This report provides in-depth statistical insights into a dataset developed for the purpose of studying behavioral, academic, and well-being-related patterns among college students. The dataset, collected from [insert your dataset source here], comprises comprehensive data on students demographic characteristics, academic performance measures, lifestyle habits, and psychological well-being measures. Both in terms of observations and variables, this dataset is large enough to allow the study of how the day-to-day behaviors of students along with their personal circumstances are linked to their academic and emotional outcomes.
The main goal of the report is to systematically answer a set of research questions concerning the key factors that influence college students academic performance, their sleep behavior, and lifestyle choices, and their psychological health. This report will rely on statistical inference, such as confidence intervals, hypothesis testing, and graphical analyses, in an attempt to uncover meaningful patterns in the data and examine whether differences between groups observed are statistically significant.
The following research questions guide the analysis in this report: -1: Is there a significant difference in average weekday sleep duration (WeekdaySleep) between male and female students?
-2: Do first-year students have significantly poorer sleep quality (PoorSleepQuality) than seniors?
-3: Is the average cognitive score (CognitionZscore) significantly higher among students with normal anxiety status compared to those with moderate or severe anxiety?
-4: Do students who have at least one early class (EarlyClass = 1) wake up significantly earlier on weekdays (WeekdayRise) than students without early classes (EarlyClass = 0)?
-5: Is there a significant difference in average happiness levels between students with high stress and those with normal stress levels?
-6: Do students who report heavy alcohol use have significantly lower weekday sleep duration (WeekdaySleep) compared to abstainers?
-7: Is there a significant difference in the number of classes missed (ClassesMissed) between larks and owls?
-8: Do students who pulled an all-nighter (AllNighter = 1) have significantly different average GPA scores compared to those who did not (AllNighter = 0)?
-9: Is the average weekend bedtime (WeekendBed) significantly different between students with moderate depression and those with normal depression status?
-10: Do students who drink more alcohol per week (Drinks) have significantly poorer overall sleep quality (PoorSleepQuality) than those who drink less?
The SleepStudy dataset analyzed in this report was composed of 253 observations, with each observation representing a college student, and included 27 different variables. The dataset captured detailed information relative to demographic characteristics, academic status, sleep patterns, mental health, and lifestyle factors.
study= read.csv("https://www.lock5stat.com/datasets3e/SleepStudy.csv")
head(study)## Gender ClassYear LarkOwl NumEarlyClass EarlyClass GPA ClassesMissed
## 1 0 4 Neither 0 0 3.60 0
## 2 0 4 Neither 2 1 3.24 0
## 3 0 4 Owl 0 0 2.97 12
## 4 0 1 Lark 5 1 3.76 0
## 5 0 4 Owl 0 0 3.20 4
## 6 1 4 Neither 0 0 3.50 0
## CognitionZscore PoorSleepQuality DepressionScore AnxietyScore StressScore
## 1 -0.26 4 4 3 8
## 2 1.39 6 1 0 3
## 3 0.38 18 18 18 9
## 4 1.39 9 1 4 6
## 5 1.22 9 7 25 14
## 6 -0.04 6 14 8 28
## DepressionStatus AnxietyStatus Stress DASScore Happiness AlcoholUse Drinks
## 1 normal normal normal 15 28 Moderate 10
## 2 normal normal normal 4 25 Moderate 6
## 3 moderate severe normal 45 17 Light 3
## 4 normal normal normal 11 32 Light 2
## 5 normal severe normal 46 15 Moderate 4
## 6 moderate moderate high 50 22 Abstain 0
## WeekdayBed WeekdayRise WeekdaySleep WeekendBed WeekendRise WeekendSleep
## 1 25.75 8.70 7.70 25.75 9.50 5.88
## 2 25.70 8.20 6.80 26.00 10.00 7.25
## 3 27.44 6.55 3.00 28.00 12.59 10.09
## 4 23.50 7.17 6.77 27.00 8.00 7.25
## 5 25.90 8.67 6.09 23.75 9.50 7.00
## 6 23.80 8.95 9.05 26.00 10.75 9.00
## AverageSleep AllNighter
## 1 7.18 0
## 2 6.93 0
## 3 5.02 0
## 4 6.90 0
## 5 6.35 0
## 6 9.04 0In total, the 27 variables include both quantitative variables (e.g., hours of sleep, GPA, number of drinks) and categorical variables (e.g., gender, depression status, alcohol use), allowing for a wide range of statistical comparisons and inference procedures.
Data collection was accomplished through a survey-based approach, in which college students self-reported information using standardized questionnaires as part of ongoing research into sleep and student outcomes. Item responses were scored based on established scales for depression, anxiety, and stress, and using direct quantitative metrics for sleep hours, bedtime, and other variables. Efforts to representatively sample students across years, genders, and academic disciplines were taken.
This robust structure enables the investigation of sleep and its correlations with psychological health, academic performance, and lifestyle habits in a single integrated dataset among college students.
This section addresses each research question using statistical analysis of the SleepStudy dataset. For each question, the relevant methods, results, and graphical representations are provided.
t.test(WeekdaySleep ~ Gender, data = study)##
## Welch Two Sample t-test
##
## data: WeekdaySleep by Gender
## t = 1.0218, df = 226.08, p-value = 0.308
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.1402106 0.4422207
## sample estimates:
## mean in group 0 mean in group 1
## 7.926887 7.775882There was no statistically significant difference in average weekday sleep duration between male (mean = 7.93 hours) and female (mean = 7.78 hours) students, Welch’s t(226.08) = 1.02, p = 0.31, 95% CI for the difference in means: [-0.14, 0.44].
study_sub <- subset(study, ClassYear %in% c(1, 4))
t.test(PoorSleepQuality ~ ClassYear, data=study_sub)##
## Welch Two Sample t-test
##
## data: PoorSleepQuality by ClassYear
## t = 0.63612, df = 101.94, p-value = 0.5261
## alternative hypothesis: true difference in means between group 1 and group 4 is not equal to 0
## 95 percent confidence interval:
## -0.7099912 1.3803906
## sample estimates:
## mean in group 1 mean in group 4
## 6.510638 6.175439There was no statistically significant difference in average sleep quality between first-year students (mean = 6.51) and seniors (mean = 6.18), Welch’s t(101.94) = 0.64
# Filter for only "normal" and "moderate" or "severe" anxiety status
study_sub <- subset(study, AnxietyStatus %in% c("normal", "moderate", "severe"))
# Create a new grouping variable: "normal" vs. "moderate/severe"
study_sub$AnxietyGroup <- ifelse(study_sub$AnxietyStatus == "normal", "Normal", "Moderate/Severe")
# Run the Welch Two Sample t-test
t.test(CognitionZscore ~ AnxietyGroup, data = study_sub)##
## Welch Two Sample t-test
##
## data: CognitionZscore by AnxietyGroup
## t = -1.6378, df = 136.31, p-value = 0.1038
## alternative hypothesis: true difference in means between group Moderate/Severe and group Normal is not equal to 0
## 95 percent confidence interval:
## -0.34785148 0.03268267
## sample estimates:
## mean in group Moderate/Severe mean in group Normal
## -0.11277778 0.04480663There was no statistically significant difference in average cognitive scores between students with moderate or severe anxiety (mean = -0.11) and those with normal anxiety status (mean = 0.04).
t.test(WeekdayRise ~ EarlyClass, data = study)##
## Welch Two Sample t-test
##
## data: WeekdayRise by EarlyClass
## t = 6.9556, df = 148.9, p-value = 1.034e-10
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## 0.5967698 1.0703926
## sample estimates:
## mean in group 0 mean in group 1
## 9.139176 8.305595Students with at least one early class (EarlyClass = 1) woke up significantly earlier on weekdays (mean = 8.31) compared to students without early classes (mean = 9.14).
# Filter data to include only 'high' and 'normal' stress students
study_sub <- subset(study, Stress %in% c("high", "normal"))
# Run Welch Two Sample t-test for Happiness by Stress level
t.test(Happiness ~ Stress, data = study_sub)##
## Welch Two Sample t-test
##
## data: Happiness by Stress
## t = -4.4208, df = 71.565, p-value = 3.433e-05
## alternative hypothesis: true difference in means between group high and group normal is not equal to 0
## 95 percent confidence interval:
## -6.095995 -2.306652
## sample estimates:
## mean in group high mean in group normal
## 22.83929 27.04061There was a statistically significant difference in average happiness levels between students with high stress (mean = 22.84) and those with normal stress (mean = 27.04).
# Filter data for Heavy alcohol use and Abstain groups
study_sub <- subset(study, AlcoholUse %in% c("Heavy", "Abstain"))
# Run Welch Two Sample t-test for WeekdaySleep by AlcoholUse group
t.test(WeekdaySleep ~ AlcoholUse, data = study_sub)##
## Welch Two Sample t-test
##
## data: WeekdaySleep by AlcoholUse
## t = -0.13946, df = 43.309, p-value = 0.8897
## alternative hypothesis: true difference in means between group Abstain and group Heavy is not equal to 0
## 95 percent confidence interval:
## -0.7831244 0.6818009
## sample estimates:
## mean in group Abstain mean in group Heavy
## 7.610588 7.661250There was no statistically significant difference in average weekday sleep duration between students who report heavy alcohol use (mean = 7.66) and abstainers (mean = 7.61)
# Filter the data to include only larks and owls
study_sub <- subset(study, LarkOwl %in% c("Lark", "Owl"))
# Run the Welch Two Sample t-test for ClassesMissed by sleep preference
t.test(ClassesMissed ~ LarkOwl, data = study_sub)##
## Welch Two Sample t-test
##
## data: ClassesMissed by LarkOwl
## t = -3.2335, df = 63.596, p-value = 0.001941
## alternative hypothesis: true difference in means between group Lark and group Owl is not equal to 0
## 95 percent confidence interval:
## -4.276297 -1.009915
## sample estimates:
## mean in group Lark mean in group Owl
## 1.560976 4.204082There was a statistically significant difference in the number of classes missed between larks (mean = 1.56) and owls (mean = 4.20)
t.test(GPA ~ AllNighter, data = study)##
## Welch Two Sample t-test
##
## data: GPA by AllNighter
## t = 0.85745, df = 42.014, p-value = 0.3961
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.09239717 0.22892147
## sample estimates:
## mean in group 0 mean in group 1
## 3.252968 3.184706There was no statistically significant difference in average GPA scores between students who pulled an all-nighter (mean = 3.18) and those who did not (mean = 3.25).
# Filter data to include only 'moderate' and 'normal' depression status
study_sub <- subset(study, DepressionStatus %in% c("moderate", "normal"))
# Run Welch Two Sample t-test for WeekendBed by DepressionStatus
t.test(WeekendBed ~ DepressionStatus, data = study_sub)##
## Welch Two Sample t-test
##
## data: WeekendBed by DepressionStatus
## t = -2.1222, df = 42.261, p-value = 0.03973
## alternative hypothesis: true difference in means between group moderate and group normal is not equal to 0
## 95 percent confidence interval:
## -1.04703063 -0.02641716
## sample estimates:
## mean in group moderate mean in group normal
## 25.09294 25.62967There was a statistically significant difference in average weekend bedtime between students with moderate depression (mean = 25.09) and those with normal depression status (mean = 25.63)
# Find the median number of drinks per week
median_drinks <- median(study$Drinks, na.rm=TRUE)
# Create a new group variable: "More" if Drinks > median, "Less" if Drinks <= median
study$DrinkingGroup <- ifelse(study$Drinks > median_drinks, "More", "Less")
# Welch Two Sample t-test for PoorSleepQuality by DrinkingGroup
t.test(PoorSleepQuality ~ DrinkingGroup, data = study)##
## Welch Two Sample t-test
##
## data: PoorSleepQuality by DrinkingGroup
## t = 0.91339, df = 250.76, p-value = 0.3619
## alternative hypothesis: true difference in means between group Less and group More is not equal to 0
## 95 percent confidence interval:
## -0.382907 1.045253
## sample estimates:
## mean in group Less mean in group More
## 6.408759 6.077586There was no statistically significant difference in overall sleep quality between students who drink more alcohol per week (mean = 6.08) and those who drink less (mean = 6.41).
This analysis examined ten research questions on sleep patterns, academic performance, and well-being with respect to students in college. Overall, statistically significant differences were found in several of these outcomes: students who had early classes got up earlier on weekdays; larks missed fewer classes than owls; students who reported high stress were less happy; and students with moderate depression went to bed earlier on weekends than did students with normal depression.
LaFrance, M., & Hecht, M. A., “Why smiles generate leniency”, Personality and Social Psychology Bulletin, 21, 1995, 207-214.