Questions

1. How does an analyst tell what the variable names mean and what the coded levels for categorical variables mean in a dataset?

2. PROC FREQ is for creating frequency tables about categorical variables, and PROC UNIVARIATE is for producing summary statistics about continuous variables. Therefore, why would a person preparing data for loading into a data warehouse ever use PROC FREQ on a continuous variable?

3. Why is it helpful to plan transformed variables in a data dictionary before developing ETL code?

4. How does suppressing values as missing in a continuous variable impact PROC UNIVARIATE output?

5. Imagine you were working on a data warehouse with stock market data. In your data warehouse, you had the value of the stock market at the time of closing every day. What are some classification variables you could make that might improve how the users of the data warehouse were served?

6. Imagine you had some weather data from a tropical region. After checking a data...