Moving your clinical graphics from device based PROCs to template driven graphics

SAS Programming in the Pharmaceutical Industry, Second EditionIn writing the second edition of SAS Programming in the Pharmaceutical Industry, I knew that I wanted to replace the device-driven SAS/GRAPH figures with the new ODS template-driven graphics procedures. The latest developments in SAS graphics involve the template-driven procedures and tools found in SAS ODS graphics (i.e., ODS Graphics Procedures, Graph Template Language (GTL), ODS Graphics Editor, and ODS Graphics Designer), which are included as part of a Base SAS license. The second edition of my book will show you how to employ these tools to create common clinical trials graphics. Here are a few things to keep in mind with template-driven graphics:

SAS provides graphics help, if you need it

You don’t have to become a GTL wizard to use SAS ODS graphics. You may be able to get your graph straight from a SAS procedure by simply turning on ODS graphics. If not, maybe one of the new SG graphics procedures will do what you need with fairly simple procedural syntax. If that doesn’t work, then you can use the ODS Graphics Designer to write your GTL code for you.

Some graphs are much easier to produce now

The new template driven graphical procedures have made our work easier. Forest plots, created with PROC SGPLOT or PROC LOGISTIC directly, are much easier to produce than they were in PROC GPLOT. Survival or failure plots produced during survival analysis are easy to create now either through PROC LIFETEST directly, or through PROC SGPLOT. The new survival plots even make it easy to include the number at risk on the bottom of the figure.

ODS Graphics templates allow for extensive customization

The ODS templates that you can define via PROC TEMPLATE allow you to fully customize your ODS template driven graphics. Also, if you miss the customization flexibility found in the Annotate Facility and annotate datasets from SAS/GRAPH, don’t worry, because there is now an analogous SG annotate facility as well.

Post a Comment

SAS author's tip: Crafting the decision tree structure for insight and exposition

Decision Trees for Analytics Using SAS Enterprise MinerThis week's SAS tip is from Barry de Ville and Padraic Neville's enterprising new book Decision Trees for Analytics Using SAS Enterprise Miner. With their combined vast expertise, De Ville and Neville have created a comprehensive guide to decision tree theory, use, and applications.

If you're interested in this week's free tip and want to learn more about the topic or book, visit our online catalog. You'll find a free book excerpt, example code and data, and more...

The following excerpt is from SAS Press authors Barry de Ville and Padraic Neville and their book “Decision Trees for Analytics Using SAS Enterprise Miner” Copyright © 2013, SAS Institute Inc., Cary, North Carolina, USA. ALL RIGHTS RESERVED. (please note that results may vary depending on your version of SAS software).

Crafting the Decision Tree Structure for Insight and Exposition

Here we talk about the art of growing a decision tree for insight (extracting conceptually appealing information from data) and exposition (displaying the decision tree results in a form that communicates insight and informs policy and planning). The goals of insight and exposition differ and complement the goal of using decision trees to extract key relationships and predictive structure from data (which satisfies the requirement of maintaining an overall form, structure, and sequence of branch formation in the decision tree).

You might find it useful to think in terms of telling a story when growing a decision tree to reveal information and communicate results. The storyline and theme needs to support the conceptual framework of the audience. The story illuminates key interests and potentially contains a few plot twists that upset conventional ways of looking at the data and therefore pave the way for the development of insight and improved understanding.

In telling the story, it is important to have a beginning, middle, and end. The story should be told in terms that are familiar to the audience. And, while it can be useful to include a few twists in the plot, the insights that are revealed should be plausible. The best way to ensure a good story line is to construct the decision tree in-line with the conceptual model of the area that the decision tree is designed to illuminate. For example, if you are looking at purchase behavior, then the attributes of the decision tree need to reflect concepts that are relevant to purchasing behavior. If the application is quality control and you are looking at part failures, then the attributes of the decision tree need to reflect concepts that are relevant to part failures.

Every application area in which expository decision trees can be deployed is characterized by concepts that either explicitly or implicitly exist in the minds of the audience. Concepts have been measured and reflected by different entities in the data set and can be linked differently, particularly if the entities suggest different links based on the empirical characteristics of the data. However, there is always an underlying story line, a presumed relation, and a presumed cause and effect or sequence of causes and effects. Some decision trees are more comprehensive than others. One characteristic of a comprehensive decision tree is that the data in the conceptual area that is being explored contains a range of related attributes. As a result, the story that is told by the decision tree reflects both a plausible set of relationships and a fairly complete set of relationships (i.e., to the extent possible, the substantial drivers of the relationships being explored have been included).

To build this type of decision tree for exposition, the following tasks should be performed:

1.) Define the business and/or scientific question.

2.) Determine the main features of a conceptual model that describes the major constructs
involved in the question resolution.

3.) Determine the data measures, fields, and field values that will become the operational
components of the conceptual model when the model is translated to form the decision tree.

4.) Develop the story line (i.e., the presumed sequence of events as the operational components
unfold to tell the story).

5.) Determine key relationships or potential plot twists to be examined in shaping the form of the
decision tree.

6.) Translate the tree results into a form that illuminates the original question.

Post a Comment

Write a book for SAS

Have you written a popular SAS Global Forum paper? Have you shared a winning case study with your colleagues? Have you talked about a cool, new feature you found in SAS? Well, share it with the world!

SAS Press can help you share your knowledge and expertise worldwide. We’ve published more than 250 “how-to” books on SAS software. Our titles cover programming, data mining, statistics, analytics and JMP. If you’ve used SAS to solve a business problem, in any of these areas, tell us about it.

We’ll help you prepare a book proposal, and get it reviewed within SAS. If it’s accepted, you will join the family of SAS Press authors. Hurry and send in that idea, before someone beats you to it!

Post a Comment

3 reasons you should read ODS Techniques

The Output Delivery System (ODS) is a very large topic and it can sometimes be difficult to find out if something is even possible from the reference documentation.  My new book ODS Techniques: Tips for Enhancing Your SAS Output takes a cookbook approach to various areas in ODS and introduces you to features from the common to the rather esoteric.  The code samples for each tip can be run as-is so that you can see the code working in action right away, and hopefully, it will send you in directions that you might not have thought were possible in the world of ODS.

1.) From beginner to advanced, there is something for everyone in this book.

There are many basic tips in this book that can be taken advantage of immediately by any level of user.  But there are also many advanced tips that may take a little longer to sink in.  The intent of the book is to show you what kinds of things are possible and inspire you to explore some of the more mystical areas of ODS.

2.) You can read just the parts that interest you.

This book is laid out so that all of the tips are independent.  You can jump around in the book as much as you want, read the parts you are currently interested in, and save the rest for later.  The code samples for each tip can also be run independently.  Just copy and paste.

ODS Techniques: Tips for Enhancing Your SAS Output3.) You’ll be able to impress your friends and coworkers.

I guarantee that there are things in this book that you have not seen before.  There are many new features in ODS that haven't gotten a lot of press.  This is your chance to get ahead of the game and let the others play catch up.

This book is intended to point you in directions you may not have otherwise considered, but that isn't the end of the adventure.  My point of view is just the start.  Just combine the tips in this book with your own imagination and see where it leads you.

Post a Comment

Highlights of the SAS Global Forum 2014 conference

After just returning home from the greatest SAS conference on earth, I wanted to share a few highlights from the 2014 SAS Global Forum (SASGF) conference, where more than 4,500 attendees from every corner of the globe took part in a multi-day SAS-fest. For four days, from sun-up to well after sun-down, conference attendees heard about a number of new product introductions, features and solutions, and learned countless tips, tricks, shortcuts, programming techniques, and other content.

The 2014 SAS Global Forum (SASGF) conference took place in our nation’s capital in Washington, DC from Sunday, March 23 through Wednesday, March 26. Neither rain, sleet, or snow could prevent conference goers from attending, learning, and networking with like-minded colleagues. Attendees gathered to watch and listen to speakers in the many informative and content-filled sessions, including the opening session, presentations, papers, keynotes, hands-on workshops (HOWs), demonstrations, e-posters, mixers, networking events, and other venues. In fact, many sessions were so well attended that not an empty seat could be found.

So, what were the highlights from the 2014 SAS Global Forum conference? I’ve listed a series of clickable links, below, to enable you to relive and enjoy the conference experience. Using your favorite web browser, access an overview of the 2014 conference highlights; the complete list of published conference papers; select presentations, demos and interviews featuring conference leaders, presenters and the SAS staff; and a brief look at what you can expect at next year’s 2015 SAS Global Forum conference in Dallas, Texas.

Enjoy, learn and experience the greatest show on earth for SAS users!

SAS Global Forum 2014 Conference Overview

SAS Global Forum 2014 Live and On Demand

SAS Global Forum 2014 Conference Published Papers

SAS Global Forum 2015 Preview

 

 

Post a Comment

Grasp some key statistical procedures used by researchers with latest book

Is there a good "fit" between the proposed theoretical model and the data actually obtained? How large are the path coefficients that represent the effects of the antecedent variables on the consequent variables? Do the antecedent variables account for a large percentage of variance in the consequent variables?

Norm O’Rourke and Larry Hatcher’s new book A Step-by-Step Approach to Using SAS for Factor Analysis and Structural Equation Modeling, Second Edition gently guides users through performing some of the most sophisticated data analysis procedures used by researchers today and can help answer these questions plus more.  Structural equation modeling is one of the most important statistical procedures for testing complex causal models with correlational data.     

Unlike most existing texts, this book provides clear guidelines to determine sample size requirements for path analysis, confirmatory factor analysis (CFA), and structural equation modeling (SEM).  For example, it provides syntax to estimate the statistical power of completed studies.  It also provides syntax to estimate minimum sample size requirements for planned research to have confidence in the results (i.e., sample sizes required for CFA and SEM). 

Most of the book's examples are drawn from the social and behavioral sciences, but the statistical procedures it covers will be useful to students and researchers in any discipline that makes use of correlational (i.e, nonexperimental) data: business, education, nursing, public health, and biology.

Determining the sample size required to achieve a specific level of statistical power is important to researchers preparing grant proposals, for graduate students completing dissertations, and even for upper-level undergraduates completing honors theses. This is one of the few books that makes these procedures possible within the framework of structural equation modeling.

Delve into the world of measurement and structural equation modeling and uncover solutions to problems encountered in real-world research with A Step-by-Step Approach to Using SAS for Factor Analysis and Structural Equation Modeling, Second Edition.

Read the free excerpt to begin your journey.

Post a Comment

SAS author's tip: Displaying multiple box plots for each value of a categorical variable

SAS Statistics by ExampleThis week's SAS tip is from superstar author Ron Cody and his very popular book SAS Statistics by Example. Ron has been using SAS (and writing about SAS) for a long time. And he communicates his vast expertise in a friendly, easy-to-understand manner. If you've used any of Ron's books, I'm sure you'll agree.

The following excerpt is from SAS Press author Ron Cody's book “SAS Statistics by Example” Copyright © 2011, SAS Institute Inc., Cary, North Carolina, USA. ALL RIGHTS RESERVED. (please note that results may vary depending on your version of SAS software).

Displaying Multiple Box Plots for Each Value of a Categorical Variable

If you want to see a box plot for each value of a categorical variable, you can include the option CATEGORY= on the HBOX or VBOX statement. The example that follows uses the original Blood_Pressure data set (without the outliers) and displays a box plot for each value of Drug.

Program 2.10: Displaying Multiple Box Plots for Each Value of a Categorical Variable

title "Box Plots of SBP for Each Value of Drug";
proc sgplot data=example.Blood_Pressure;
hbox SBP / category=Drug;
run;

The HBOX option CATEGORY= generates a separate box plot for each of the three Drug values:

If you like the subject of this week's tip or just want to learn lots more about Ron Cody, visit his author page.

Post a Comment

At least 6 reasons to visit the Publications booth at SAS Global Forum

I know you’re going to be very, very busy at SAS Global Forum. But there are at least 6 good reasons why you should add the Publications booth to your must-see list:

1.)    Books, books, and more books. For purchase onsite, for order, for preview. On virtually any SAS topic you can think of. And at a 20% discount.

2.)     Meet some really cool SAS authors.  They’re often hanging around (when not presenting) and will definitely be in our area during the Monday night reception in the demo room from 6:00-7:30. Have a photo taken, get a book signed, ask how they got started writing…

3.)    Talk to us about new book topics you’d like to see us cover. Or, better yet, talk to us about writing your own book for us. One of our acquisitions editors will always be on hand. Plus, we’re hosting two informal chats about getting published. Join us on Monday, March 24 from 6:00–6:30 p.m. or on Tuesday, March 25 from 3:00–3:30 p.m.

4.)    Learn the latest and greatest in SAS Documentation. Our team looks forward to sharing new features and helping you find and use the information you need.

5.)    Play the fun Publications game. While I won’t reveal the theme of the game in this post, let’s just say that you should elect to stop by and check it out. Plus there’s a leaderboard, a prize for the winner, and some unique photo opportunities.

6.)    Get to know our staff and tell us how we can better help you. A highlight for all of us attending the conference is to meet and talk with you. :)

I’m excited about seeing many of you in a couple of days! Let's just hope it doesn't snow.

 

Post a Comment

Worth a shopping trip!

SAS Books storeSAS has launched the first phase of a new shopping experience for SAS users. In phase 1, you can buy books and some software by shopping in our new SAS store. The long-term goal for SAS is to have a single shopping experience for all your SAS shopping needs.

Two things that should send you directly to www.sas.com/store under the books section are eBooks and free shipping. Yes, we said free shipping!

Come see our new site today and revisit us frequently over the next year. We will continue to add products and functionality to the new store. Tell us what you think.

Post a Comment

Longitudinal data to improve education

Implement, Improve, and Expand Your Statewide Longitudinal Data SystemIf there is one game-changing advancement that can change the current realities of education and the future of how children learn, it is data. Schools are overflowing with data – attendance records, achievement data, even logs from mobile devices – and the questions remain: How can schools turn the data into actionable information? How can education systems create a culture that uses data to make decisions? How can the data be leveraged to make education better for today’s students, and generations to come? My new book Implement, Improve and Expand your Statewide Longitudinal Data System: Creating a Culture of Data in Education, coauthored with Armistead Sapp, aims to address these pressing questions.

What’s a statewide longitudinal data system?

Statewide longitudinal data systems (SLDSs) are growing in popularity and prevalence. Many states (including North Carolina) have been the recipients of federal grant money to establish and enhance their SLDSs, toward the goal of having their data linked and accessible. SLDSs aim to connect data from educational entities, large systems that track student data from preschool through college and workforce across the state. Primarily, SLDSs prevent data siloes from existing, promoting sharing data with entitled stakeholders to enable smarter educational decisions. All of this sharing is within student privacy laws and FERPA, and indeed, a strong SLDS can enable better compliance to these laws.

Wait, what's longitudinal data?

Longitudinal data are repeated measures of the same information over time. It could be attendance records, test scores, discipline data – anything measured and stored. Having more data in one place enables a more complete picture of each student.

Well, that’s great, but don’t we have that? What can an SLDS do that other data systems can’t?

SLDSs offer substantial improvements over previous data systems, ones that promise to change the way education is conducted for the better. Data driven decisions, maximization of resources and improved student outcomes all begin with investment in a culture of data from the leadership level to the teachers in the classroom.

With longitudinal data, leaders can see patterns and trends: are reading scores improving overall at a certain school? District wide? With enough data, it might even allow leaders to figure out why the scores are changing. The breadth of data contained in an SLDS further allows for teachers to have better data available to them, and make decisions based on what was successful for other students with similar circumstances. Tools like early warning systems can be enabled with longitudinal data to predict something like the likelihood a child will drop out of high school as early as elementary school. It offers an opportunity to create a true permanent record for each student, rich with much more information than past systems. An SLDS is a resource for the state.

There’s no disagreement that schools are managing more than they ever have before, and at much higher stakes. We are demanding higher test scores, improvements in graduation rates and literacy, and more effective teachers and often cutting resources available. It’s easy to see how efficient use of data could fall through the cracks. However, the missing link is that data can make educational systems and decisions more effective and easier, leading to better use of resources. Indeed, for all of the data currently in schools, it remains the most underutilized tool in the toolbox for the education system. With high levels of investment from state and federal government in SLDSs, it’s vital for educators and administrators embrace a culture of data.

Learn even more about longitudinal data in education with this short and informative video:

Read more about the innovative new book Implement, Improve and Expand Your Statewide Longitudinal Data System: Creating a Culture of Data in Education.

Post a Comment