SAS For Dummies

Introduction

Unless you’re a hermit, chances are good that your life is touched by SAS (pronounced sass) almost every day.

Have you ever received an offer for a credit card in the mail? The bank might have used SAS to select you for the particular offer you received. Remember a recent news article that cited demographic trends in the United States? The Census Bureau uses SAS to crunch its numbers. Were you tempted to buy that new gadget in a big-name retail store or online? The corporate office might have used SAS to calculate the best price to set for that specific item on that specific week.

The rate you pay for life insurance, the analysis behind pharmaceutical drug trials, the quality of parts used to assemble your automobile — all these are determined by people who use SAS. You don’t see SAS directly from day to day — but, like gravity, it’s an invisible force that affects your life.

This book offers a prolonged glimpse into the multifaceted world of SAS software. Read on to discover how people use SAS to influence the world around you. Perhaps you’ll see how to grab the reins yourself and use SAS to affect your own sphere of influence.

About This Book

Although this book is titled SAS For Dummies, 3rd Edition, you absolutely need some smarts to produce solid results using SAS. However, the overarching message of this book is that you don’t need to be an expert at using software. You just need to know what questions to ask, what data is needed to provide an answer, and how to interpret the results.

This book covers a variety of SAS products. I help you take a high-level look at some and then dive deeply into those that you’re most likely to use. The amazing fact is that SAS offers hundreds of software products covering dozens of industries and disciplines. No lone person could possibly use them all and still have time for essential activities, such as sleep and personal hygiene. (Hmm, maybe that explains the smell around here.)

Like most software products, SAS products look and work differently from version to version. This book describes the modern platforms of SAS 9.4 and SAS Viya, and their many different applications. Many of these interfaces are actively developed by SAS and will change and receive new features over time. As a result, some of the instructions and figures in the book will differ from what you see in your installation.

And, hey! Here’s something cool about this book: You don’t have to read it from stem to stern. Feel free to skip around, reading the sections that cover what you need to know.

This book does not dive deep into two popular SAS topics:

How to program in SAS: SAS software has been around for almost 50 years, and you can find plenty of books about SAS programming. Indeed, one goal of this book is to show you how much you can do with SAS without having to become a SAS programmer. However, you’ll find several examples of SAS programs throughout the book, especially in Chapter 4, so you can at least recognize a SAS program if you meet one on the street.

Life at SAS Institute Inc., the makers of SAS software: SAS, the company, has had more than its 15 minutes of fame on TV shows (such as 60 Minutes and Oprah), plus a big dose of coverage in business magazines (such as Fortune and Forbes). The stories are overwhelmingly positive (not featuring anyone trying to blot out the camera view with their palm). SAS is famous for being a great place to work. (As an author, I do hold a day job at SAS — and I enjoy that job. That’s all I’ll say about that.)

Conventions Used in This Book

This book contains lots of descriptive information about SAS software. Because a picture is worth — well, you know — this book has lots of figures of the software in action. (Action is a relative term; after all, this is business and analytical software, not Super Smash Bros.)

You’ll find plenty of step-by-step instructions to accomplish specific tasks. You can follow along with these if you have the software handy; otherwise, you can use your imagination and imagine how much fun it is.

When I show a filename, path, data set, or code within regular text, I set it off in a monofont type, like this.

When I want you to type something, I put the characters you type (such as type this, in bold).

If you get the munchies while reading this book, it's because most of the examples refer to data with a candy theme.

What You’re Not to Read

Occasionally, you’ll see some sidebar topics or Technical Stuff icons in the margin that indicate a historical or technical side point. You can skip those if you want, but reading them will give you that extra edge when SAS comes up in the discussion at the next cocktail party you attend. Study up and impress your friends!

Foolish Assumptions

To better manage the task of writing this book, I had to begin with some assumptions about you, the reader. Here they are:

SAS software runs on many types of computer systems, but the majority of people experience it under Microsoft Windows or within a web browser. So, the examples are presented as though you’re using a PC. I assume that you know your way around a PC, clicking the mouse, selecting menus, and so on.

As I stated, I don’t assume that you’re a SAS programmer or that you even aspire to be one. However, if you are or if you do, you’ll still find this book useful to round off your SAS knowledge.

Icons Used in This Book

All the information in this book is special; I wouldn’t have included it otherwise. But some information that I provide is more special than the rest. To draw attention to its specialness, I tagged it with some eye-catching little icons.

Tip The Tip icon calls out a sentence or two that might prove to be a time-saver in your work. (You’re welcome.)

Remember Got a mind like a steel sieve? Well, you might want to reserve some space in your memory bank for the content next to the Remember icon. I use this icon as a way to emphasize an important point or concept.

Warning Hear the voice in your head yelling Danger, Will Robinson! Danger!? Is your Spidey-sense tingling? Well, there’s little danger, really, as long as you heed the advice shown near the Warning icon.

Technical stuff This book contains many little gems of technical information. You can still use SAS if you don’t read and understand this stuff, just like you can still enjoy watching hockey if you don’t know what icing means. But, as any fan will tell you, it’s more fun knowing what it all means.

Beyond the Book

After you complete this book, you might crave more details about specific areas that I cover. (Or maybe those cravings are related to the candy-themed examples.) The best starting place for more information is the SAS support website at https://support.sas.com.

If you want to try some of the exercises in the book on your own, I’ve assembled all the sample data, SAS programs, and projects in an online GitHub repository. You can find all of these at https://github.com/cjdinger/sasfordummies.

If this book transforms you into a card-carrying SAS user, your next step might be to seek out others like you. That will be easy because millions of people around the globe use SAS. And do you know what? Every day, they gather virtually in the SAS Support Communities, an online Q&A discussion site for sharing SAS experience and knowledge. Check it out at https://communities.sas.com.

Finally, in line with all the other books in the For Dummies series, I also provide a SAS online Cheat Sheet, which has additional tips for SAS programmers and the most essential techniques to learn in SAS code. To see the Cheat Sheet, simply go to www.dummies.com and type SAS For Dummies in the search box.

Part 1

Welcome to SAS!

IN THIS PART …

Learn about SAS and its long history as a statistical software package.

See the various applications that make up SAS and how people use them.

Take a whirlwind tour of SAS Enterprise Guide and learn to create results quickly.

Dive into SAS programming with a crash course on programming concepts and syntax.

Chapter 1

Touring the Wonderful World of SAS

IN THIS CHAPTER

Bullet Finding something for everyone in SAS

Bullet Learning what SAS is

Bullet Discovering the many uses for SAS

Bullet Programming using SAS, or not

Bullet Examining a few real-world examples

One of the questions newcomers ask most frequently about SAS is, What does the name mean? After all, those capital letters usually indicate an acronym, right? Today, SAS just refers to the name of a company. If you’ve been around the world of data analysis for a while, however, you may also be familiar with the old meaning of SAS: Statistical Analysis System.

SAS software was developed by a bunch of smart and inquisitive people at North Carolina State University (NCSU) in the late 1960s and early 1970s. Some of these people are still at the company as owners or executives: Jim Goodnight (the current company president) and John Sall. Most of these SAS software pioneers were trained as statisticians or mathematicians and developed the SAS language to help analyze a variety of scientific experiments being conducted at NCSU and other research universities.

Over time, the software became as important as the experiments it was being used to analyze. The company now known as SAS Institute was formed in 1976, by a few people who were brave enough to leave the cozy world of academics for the then-unknown world of software. The first few years were a bit rough, but before long, word of this software and its capabilities began to spread, revenues increased, and the company began to grow. As of this writing, SAS has enjoyed nearly 50 consecutive years of growth and profitability. They must be doing something right.

This chapter is an overview of the power and flexibility of SAS for a range of applications and industries. SAS has expanded from being just a programming language for experts to meeting the needs of a wide variety of users in almost every industry and country in the world.

So, What Is SAS and Who Uses It?

SAS is the iconic software that provides capabilities for data management, analytics, reporting, decisioning, and machine learning and AI.

What SAS looks like to you depends on your skills and interests, your job role, and what SAS products or solutions your organization has provided. As you can learn in Chapter 2, SAS comes in many shapes and sizes. Figure 1-1 shows an example of a SAS program and output in SAS Enterprise Guide, where Figure 1-2 shows a report designed within SAS Visual Analytics. These are just two of the many faces of SAS that SAS users may encounter.

FIGURE 1-1: One view of SAS: A program, log, and results shown in SAS Enterprise Guide.

FIGURE 1-2: Also SAS! A designed report in SAS Visual Analytics.

A Tale of Two Platforms: SAS 9.4 and SAS Viya

SAS 9.4 was released in 2013 as the latest major version of what users think of as the classic SAS platform. Even though its initial release was over a decade ago, SAS continues to enhance it and issue fixes by delivering maintenance releases, which allows SAS customers to continue using SAS 9.4 with the latest operating systems and security-conscious IT policies.

SAS Viya represents the newest capabilities of SAS, including the latest machine learning algorithms and AI methods. Every month, SAS delivers new SAS Viya releases, with fixes and new features. This continuous-delivery model is a standard practice for cloud-based software and software-as-a-service.

Even though SAS 9.4 and SAS Viya seem very different on the surface, they share a core that makes it easy to move from one to the other. In fact, many customers have both: a continuing SAS 9.4 installation while they accomplish new tasks using SAS Viya. The ability of SAS 9.4 to connect to SAS Viya helps these customers share data and code between the two systems.

Isn’t SAS just for gurus?

You might assume that you need to be a statistician or math guru to use SAS, but happily that’s not the case. In the past several years, SAS has made a significant investment in making the unparalleled analytical and data management capabilities developed over 40-plus years available to almost anyone with a problem to solve in business, science, or government. With products such as SAS Enterprise Guide, SAS Visual Analytics, and SAS for Microsoft 365, SAS has never been more accessible or flexible. These products provide user-friendly interfaces to maximize the heavy-duty capabilities that SAS has long provided to gurus!

Most of this book is dedicated to spelling out simple-to-understand principles that are full of possibilities and limited only by your situation and imagination. SAS offers so much potential that this book just scratches the surface and gets you up to speed on the basics.

SAS for data managers

SAS is famous for its ability to access any type of data, regardless of the source. Of course, you can use SAS to connect with any database system to read and update data. SAS users also often work with file-based data such as flat files, Excel files, and long-forgotten formats such as fixed-length records and more. Finally, SAS includes methods to work with application programming interfaces (APIs) to pull and publish data in our Internet-connected world.

Data managers use all these aspects together with SAS procedures and interfaces to build robust, repeatable processes that can pull data in, transform and enrich it with analytical insights, and publish new data and results to the systems that need it. Conventional wisdom holds that 80 percent of analytics lies in the data prep — and SAS has that covered, and more.

SAS for statisticians

SAS has been a leader in statistics since its inception — it’s literally part of the original meaning of the SAS name (as in Statistical Analysis Software). SAS software is used in universities around the world to teach statistical concepts. (See Chapter 16 for free and easy ways to learn SAS.)

In industry, SAS is used for all types of important statistical applications, including pharmaceutical research, medical studies, quality control, risk management, fraud detection, and many more. SAS software is often cited in published papers found in peer-reviewed scientific journals, where authors must share their methodology along with their findings and conclusions.

Chapter 9 provides an overview of the many statistical methods that SAS supports. Reading this book won’t make you a statistician, but you will learn enough to distinguish a p-value from a pie chart.

SAS for business analysts

Regardless of industry, it’s the job of business analysts to help their organization make data-driven decisions. You’ve already read how SAS offers great coverage for managing data and crunching statistics. A business analyst needs the tools to build upon this work to create compelling data stories and communicate the insights to a less-technical audience. To that end, they need tools for

Reporting and visualization: Needed to create detailed reports and visualizations to present findings in a clear and understandable way. This helps stakeholders grasp insights quickly and make strategic decisions.

Problem solving: To identify business problems and use data to find solutions and examine what-if scenarios. This involves a lot of critical thinking and the ability to interpret data in the context of the business environment. Skilled analysts can explore solutions by using SAS code or by using interactive tools like SAS Visual Analytics (discussed in Chapter 14).

Communication: To share their findings effectively to both technical and nontechnical audiences. This requires strong presentation skills and the ability to translate complex data into insights you can act on. The collaboration features of SAS for Microsoft 365 (see Chapter 13) and SAS Visual Analytics (see Chapter 14) reduce the barriers for sharing information with nontechnical audiences.

SAS for data scientists

What happens when you cross the mathematical rigor of statistics with the process innovation of computer science? You get the newer discipline of data science, which has driven the adoption of machine learning and AI. Data scientists appreciate the tools that SAS offers for their discipline, which includes

Model building: To develop and train statistical and machine learning models to make predictions or uncover insights. SAS provides robust tools for building and validating these models. Chapter 10 covers the machine learning capabilities of SAS Viya.

Experimentation: To design and conduct experiments to test hypotheses and validate models. This iterative process helps in refining models and improving their accuracy. Data scientists move easily through the analytics life cycle, as described in Chapter 12.

Algorithm Development: To create and refine algorithms to solve specific business problems. This requires a deep understanding of both the data and the business context.

Collaboration: To work closely with other teams and gain value from work done in the open-source community. To that end, they’re familiar with GitHub and programming tools that offer Git integration.

Data scientists are also more likely to be programming polyglots, proficient with multiple programming languages such as Python or R, along with SAS. SAS Viya and SAS Viya Workbench offer ways for them to use all their programming language skills to get the best results.

Myth: You Need to Be a Programmer to Use SAS

It used to be that you could access the capabilities of SAS only if you knew how to write programs (or if you were willing to learn). SAS has an incredibly powerful programming language, and if you know how to use it, there’s almost nothing you can’t accomplish (in the realm of data, statistics, and AI, that is). This book covers SAS programming in Chapter 4 and includes little drops of code examples throughout the rest of the chapters.

But if you’re not interested in writing and running your own SAS code, that won’t stop you from succeeding with SAS. So many of the SAS capabilities are available in easy-to-use applications that do not require or expect programming skills. For example, you can

Build ad hoc analyses and repeatable Process Flows with SAS Enterprise Guide, covered in Chapter 2 and Chapter 3.

Manage and transform your data using an intuitive Query Builder interface, covered in Chapter 5.

Develop analytical models using machine learning with SAS Model Studio, as shown in Chapter 10.

Make the most of SAS data and reports in Microsoft 365 apps, like Excel and PowerPoint, using SAS for Microsoft 365. Check out Chapter 13 to learn more about that.

Create amazing reports using SAS Visual Analytics, covered in Chapter 14.

Checking Out Real-World Success Stories

As a long-time SAS user and employee of SAS, I have visited hundreds of customers and seen many real-world SAS success stories. From forecasting and data management to machine learning and beautiful reports, SAS can meet just about any need you can imagine. To read a wide array of detailed SAS case studies, use your favorite web browser and visit www.sas.com/success.

Chapter 2

All Shapes and Sizes: Your SAS Is Beautiful

IN THIS CHAPTER

Bullet Exploring the most common SAS interfaces: SAS Enterprise Guide and SAS Studio

Bullet Practicing with SAS tasks and a bit of code

Bullet Understanding how your SAS setup affects the way you work

In the early days of computing, SAS was the exclusive province of the geekiest statisticians and programmers. You could analyze data with SAS only if you knew how to prepare a set of punch cards with your program instructions. But today SAS offers a wide range of interfaces, from friendly point-and-click to code-centered workspaces.

In this chapter, you can learn about the many ways you can access SAS. Whether you're working on a desktop PC, in the cloud, or on a mobile device, SAS has an interface for you. You might even use multiple interfaces, depending on your tasks and your circumstance.

Introducing SAS Enterprise Guide, the Swiss Army Knife of SAS

Looking at the wide array of capabilities that SAS Enterprise Guide encompasses, we can confidently call it the Swiss army knife of SAS. Just like a Swiss army knife, SAS Enterprise Guide is handy in lots of situations and offers a surprising array of options in a simple-to-learn package.

SAS Enterprise Guide is a ubiquitous SAS interface that almost every SAS customer has access to, in one way or another. It’s included with SAS for Microsoft Windows (sometimes called PC SAS), which is a local copy of SAS for your PC that works like your own personal SAS server. Universities teaching statistics courses and independent professionals learning SAS use SAS Enterprise Guide to access SAS OnDemand over the Internet, where SAS (the company) hosts the SAS server. Many companies also license SAS Enterprise Guide to allow their users to work with remote Windows, Unix, or mainframe SAS servers that they configure and maintain. Whichever configuration of SAS you use with SAS Enterprise Guide, most of the functionality is the same; the difference is whether the processing is performed on your PC or on a remote computer.

Remember This book addresses SAS Enterprise Guide 8.4 or later, which works with SAS 9.4 and SAS Viya.

Using SAS Enterprise Guide for the first time

When you first install and use SAS Enterprise Guide, the interface looks like Figure 2-1. This is the default, out-of-the-box view.

FIGURE 2-1: The welcoming SAS Enterprise Guide start screen.

The interface contains familiar elements, such as a top-level menu and a toolbar. Don't let this simple façade fool you, though. Beneath the menus and widget panes are hundreds of tasks and functions that await your command.

SAS Enterprise Guide supports two ways of working: using a project workspace or bypassing the project work mode.

Using a SAS Enterprise Guide project. A project is handy for organizing your work. A project may contain SAS programs, data shortcuts, tasks such as analytical steps or query steps, and one or more Process Flow diagrams that help you keep everything straight.

Tip Use a project when you want to build a repeatable series of steps that you might need in the future, whether that's tomorrow or next month or next year.

Some SAS Enterprise Guide features require a project, such as interactive tasks or query steps. A project file is saved as a document with a file extension of .egp (Enterprise Guide Project — get it?). It's easy to open the project again later to pick up where you left off.

Skipping the project. Sometimes you want to simply open and view data, or open or create a SAS program to run. For these simple operations, a project file isn't required. If you don’t need tasks or flows, you can jump in and out of SAS Enterprise Guide without the overhead of a project file.

Making yourself at home: Customizing your view

If you plan to spend any appreciable amount of time in SAS Enterprise Guide, you should spend a few moments to customize the workspace according to your preferences.

For many users, the first thing they want to enable is dark mode. Like most productivity applications these days, SAS Enterprise Guide includes a dark theme that you might find is easier on your eyes.

To set the appearance theme for SAS Enterprise Guide, follow these steps:

Choose Tools ⇒ Options from the main menu.

The Options window offers hundreds of preferences that you can set. It's worth exploring all of these later, but for now you're on the hunt for one specific setting.

Choose the General category.

Under the Visual Experience heading, you’ll see a single selection for Color Theme. The default theme is Illuminate (Light).

Choose Ignite (Dark) from the drop-down list and then click OK.

The effect is immediate, and the SAS Enterprise Guide window transforms to a deep midnight blue.

Tip Use Ctrl+F2 as a keyboard shortcut to toggle between the Ignite (dark) and Illuminate (light) themes.

You can arrange the SAS Enterprise Guide windows in an infinite array of combinations. The easiest way to see this in action is to run a SAS program that creates a variety of outputs — this creates plenty of windows and tabs to play with. (Don't worry if you aren't an experienced programmer; Chapter 4 introduces you to the basics of SAS programming.) The next steps include everything you need.

To create output with a sample SAS program:

Choose File ⇒ New ⇒ Program from the main menu.

An empty Program window appears, a blank canvas for your code creation.

In the Program window, type the following program statements:

ods graphics on;

proc freq data=sashelp.cars;

  table origin / out=counts plots=freqplot;

run;

This simple program tells SAS to generate frequency counts for one variable in a sample data set. It saves the Counts data to a new data set and creates a simple listing and plot for your review.

Click Run on the Program toolbar.

It may take a moment to connect to your SAS environment and process the code, but in less than a minute, you should see the results.

Remember The Program window includes several tabs with the additional content. In addition to the original Code tab, you see tabs for Log, Results, and Output Data.

Click-and-drag the Log tab.

As you drag the cursor, the Log tab tears away from its docked position. A position indicator shows the potential docking options to place the Log tab and customize your view. Hover the cursor over the position indicator to preview how the window will be docked when you release it.

Drag the Log tab over the Code tab and use the position indicator to place the Log tab at the bottom, and then release. The Code tab splits horizontally to create a space for the Log tab.

Tip You can also float a tab or window without docking it. This allows you to place your SAS Enterprise Guide windows anywhere on your desktop, and even arrange them across multiple displays. This is a true power-user maneuver!

Click-and-drag the Output Data tab.

Just as you did with the Log tab, use the position indicator to place the Output Data tab and dock it to the bottom region, this time below the Results tab. When you release the mouse button, you should have a window arrangement that looks like Figure 2-2.

Take a moment to admire your work. The next step is to practice resetting your custom view.

Choose View ⇒ Program Tab Presets ⇒ Standard.

The Program window layout snaps back to its original arrangement.

Remember The Program Tab Presets menu offers several different window layouts that SAS users have found to work well for them. Feel free to try these on for size to see how you like them.

FIGURE 2-2: A quad-box arrangement of the essential SAS elements: code, log, results, and data.

Tip Every window in SAS Enterprise Guide is movable, dockable, and floatable. This provides all the flexibility you need to arrange your workspace to fit your needs. As you play with the windows and tabs, you might find yourself stuck with a layout that feels hard to undo. When this happens, choose View ⇒ Reset Default Layout to return to the original start position.

Saving your work for later

After running a program in SAS Enterprise Guide and taking pride in your results, you have several choices for what to do next:

You can exit the application and discard your work.

You can save the program as a new program file, with a .sas file extension, so that you can call it up later in any SAS application.

You can save the program and its results in a new SAS Enterprise Guide project file. Project files allow you to keep multiple programs and tasks together, along with the results from the last time you ran them.

Each of these options is valid and useful. There are no wrong answers!

The following steps pick up with work from the previous section, where you have a SAS program that you ran and created some output. To save a new project file with an existing SAS program and results, do the following:

Choose File ⇒ New ⇒ Project.

A new project workspace is created. You see a few subtle changes in the SAS Enterprise Guide windows.

First, the main window title changes to have the word Project displayed. Project is the name of your project until you save it permanently with a different name.

Second, you see the structure of the project on the Project tab (docked in the upper left corner, by default). At this point, the project is empty.

Right-click on the Program