2. You have access to school health records for a small county in New York state. Data on students' BMI is collected
once, at the end of 2019. You are interested in prevalence of overweight and obesity at the different school
levels - elementary, middle and high.
a. What kind of study is this?
b. What are the strengths and weaknesses of this type of study?
c. Of the students in elementary school, 50 are normal weight, 120 are overweight and 80 are obese. Of
the students in middle school, 20 are normal weight, 45 are overweight, and 45 are obese. Of the
students in high school, 30 are normal weight, 85 are overweight and 80 are obese. Construct a 3 x 3
table. What kind of variable is weight in this study?
d. What is the prevalence of overweight in elementary school students?
e. What is the prevalence of overweight or obesity in high school students?
f. Create a frequency and relative frequency table for the weight status of middle school students.
g. Calculate a 95% confidence interval for overweight relative frequency you found in g.
3. You are interested to see whether serum glucose differs by BMI category in the Framingham dataset.
a. What kind of variable is serum glucose?
b. Which descriptive statistics would you use with serum glucose? Why?
c. Formulate a null and alternate hypothesis for the above question.
d. What a level would you select? What does a mean?
e. What kind of analysis would you select to test this hypothesis? What is the test statistic?
f. Your results are below. Would you reject the null hypothesis? Interpret the results.
Serum glucose, mg/dL
Sum of
Squares
df
Mean Square
F
Sig.
Between Groups
14837.896
3
4945.965
8.493
.000
Within Groups
2309627.263
3966
582.357
Total
2324465.159
3969