Due 5/5/19  9 p.m EST

ORIGINAL AND ON TIME WORK!

DON’T ASK IF YOU HAVEN’T READ DIRECTIONS!

DATA AND STEP BY STEP GUIDE ATTACHED

Most CDC datasets include the following disclaimer:

“The use of sampling weights and sample design variables is recommended for all analyses because the sample design is a clustered design and incorporates differential probabilities of selection. If you fail to account for the sampling parameters, you may obtain biased estimates and overstate significance levels.”

In other words, samples selected for surveys may have imperfections in their representation of the reference population. Imperfections include the selection of sampling unit with unequal probability, non-coverage of the population, and non-responses to survey questions. Sampling weights would be used to compensate for these imperfections and produce valid and reliable results.

For this Assignment, you analyze the relationship of two variables with logistic regression, using both weighted and unweighted data. You then compare the results to identify the effect of weighting on the interpretation of the relationship.

The Assignment

1. Examine the Data )
   1. Open the Wk 10 Dataset (SPSS document) l.
   2. Produce numeric descriptive statistics for the following variables:
      • Cregion
      • USR
      • Sex
      • Q1
      • Q6a
      • Q16
      • Q22a
      • Receduc
      • Race/Ethnicity
2. Logistic Regression 
   1. Use SPSS to run a logistic regression model with Q22a. “Have you ever looked online for — Information about a specific disease or medical problem?” as your dependent variable (Note that there are 4 levels of responses possible, but only 2 are actually used in the responses so you can state the dependent variable is a binomial and use binary logistic regression) and Sex as the independent variable.
   2. Use backwards stepwise regression to add Receduc to the model as a potential confounder.
   3. How does the relationship between Q22a and Sex change with the addition of Receduc? Include a discussion of Odds Ratios and the Model Summary in your answer. Would you consider Receduc a confounder? Is it worth keeping it in the model even if it does not coufound the relationship between Q22a and Sex in this sample?
3. Logistic Regression with weights 
   1. Weight cases using the variable standwt (Standardized weight)
   2. Use SPSS to rerun a logistic regression model with Q22a. “Have you ever looked online for — Information about a specific disease or medical problem?” as your dependent variable, Sex as the independent variable, and Receduc as a covariate.
   3. How does weighting the cases change the outcome of the logistic regression?
   4. Discuss why it is important to weight cases from surveys with complex sampling schemes