sas-problem-1

The take-home assignment will account for 10 points.

This assignment is due at the end of Module 12, Tuesday night at 11:59 pm.

1. Please employ appropriate SAS procedures to produce descriptive statistics and p-values that would allow you to fill in the table below.

a. Use the Dataset EPI626_Assign6_F2019.

b. Descriptive statistics

i. For normally distributed continuous variables, present mean and standard deviation. For continuous variables that are not normally distributed, present median and IQR.

ii. For categorical variables, present number (count) and proportion (%).

1. Hint: You may have to recode some of the categorical variables.

c. P-values

i. If comparing means from two groups, use T-test

ii. If comparing means from three groups, use ANOVA.

iii. If comparing distribution of non-normally distributed continuous variables, use non-parametric tests.

iv. If comparing proportions from two or more groups, choose between Chi-Square or Fisher’s Exact test, depending on expected cell sizes.

d. Hint: you will have to recode age from a continuous variable into a categorical variable.

i. Fill in the number of observations in each age group at the top of the table. N = (???)

2. Please submit SAS code, log, and output.

a. SAS program should have the following components:

i. Checking distribution

ii. Producing descriptive statistics

iii. Producing p-values

3. Please fill out the table below and submit this word file.

Age Group

£ 25 Years

N = ( )

>25 Years

N = ( )

P-value

Gender, N (%)*

Female

Male

Left Handed, N (%)*

Yes

No

Height, Mean (SD)**

*% out of total in each age group

**SD refers to standard deviation