Please report solutions to only two decimal places. Use the updated calcium database.1. Explore the distribution of the body temperature and heart rate variables by looking at
the Normality tests, Q-Q plot and histogram and describe how the distribution looks like
compare to a normal distribution.
2. We would like to estimate the proportion of people who smoke regularly (p = 0.48)
(hint: variance for Bernoulli distribution is p(1-p)). For this, we decide to interview a
sample of people from the population. If we accepted margin of error at 0.95 confidence
level is 0.02,
a.
How many people should we interview?
b.
Suppose we interview a random sample of 2000 people and found
that 320 of them smoke regularly. Find the 90% confidence interval for the
population proportion of smokers.
3. Subjects in this data are randomized into calcium treatment and placebo.
a. What study design is that? And why do we need a placebo group?
b. how would you design the study to better exclude the influence of age, gender
and race?
c. How would you design a study to examine whether calcium intake relates to
cardiovascular disease in the general population? Give at least two study designs.
