Introduction

Welcome to Edition 18 of Making SAS Accessible to Everyone. This edition is a knowledge check. It features a quiz to reinforce your understanding of key concepts from Editions 1 through 8, covering:

  • Basic SAS syntax and data manipulation
  • Data step processing and PDV
  • Data exploration and formatting

Each section includes multiple-choice and true/false questions. Answers and explanations follow at the end.

1. Multiple Choice Questions

Q1. Which SAS procedure is used to preview the first few observations in a dataset?

A. PROC UNIVARIATE
B. PROC CONTENTS
C. PROC PRINT
D. PROC MEANS

Q2. What does the PDV (Program Data Vector) do during DATA step execution?

A. Stores entire datasets in memory
B. Holds one observation at a time during processing
C. Compiles summary statistics
D. Filters data rows before output

Q3. Which SAS format displays numeric values as percentages?

A. DATE9.
B. DOLLAR8.2
C. PERCENT8.
D. COMMA.

Q4. In the DATA step, what happens if you omit the RUN; statement?

A. The program crashes immediately
B. SAS auto-detects the end of step when another step starts
C. Nothing happens, the code is ignored
D. It becomes a comment

Q5. Which PROC gives you both mean and standard deviation of numeric variables?

A. PROC PRINT
B. PROC CONTENTS
C. PROC MEANS
D. PROC FREQ

Q6. Which statement is used to filter observations during execution?

A. WHERE
B. SELECT
C. FORMAT
D. CLASS

Q7. What is the purpose of OBS=n in PROC PRINT?

A. Hides the observation numbers
B. Limits the output to n rows
C. Sorts data in ascending order
D. Saves the result in a new dataset

Q8. What does the NODUPKEY option in PROC SORT do?

A. Removes observations with missing values
B. Exports the dataset as a CSV file
C. Removes duplicate observations based on key variables
D. Converts numeric to character variables

Q9. What type of variables is required for PROC UNIVARIATE analysis?

A. Character
B. Categorical
C. Numeric
D. Date

Q10. Which operator is used to match a pattern in a WHERE clause?

A. BETWEEN
B. LIKE
C. MATCHES
D. CONTAINS

2. True or False Questions

Q11. The WHERE statement can be used in both DATA and PROC steps.

True / False

Q12. The PROC SORT step must be followed by a BY statement.

True / False

Q13. The PDV is built during the execution phase of the DATA step.

True / False

Q14. The FORMAT statement modifies how values are stored in the dataset.

True / False

Q15. PROC UNIVARIATE can help identify outliers.

True / False

Q16. PROC FREQ is used to generate frequency tables for numeric variables only.

True / False

Q17. The LABEL statement can only be used inside PROC PRINT.

True / False

Q18. You can use macro variables inside a FORMAT statement.

True / False

Q19. The TITLE statement allows macro variable expansion.

True / False

Q20. PROC MEANS requires you to specify all variables using a VAR statement.

True / False

Answers & Explanations

Q1. C. PROC PRINT

Used to preview raw observations.

Q2. B. Holds one observation at a time during processing

The PDV is a temporary storage area where one observation is built.

Q3. C. PERCENT8.

Displays numbers multiplied by 100 and adds a % symbol.

Q4. B. SAS auto-detects the end of step when another step starts

SAS interprets the next DATA or PROC step as the boundary.

Q5. C. PROC MEANS

Provides summary statistics including mean, min, max, and std dev.

Q6. A. WHERE

Used to subset rows based on logical conditions.

Q7. B. Limits the output to n rows

Restricts the number of rows printed to the specified value.

Q8. C. Removes duplicate observations based on key variables

Only one observation is kept for each unique BY-group.

Q9. C. Numeric

PROC UNIVARIATE is designed for numeric variables.

Q10. B. LIKE

Allows pattern matching using wildcards % and _.

Q11. True

The WHERE clause is versatile and can filter in both contexts.

Q12. False

You can sort without BY; it’s needed only for specifying sort order.

Q13. False

The PDV is constructed during the compile phase.

Q14. False

FORMAT changes how data is displayed, not stored.

Q15. True

PROC UNIVARIATE provides detailed statistics, including outlier detection.

Q16. False

PROC FREQ can be used for both categorical and numeric values.

Q17. False

LABEL can be used in DATA steps and many procedures.

Q18. True

You can reference macro variables to dynamically set formats.

Q19. True

Macro variables can be resolved within TITLE statements.

Q20. False

If VAR is omitted, PROC MEANS uses all numeric variables by default.

In Edition 19, we will continue with another round of quiz questions focused on Editions 9 to 13.

Stay sharp and keep learning with 3 D Statistical Learning!

With sincere thanks to Dr. Dany Djeudeu for fostering confidence in SAS programming.