Professional Documents
Culture Documents
In the dataset named “class_mid.csv”, data of parental age and allergy disease history
were collected in students taking the class of “medical statistics and epidemiology”
this year.
Question 1a. Create a scatter plot to examine the relationship between parental age
data.
Command: scatter dage mage
Question 1b. Create a box plot for weight data and group by allergy disease history.
Command: graph box weight allergy_hx
Question 4. Use the statistical method(s) introduced in class to examine whether there
is difference between standardized weight at 1 year and weight gain at 4 months.
What are the null and alternative hypotheses? What is your conclusion? Why?
Question 5a. What is x2 value for df=7, at level = 0.025?
Question 5b. What is F value for df=(7, 3), at level = 0.05?
Question 5c. What is t value for df=6, at one-sided level = 0.01?
Question 5d. What is corresponding p-value for z=1.96 (one-sided)?
Question 6a. What are the null and alternative hypotheses of the paper (N Engl J Med
2022;386:428-36)?
Question 6b. What is your conclusion, accept or reject the null hypothesis?
Question 6c. What is the statistical method introduced in this class you will use to test
the null hypothesis? Why?
In the dataset named “class_mid.csv”, height and allergy disease history were
collected.
Question 7. Use the statistical method(s) introduced in class to test whether there is
difference between height and allergy disease history. What are the null and
alternative hypotheses? What is your conclusion? Why?
In the dataset named “class_mid.csv”, pet owners and dog lovers were collected.
Question 8. Use the statistical method(s) introduced in class to examine whether there
is association between pet owners and dog lovers. What are the null and alternative
hypotheses? What is your conclusion? Why?
Question 9a. x2 test is a test of independence, thus cannot provide the strength of
association between two variables, true or false?
Question 9b. According to one of assumption of ANOVA, variance is not necessary
to be equal across all tested groups, true or false?
Question 9c. Which method is more sensitive to outlying values, Pearson’s
correlation coefficient or Spearman’s rank correlation coefficient?
Question 9d. When sample size gets bigger, for example, sample size equal to 2023, t
distribution will be close to which distribution?
In the dataset named “toy_mid.csv”, standardized weight at 1 year and standardized
weight at 2 years were collected in study subjects.
Question 10. Use the statistical method(s) introduced in class to examine whether
there is difference between standardized weight at 1 year and standardized weight at 2
years. What are the null and alternative hypotheses? What is your conclusion? Why?