")

table3 <- sleep %>%
  select(all_of(names(var_labels))) %>%
  pivot_longer(everything(), names_to = "Variable", values_to = "Value") %>%
  group_by(Variable) %>%
  summarise(N = n(), Mean = mean(Value), SD = sd(Value), Median = median(Value),
            Q1 = quantile(Value, 0.25), Q3 = quantile(Value, 0.75),
            IQR = IQR(Value), Min = min(Value), Max = max(Value),
            .groups = "drop") %>%
  arrange(match(Variable, names(var_labels))) %>%
  mutate(Variable = unname(var_labels[Variable]),
         across(where(is.numeric), ~ round(.x, 2)))

kable(table3, caption = "Table 3. Summary statistics for the quantitative variables (N = 374)")
Table 3. Summary statistics for the quantitative variables (N = 374)
Variable N Mean SD Median Q1 Q3 IQR Min Max
Physical activity (min/day) 374 59.17 20.83 60.0 45.00 75.0 30.00 30.0 90.0
Sleep quality (1-10) 374 7.31 1.20 7.0 6.00 8.0 2.00 4.0 9.0
Sleep duration (hours) 374 7.13 0.80 7.2 6.40 7.8 1.40 5.8 8.5
Stress level (1-10) 374 5.39 1.77 5.0 4.00 7.0 3.00 3.0 8.0
Age (years) 374 42.18 8.67 43.0 35.25 50.0 14.75 27.0 59.0

Distribution analysis (Figure 1)

Histogram bin widths match the reporting granularity (15 minutes, 1 point, 0.5 hour) so that rounded self-reports do not create artificial gaps.

p1 <- ggplot(sleep, aes(x = Activity)) +
  geom_histogram(binwidth = 15, boundary = 22.5, fill = "blue",
                 color = "white", alpha = 0.85) +
  scale_x_continuous(breaks = seq(30, 90, 15)) +
  theme_minimal() +
  labs(title = "(a) Daily physical activity",
       x = "Activity (min/day)", y = "Frequency")

p2 <- ggplot(sleep, aes(x = Quality)) +
  geom_histogram(binwidth = 1, boundary = 3.5, fill = "blue",
                 color = "white", alpha = 0.85) +
  scale_x_continuous(breaks = 4:9) +
  theme_minimal() +
  labs(title = "(b) Sleep quality rating",
       x = "Quality score (1-10)", y = "Frequency")

p3 <- ggplot(sleep, aes(x = Duration)) +
  geom_histogram(binwidth = 0.5, boundary = 5.5, closed = "left",
                 fill = "blue", color = "white", alpha = 0.85) +
  scale_x_continuous(breaks = seq(5.5, 8.5, 0.5)) +
  theme_minimal() +
  labs(title = "(c) Sleep duration",
       x = "Sleep duration (hours)", y = "Frequency")

grid.arrange(p1, p2, p3, ncol = 3)
Figure 1. Distributions of (a) daily physical activity, (b) sleep quality score, and (c) sleep duration (N = 374).

Figure 1. Distributions of (a) daily physical activity, (b) sleep quality score, and (c) sleep duration (N = 374).

# Evidence for the "rounding" claim: how many records sit on multiples of 15 min?
act_counts <- sort(table(sleep$Activity), decreasing = TRUE)
print(head(act_counts, 8))
## 
## 60 30 45 75 90 40 55 35 
## 70 68 68 67 67  6  6  4
cat("\nShare of records with activity at a multiple of 15 minutes:",
    round(mean(sleep$Activity %% 15 == 0), 3), "\n")
## 
## Share of records with activity at a multiple of 15 minutes: 0.909

Correlation analysis (RQ1 and RQ2)

cor_row <- function(x, y, xlab, ylab) {
  p <- cor.test(x, y, method = "pearson")
  s <- cor.test(x, y, method = "spearman", exact = FALSE)
  tibble(Predictor = xlab, Outcome = ylab,
         `Pearson r` = round(unname(p$estimate), 3),
         `95% CI` = sprintf("[%.3f, %.3f]", p$conf.int[1], p$conf.int[2]),
         `p-value` = fmt_p(p$p.value),
         `Spearman rho` = round(unname(s$estimate), 3),
         `p-value (rho)` = fmt_p(s$p.value))
}

table4 <- bind_rows(
  cor_row(sleep$Activity, sleep$Quality,  "Physical activity", "Sleep quality"),
  cor_row(sleep$Activity, sleep$Duration, "Physical activity", "Sleep duration"),
  # Stress rows: these should reproduce r = -0.899 and r = -0.811 quoted in the paper
  cor_row(sleep$Stress,   sleep$Quality,  "Stress level",       "Sleep quality"),
  cor_row(sleep$Stress,   sleep$Duration, "Stress level",       "Sleep duration")
)

kable(table4, caption = "Table 4. Correlation between predictors and sleep outcomes (N = 374)")
Table 4. Correlation between predictors and sleep outcomes (N = 374)
Predictor Outcome Pearson r 95% CI p-value Spearman rho p-value (rho)
Physical activity Sleep quality 0.193 [0.093, 0.289] 1.75e-04 0.178 5.25e-04
Physical activity Sleep duration 0.212 [0.113, 0.307] 3.47e-05 0.209 4.54e-05
Stress level Sleep quality -0.899 [-0.917, -0.877] 2.88e-135 -0.908 9.71e-143
Stress level Sleep duration -0.811 [-0.843, -0.773] 1.24e-88 -0.811 1.75e-88

Scatterplots (Figure 2)

p_scatter1 <- ggplot(sleep, aes(x = Activity, y = Quality)) +
  geom_count(color = "blue", alpha = 0.6) +
  geom_smooth(method = "lm", formula = y ~ x, se = TRUE,
              color = "darkred", fill = "red", alpha = 0.15) +
  scale_size_area(max_size = 6) +
  theme_minimal() +
  labs(title = "(a) Physical activity vs. sleep quality",
       x = "Physical activity (min/day)", y = "Sleep quality (1-10)", size = "Count")

p_scatter2 <- ggplot(sleep, aes(x = Activity, y = Duration)) +
  geom_count(color = "darkgreen", alpha = 0.6) +
  geom_smooth(method = "lm", formula = y ~ x, se = TRUE,
              color = "darkred", fill = "red", alpha = 0.15) +
  scale_size_area(max_size = 6) +
  theme_minimal() +
  labs(title = "(b) Physical activity vs. sleep duration",
       x = "Physical activity (min/day)", y = "Sleep duration (hours)", size = "Count")

grid.arrange(p_scatter1, p_scatter2, ncol = 2)
Figure 2. (a) Physical activity versus sleep quality and (b) physical activity versus sleep duration, with fitted regression lines and 95% confidence bands. Larger points represent more observations.

Figure 2. (a) Physical activity versus sleep quality and (b) physical activity versus sleep duration, with fitted regression lines and 95% confidence bands. Larger points represent more observations.

Simple and multiple linear regression (RQ1, RQ2, RQ3)

# Simple models
mod_q_s <- lm(Quality  ~ Activity, data = sleep)   # Model 1A
mod_d_s <- lm(Duration ~ Activity, data = sleep)   # Model 2A

# Multiple models (BMI reference group = Normal)
mod_q_m <- lm(Quality  ~ Activity + Stress + Age + BMI, data = sleep)  # Model 1B
mod_d_m <- lm(Duration ~ Activity + Stress + Age + BMI, data = sleep)  # Model 2B
models <- list("Model 1A: Quality (simple)"     = mod_q_s,
               "Model 1B: Quality (multiple)"   = mod_q_m,
               "Model 2A: Duration (simple)"    = mod_d_s,
               "Model 2B: Duration (multiple)"  = mod_d_m)

term_labels <- c("(Intercept)"   = "Intercept (b0)",
                 "Activity"      = "Physical activity (b1)",
                 "Stress"        = "Stress level (b2)",
                 "Age"           = "Age (b3)",
                 "BMIOverweight" = "BMI: Overweight vs. Normal (b4)",
                 "BMIObese"      = "BMI: Obese vs. Normal (b5)")

coef_cell <- function(m, term) {
  s <- summary(m)$coefficients
  if (!term %in% rownames(s)) return("-")
  sprintf("%.4f (%.4f)%s", s[term, 1], s[term, 2], stars(s[term, 4]))
}
f_pvalue <- function(m) {
  f <- summary(m)$fstatistic
  pf(f[1], f[2], f[3], lower.tail = FALSE)
}

table5 <- tibble(`Predictor / statistic` = c(unname(term_labels),
                                             "Adjusted R-squared", "F-test p-value"))
for (nm in names(models)) {
  m <- models[[nm]]
  coefs <- vapply(names(term_labels), function(t) coef_cell(m, t), character(1))
  table5[[nm]] <- c(unname(coefs),
                    sprintf("%.4f", summary(m)$adj.r.squared),
                    fmt_p(f_pvalue(m)))
}

kable(table5, caption = "Table 5. Simple vs. multiple linear regression models (coefficient (SE); * p < 0.05, ** p < 0.01, *** p < 0.001; N = 374)")
Table 5. Simple vs. multiple linear regression models (coefficient (SE); * p < 0.05, ** p < 0.01, *** p < 0.001; N = 374)
Predictor / statistic Model 1A: Quality (simple) Model 1B: Quality (multiple) Model 2A: Duration (simple) Model 2B: Duration (multiple)
Intercept (b0) 6.6570 (0.1834)*** 7.5742 (0.1549)*** 6.6521 (0.1214)*** 7.3858 (0.1768)***
Physical activity (b1) 0.0111 (0.0029)*** 0.0076 (0.0008)*** 0.0081 (0.0019)*** 0.0066 (0.0009)***
Stress level (b2) - -0.4536 (0.0117)*** - -0.2739 (0.0134)***
Age (b3) - 0.0508 (0.0028)*** - 0.0266 (0.0032)***
BMI: Overweight vs. Normal (b4) - -0.9732 (0.0458)*** - -0.7268 (0.0522)***
BMI: Obese vs. Normal (b5) - -0.9360 (0.1020)*** - -0.2409 (0.1165)*
Adjusted R-squared 0.0346 0.9308 0.0425 0.7961
F-test p-value 1.75e-04 5.02e-212 3.47e-05 9.85e-126
# Full coefficient tables with p-values and 95% CIs (use these for the [R] values
# in Section 3.5, e.g. the p-value of the activity coefficient in Model 1B)
coef_table <- function(m, title) {
  s  <- summary(m)$coefficients
  ci <- confint(m)
  out <- tibble(Term = rownames(s),
                Estimate = round(s[, 1], 4),
                SE = round(s[, 2], 4),
                `95% CI` = sprintf("[%.4f, %.4f]", ci[, 1], ci[, 2]),
                `p-value` = fmt_p(s[, 4]))
  kable(out, caption = title)
}

coef_table(mod_q_s, "Model 1A (quality, simple)")
Model 1A (quality, simple)
Term Estimate SE 95% CI p-value
(Intercept) 6.6570 0.1834 [6.2964, 7.0175] 2.47e-124
Activity 0.0111 0.0029 [0.0053, 0.0168] 1.75e-04
coef_table(mod_q_m, "Model 1B (quality, multiple)")
Model 1B (quality, multiple)
Term Estimate SE 95% CI p-value
(Intercept) 7.5742 0.1549 [7.2695, 7.8789] 5.04e-163
Activity 0.0076 0.0008 [0.0060, 0.0091] 2.72e-19
Stress -0.4536 0.0117 [-0.4766, -0.4305] 1.24e-131
Age 0.0508 0.0028 [0.0452, 0.0564] 3.68e-52
BMIOverweight -0.9732 0.0458 [-1.0632, -0.8832] 5.06e-66
BMIObese -0.9360 0.1020 [-1.1366, -0.7353] 3.34e-18
coef_table(mod_d_s, "Model 2A (duration, simple)")
Model 2A (duration, simple)
Term Estimate SE 95% CI p-value
(Intercept) 6.6521 0.1214 [6.4135, 6.8908] 3.10e-180
Activity 0.0081 0.0019 [0.0043, 0.0119] 3.47e-05
coef_table(mod_d_m, "Model 2B (duration, multiple)")
Model 2B (duration, multiple)
Term Estimate SE 95% CI p-value
(Intercept) 7.3858 0.1768 [7.0381, 7.7335] 1.03e-141
Activity 0.0066 0.0009 [0.0049, 0.0084] 1.79e-12
Stress -0.2739 0.0134 [-0.3002, -0.2475] 1.23e-62
Age 0.0266 0.0032 [0.0202, 0.0330] 3.27e-15
BMIOverweight -0.7268 0.0522 [-0.8295, -0.6241] 1.17e-35
BMIObese -0.2409 0.1165 [-0.4699, -0.0119] 0.039
# Check for Table 5: adjusted R-squared of Model 1A should be about 0.0346
# (the draft showed 0.3462, which is inconsistent with its own p-value of 0.00017)
sapply(models, function(m) round(summary(m)$adj.r.squared, 4))
##    Model 1A: Quality (simple)  Model 1B: Quality (multiple) 
##                        0.0346                        0.9308 
##   Model 2A: Duration (simple) Model 2B: Duration (multiple) 
##                        0.0425                        0.7961

Group comparisons by BMI category (RQ3) - Tables 6, 7, 8

table6 <- sleep %>%
  group_by(BMI) %>%
  summarise(n = n(),
            `Sleep quality, mean (SD)`  = sprintf("%.2f (%.2f)", mean(Quality),  sd(Quality)),
            `Sleep duration, mean (SD)` = sprintf("%.2f (%.2f)", mean(Duration), sd(Duration)),
            .groups = "drop") %>%
  rename(`BMI category` = BMI)

kable(table6, caption = "Table 6. Sleep outcomes by BMI category")
Table 6. Sleep outcomes by BMI category
BMI category n Sleep quality, mean (SD) Sleep duration, mean (SD)
Normal 216 7.64 (1.00) 7.39 (0.72)
Overweight 148 6.90 (1.25) 6.77 (0.76)
Obese 10 6.40 (1.90) 6.96 (0.88)
bmi_tests <- function(var, label) {
  f <- as.formula(paste(var, "~ BMI"))
  a <- aov(f, data = sleep)
  s <- summary(a)[[1]]
  k <- kruskal.test(f, data = sleep)
  tk <- TukeyHSD(a)$BMI
  pw <- pairwise.wilcox.test(sleep[[var]], sleep$BMI,
                             p.adjust.method = "holm", exact = FALSE)$p.value
  pairs <- c("Overweight-Normal", "Obese-Normal", "Obese-Overweight")

  t7 <- tibble(Outcome = label,
               Test = c("One-way ANOVA", "Kruskal-Wallis"),
               `Test statistic` = c(sprintf("F = %.2f", s[["F value"]][1]),
                                    sprintf("chi-sq = %.3f", unname(k$statistic))),
               df = c(paste(s[["Df"]][1], s[["Df"]][2], sep = ", "),
                      as.character(unname(k$parameter))),
               `p-value` = c(fmt_p(s[["Pr(>F)"]][1]), fmt_p(k$p.value)))

  t8 <- tibble(Outcome = label,
               Comparison = c("Overweight - Normal", "Obese - Normal",
                              "Obese - Overweight"),
               `Mean difference` = round(unname(tk[pairs, "diff"]), 3),
               `Tukey adjusted p` = fmt_p(unname(tk[pairs, "p adj"])),
               `Wilcoxon (Holm) p` = fmt_p(c(pw["Overweight", "Normal"],
                                             pw["Obese", "Normal"],
                                             pw["Obese", "Overweight"])))
  list(t7 = t7, t8 = t8)
}

res_q <- bmi_tests("Quality",  "Sleep quality")
res_d <- bmi_tests("Duration", "Sleep duration")

kable(bind_rows(res_q$t7, res_d$t7),
      caption = "Table 7. Tests of differences in sleep outcomes across BMI categories")
Table 7. Tests of differences in sleep outcomes across BMI categories
Outcome Test Test statistic df p-value
Sleep quality One-way ANOVA F = 22.01 2, 371 9.26e-10
Sleep quality Kruskal-Wallis chi-sq = 37.895 2 5.90e-09
Sleep duration One-way ANOVA F = 31.00 2, 371 3.55e-13
Sleep duration Kruskal-Wallis chi-sq = 43.070 2 4.44e-10
kable(bind_rows(res_q$t8, res_d$t8),
      caption = "Table 8. Pairwise comparisons between BMI categories")
Table 8. Pairwise comparisons between BMI categories
Outcome Comparison Mean difference Tukey adjusted p Wilcoxon (Holm) p
Sleep quality Overweight - Normal -0.740 7.40e-09 6.66e-09
Sleep quality Obese - Normal -1.239 0.002 0.039
Sleep quality Obese - Overweight -0.499 0.371 0.672
Sleep duration Overweight - Normal -0.618 0.00e+00 1.53e-10
Sleep duration Obese - Normal -0.428 0.174 0.342
Sleep duration Obese - Overweight 0.190 0.712 0.818
# Variance inflation factors (values above about 5 suggest collinearity problems)
vif_tbl <- function(m) {
  X <- model.matrix(m)[, -1, drop = FALSE]
  v <- diag(solve(cor(X)))
  tibble(Term = names(v), VIF = round(unname(v), 2))
}
kable(vif_tbl(mod_q_m), caption = "Variance inflation factors for the multiple models (same predictors in 1B and 2B)")
Variance inflation factors for the multiple models (same predictors in 1B and 2B)
Term VIF
Activity 1.04
Stress 1.63
Age 2.27
BMIOverweight 1.89
BMIObese 1.02

#Alternative handling of rounded activity values: Low / Moderate / High groups

sleep_grp <- sleep %>%
  mutate(ActivityGroup = cut(Activity, breaks = c(-Inf, 44, 60, Inf),
                             labels = c("Low (<45 min)", "Moderate (45-60 min)",
                                        "High (>60 min)")))

kable(sleep_grp %>%
        group_by(ActivityGroup) %>%
        summarise(n = n(),
                  `Quality, mean (SD)`  = sprintf("%.2f (%.2f)", mean(Quality),  sd(Quality)),
                  `Duration, mean (SD)` = sprintf("%.2f (%.2f)", mean(Duration), sd(Duration)),
                  .groups = "drop"),
      caption = "Sleep outcomes by activity group")
Sleep outcomes by activity group
ActivityGroup n Quality, mean (SD) Duration, mean (SD)
Low (<45 min) 82 7.01 (1.70) 7.04 (1.13)
Moderate (45-60 min) 149 7.21 (0.83) 6.87 (0.39)
High (>60 min) 143 7.59 (1.12) 7.46 (0.77)
kruskal.test(Quality  ~ ActivityGroup, data = sleep_grp)
## 
##  Kruskal-Wallis rank sum test
## 
## data:  Quality by ActivityGroup
## Kruskal-Wallis chi-squared = 11.309, df = 2, p-value = 0.003502
kruskal.test(Duration ~ ActivityGroup, data = sleep_grp)
## 
##  Kruskal-Wallis rank sum test
## 
## data:  Duration by ActivityGroup
## Kruskal-Wallis chi-squared = 39.764, df = 2, p-value = 2.319e-09