How to Prepare for the SAS Certified Specialist Base Programming Exam
The SAS Base Programming for SAS 9 Exam will be replaced by the new performance-based SAS Certified Specialist Exam on June 30, 2019.
The new performance-based exam will introduce three new things:
SAS Specialist Exam Training Program
Based on the SAS Base Specialist Certificate Exam Prep Guide, there are a total of 16 topics:
Topic 1 & 2: Setting Up Practice Data and Basic Concept
Topics 1 & 2 focus on the basics of the SAS language. It includes the SAS statement, data step and proc step, SAS programming structure, SAS library, compiling and executing programs, SAS logs, data and descriptor portions of the data set, as well as the SAS variable attributes.
You likely won't see too many questions from these two topics. However, you need to have a good foundation of the SAS base programming before you proceed to the rest of the topics.
Topic 3: Accessing Your Data
SAS data sets are stored in SAS libraries. You can think of SAS libraries as the folders that store the SAS files.
This is a short topic that introduces the library structure and the descriptor portion of the data set.
Topic 4: Creating SAS Data Sets
Proc Import is a new topic introduced to the SAS Base Certified Specialist Exam. It allows you to import CSV, text and tab-delimited files.
To prepare for the exam, you need to practice importing different types of files using the various Proc Import options, such as DBMS, DLM, REPLACE, GETNAMES, etc.
Topic 5: Identifying and Correcting SAS Language Errors
Identifying errors in SAS is a big topic in the SAS Base Certified Specialist Exam!
There will be at least one short-answer question where you need to identify the syntax, data and logic errors in the code.
To prepare for the exam, you need to understand the different types of errors in SAS, and how you can identify them in the SAS log.
Pay attention to logic errors because it is the type of error that cannot be identified without checking the results against the initial intention of the program.
Topic 6: Creating Reports
When it comes to reporting, the SAS base specialist exam focuses on the Proc Print procedure. This is a versatile data reporting tool that allows you to print a data report with simple descriptive statistics, titles and footnotes.
To prepare for the exam, you must get familiar with the various Proc Print options, as well as the WHERE statement and the CONTAIN operator, which are very likely to appear in the exam.
Topic 7: Understanding DATA Step Processing
Data step processing is the foundation of SAS base programming. Whenever a data step is processed, data is read into the program data vector before being inserted into the SAS data set, one record at a time.
This topic can be challenging for beginners, however, it is an important topic to learn before learning the more advanced topics, such as BY-group processing and the Retain statement.
Topic 8: BY-Group Processing
BY-group processing has some useful applications. You can compute cumulative summation by groups, and you can find the highest and lowest values within groups.
BY-group processing usually involves the Proc Sort procedure, a BY statement within a data step, the SUM/RETAIN statement, as well as the FRIST.VAR and LAST.VAR variables.
Getting familiar with these topics will be key to passing the exam.
Topic 9: Creating and Managing Variables
Variables are essential parts of a SAS data set. They store data of the same nature into the same columns.
To prepare for the exam, you will have to get familiar with how variables are defined. You will have to understand the six attributes of a SAS variable, how to assign values using the logical if-then statement, as well as maintaining the variable type and length to ensure the data values are captured correctly.
Last but not least, you must get familiar with simple SAS macros, which is a new topic introduced to the SAS base specialist exam.
Topic 10: Combining SAS Data Sets
Combining SAS data sets is usually a challenging topic for SAS beginners. You can stack the data sets, one on top of another, using the SET statement. You can also merge the data sets horizontally by matching common variables using the MERGE statement.
To prepare for the exam, you must learn how to handle the different scenarios when performing one-to-one or one-to-many merging. You must also understand how to handle inconsistent variable names and lengths across the input data sets.
Topic 11: Processing Data with DO Loops
Do Loops allow you to perform repetitive tasks easily without having to repeat your code in the program.
To prepare for the exam, you will have to understand how to construct a do-loop and a nested do-loop. You will also have to understand when the loop ends, which is an important and often confusing topic for beginners.
Topic 12: SAS Formats and Informats
SAS formats are a relatively easier topic than informats. SAS formats are used to control the display of the data (e.g. 1 --> "M", 2 --> "F"). There are built-in formats that you can use right out of the box. You can also define your own formats that suit your data.
SAS informats are used in two situations:
Getting familiar with these two topics are crucial when preparing for the exam.
Topic 13: SAS Date, Time and Datetime Values
SAS date, time and datetime variables are a special type of numeric variable in SAS. They are numeric in nature, but with a date, time or datetime format.
The topics that will appear in the exam include reading the date, time and datetime values into SAS. You will also see topics in date constant and date formats on the multiple-choice questions.
Topic 14: Using Functions to Manipulate Data
SAS has many built-in functions that allow you to effectively manipulate your data. Examples:
Different functions have a different number of parameters of various types. Getting familiar with these functions will not only help you to pass the exam, but will also improve your data manipulation skills.
Topic 15: Producing Descriptive Statistics
The two most common procedures for descriptive statistics in SAS are Proc Means and Proc Freq.
Proc Means is used on numeric variables and it generates statistics such as mean, standard deviation, minimum and maximum. Proc Freq is used for generating frequency statistics.
The topics of generating statistics within groups and controlling the decimal places and the outputs for Proc Means and Proc Freq are exam topics that you should be familiar with.
Topic 16: Creating Output
The ODS (Output Delivery System) allows you to export the analysis results to HTML, PDF or RTF files. You can also use ODS and Proc Export to export the results to an Excel spreadsheet.
Not everyone has access to SAS. To be a well-rounded programmer, you must understand how to export the results to a more commonly-used file type such as PDF or Excel.
There will also be a number of exam questions related to ODS!