7月 232010
 
Q: I would like to have a glossary of technical terms.

A: Almost every book or book series contain a glossary of terms related to product or topic being documented. SAS documentation includes a Base SAS Glossary. This glossary a great place to get started with SAS terminology.

I recommend these glossaries for information about terms specific to an operating system:

If you are looking for more general technical terms, you may also want to search Wikipedia. They have two categories that may be of interest: Technology and applied sciences and Mathematics and logic.

Where do you go to learn more about a term or technology?
7月 222010
 
Our “Nuts & Bolts of Social Media” video series carries on with a new interview between SAS’ Deb Orton and Gary King, CIO of national clothing retailer Chico’s.

Gary begins with a brief story of how Chico’s started as a small store selling folk art (Really? Yes, really.), before transforming into an apparel company with three brands (Chico's, White House | Black Market and Soma Intimates) and 1,100 stores across the US and Puerto Rico.

Gary goes on to discuss the demographics of their brands, and the challenges of a constantly changing marketplace.

“The advent of the Internet,” Gary says, “was a huge shift in the way people shopped. We spend a lot of time now browsing before we buy, and that has radically changed the concept of shopping.” The good part, for Chico’s anyway, is customers still want to touch and feel clothing – which makes Chico’s in-store experience tremendously important.

But don’t think Chico’s ignores the Internet or Social media.

On the contrary, Social media is a huge focus. All three brands are on Facebook, and have been for years.

Gary related one successful project, where their intimate apparel brand Soma hosted a four-hour Facebook pajama party where fans could “celebrate and share their thoughts about their favorite pajamas, movies, stories and recipes, as well as participate in personality quizzes and surveys and chat with Soma Intimates style experts.”

In another example, the White House | Black Market brand president incentivized people to participate in a “what color underwear are you wearing” survey on Facebook by giving away a gift card and shopping spree.

Deb and Gary went on to discuss who should ‘own’ Social media organizationally (“everyone” says Gary), what the future of Social media looks like (social media will evolve in the same way fashion does), what Social media IT implications there are (many).

Before closing, Gary offers two practical Social media tips:

  1. Embrace the Social media space. From an IT standpoint don’t keep it out, bring it in. And,
  2. Find the champions inside your organization who are the conduits to the Social media space. Partner with them to support, enable, and create the mechanisms by which they can be more effective.

Enjoy the video!

7月 222010
 
A few days after I posted part 1 of this blog post,an interesting message popped up on Twitter from @annmariastat:

Confused. If you can get #SAS certification in 3 months what exactly are you being certified as? How much can anyone learn in 3 months?

A fair question, and without trying to brag, I'd like to say that I can learn a lot in three months. It just takes some dedicated time and hard work. I spent six days in class (Programming 1 in March and Programming 2 in May), wrote lots of programs, and studied for ten hours/week for five weeks. It reminds me of my college days where terms were ten week quarters rather than the traditional collegiate semester.

So, might I have any advice for someone preparing for SAS Base Certification? I'm glad you asked:

1) Study within the exam objectives. The exam objectives define the content that will be tested. You may be a very good programmer and proficient in PROC SQL and macros, but if you can't read a raw text file or know the difference between a Do While and Do Until loop, you will struggle with the base certification exam. Focus your preparation on the exam objectives.

2) Understand SAS code. The base exam covers a lot of content, and you have to know it well to complete the exam within the 2-hour time limit. For me, this meant I had to write flash cards from the course content. Writing down the syntax helped a lot, and then I could discard topics that I mastered and focus on the topics that caused me grief.

3) Understand the concepts. Code is important, but so is knowing what occurs when a program runs. What happens at compile time? What happens at execution time? How is the PDV populated? You will see snippets of code during the exam and must understand what will happen when it runs.

4) Program, Program, Program! Learn by doing. Hopefully your day-job provides you opportunity to write programs. In addition, there are a ton of exercises in Prog 1 & 2 courses, try working through all of them without referring to the course notes. Another good learning technique is what my friend Elizabeth calls "what if...." programming: take a working program and change it. Re-order the statements. Use a Select Group in place of a subsetting if statement. Add a syntax error and see what happens in the log file. Mistakes and errors can be the best teacher.

5) Check the calendar. I decided to prepare for certification during both the NHL and NBA playoffs, and I missed many games while studying at the dining room table...poor me. Well, at least I finished in time for the FIFA World Cup.

So, do you have any advice for technical people who need to earn SAS Certification credentials? What worked for you during your preparations?



7月 222010
 
Am I a new programmer? Let me see. I was a new programmer when I wrote my first program in college. I was a new programmer when I wrote my first SAS program during SAS Programming 1 class. And if I were to sit down to write a program today, I'd have to classify myself as a new programmer all over again. How long do I remain a new programmer? For me, it comes down to experience.

Back in January, I wrote a blog post that offered advice to the new SAS programmer. The idea was to help the new programmer move out of the new category and put them on the road to becoming an experienced programmer. If you haven't read it, visit Advice to a New SAS Programmer and have a read.

Today, I read a funny and interesting blog post by Dr. AnnMaria De Mars. She offers a few hints that help you determine if you are a novice programmer. Hop over to her blog to see if you are a novice programmer. Heed her words: "No one is allowed to feel bad for having made these mistakes. Everyone you meet will admit to having made the exact same errors at one time...."

I second her idea that you should never feel bad. However you should:
  • Be sure to learn from your mistakes.

  • Take the advice of more seasoned programmers.

  • Give back by offering advice to others who are in the same place you were just days or years before.

7月 202010
 
If you want to view SAS dataset in SPSS you can use GET SAS command of SPSS. Here is the syntax; get sas data='C:\data\class.sas7bdat'. For conversion of SAS to SPSS we need to see if any formats assigned to variables in the dataset or not. If there are no formats then we just follow following steps to convert SAS dataset to SPSS. **STEP1: Creating .xpt file of a SAS dataset using Proc COPY.** libname SAS 'c:\sas\data\'; libname SPSS xport 'c:\sas\data\class.xpt'; proc copy in=sas out=spss; select class; run; **STEP2: Use SPSS command to convert the transport format SAS file to SPSS;** You should use following commands to convert transport format file to SPSS data. get sas data='c:\sas\data\class.xpt'. execute. *******************************************************************************************; If there are formats then we need to convert the formats catalog to a SAS data set before converting the SAS dataset into a .XPT file. This has...

[[ This is a content summary only. Visit my website for full links, other content, and more! ]]
 Posted by at 7:27 上午  Tagged with:
7月 202010
 


If you want to view SAS dataset in SPSS you can use GET SAS command of SPSS. Here is the syntax; get sas data='C:\data\class.sas7bdat'. For conversion of SAS to SPSS we need to see if any formats assigned to variables in the dataset or not. If there are no formats then we just follow following steps to convert SAS dataset to SPSS. **STEP1: Creating .xpt file of a SAS dataset using Proc COPY.** libname SAS 'c:\sas\data\'; libname SPSS xport 'c:\sas\data\class.xpt'; proc copy in=sas out=spss; select class; run; **STEP2: Use SPSS command to convert the transport format SAS file to SPSS;** You should use following commands to convert transport format file to SPSS data. get sas data='c:\sas\data\class.xpt'. execute. *******************************************************************************************; If there are formats then we need to convert the formats catalog to a SAS data set before converting the SAS dataset into a .XPT file. This has...

[[ This is a content summary only. Visit my website for full links, other content, and more! ]]
 Posted by at 7:27 上午  Tagged with:
7月 202010
 
Back in April we hosted Text Analytics 101, the first in this year’s Applying Business Analytics Webinar Series. As many of you know, organizations today are faced with a flood of text-based content, a shortage of domain and subject-matter experts and an inability to analyze data in an automated, consistent manner. So we created this 101 session to provide practical, accessible advice about the methods and technologies that will enable you to improve efficiencies, ease staff resources and seamlessly incorporate text-based insights for better decisions. SAS’ Kathy Lange & Fiona McNeill walked 350+ attendees through a Text Analytics overview.

We had registrations from the US and 40 other countries and attendees joined us from a vast array of industries including communications, education, Federal Government, Financial Services, Health and Life Sciences, Retail & Manufacturing and State and Local Governments. Of the 350+ attendees about 40% of them responded to the post survey questions and shared some interesting feedback with us regarding the stage of text analytics adoption that they are in. From the results it looks to me like majority are in initial investigation & some more 101 sessions might just be what folks need to help understand the landscape.

Other attendees were assessing vendors, enhancing existing methods, some were reviewing technologies and several were already implementing and a couple were already in a testing phase. How about your organization? What phase are you in?
7月 202010
 
/* Sample data set */ data missing; input n1 n2 n3 n4 n5 n6 n7 n8 c1 $ c2 $ c3 $ c4 $; datalines; 1 . 1 . 1 . 1 4 a . c . 1 1 . . 2 . . 5 e . g h 1 . 1 . 3 . . 6 . . k i 1 . . . . . . . . . . . 1 . . . . . . . c . . . . . . . . . . . . . . . ; run; *If you want to delete observation  if the data for every variable is missing then use the following code; *Approach 1: Using the coalesce option inside the datastep; data drop_misobs; set missing; if missing(coalesce(of _numeric_)) and missing(coalesce(of _character_)) then delete; run;  Pros: *Simple code Cons; *This code doesn't work if we want to delete observation based on specific variables and not all of them. *Approach 2:Using N/NMISS option inside the datastep; data drop_missing; set missing; *Checks the Non missing values using ; if n(n1, n2, n3, n4, n5, n6, n7, n8, c1, c2, c3, c4)=0 then delete; run; data drop_missing; set missing; *Checks the missing...

[[ This is a content summary only. Visit my website for full links, other content, and more! ]]
 Posted by at 1:41 上午
7月 202010
 


/* Sample data set */ data missing; input n1 n2 n3 n4 n5 n6 n7 n8 c1 $ c2 $ c3 $ c4 $; datalines; 1 . 1 . 1 . 1 4 a . c . 1 1 . . 2 . . 5 e . g h 1 . 1 . 3 . . 6 . . k i 1 . . . . . . . . . . . 1 . . . . . . . c . . . . . . . . . . . . . . . ; run; *If you want to delete observation  if the data for every variable is missing then use the following code; *Approach 1: Using the coalesce option inside the datastep; data drop_misobs; set missing; if missing(coalesce(of _numeric_)) and missing(coalesce(of _character_)) then delete; run;  Pros: *Simple code Cons; *This code doesn't work if we want to delete observation based on specific variables and not all of them. *Approach 2:Using N/NMISS option inside the datastep; data drop_missing; set missing; *Checks the Non missing values using ; if n(n1, n2, n3, n4, n5, n6, n7, n8, c1, c2, c3, c4)=0 then delete; run; data drop_missing; set missing; *Checks the missing...

[[ This is a content summary only. Visit my website for full links, other content, and more! ]]
 Posted by at 1:41 上午
7月 192010
 
Our newest book, Using R for Data Management, Statistical Analysis and Graphics, is anticipated to soon start shipping from Amazon, CRC Press, and other fine retailers.



The book complements our existing SAS and R book, particularly for users less interested in SAS. It presents an easy way to learn how to perform an analytical task in R, without having to navigate through the extensive, idiosyncratic, and sometimes unwieldy software documentation and vast number of add-on packages. Organized by short, clear descriptive entries, the book covers many common tasks, such as data management, descriptive summaries, inferential procedures, regression analysis, multivariate methods, and the creation of graphics.

Through the extensive indexing, cross-referencing, and worked examples in this text, users can directly find and implement the material they need. The text includes convenient indices organized by topic and R syntax, and presents example analyses that employ a single data set from the HELP study to demonstrate the R code in action and facilitate exploration. We also provide several case studies of more complex applications. Data sets and code are available for download on the book’s website.

To book tries to lucidly summarize the aspects of R most often used by statistical analysts. We believe that new users of R will find the simple approach easy to understand while more sophisticated users will appreciate the invaluable source of task-oriented information.

Note as of August, 2010: the book is now shipping from Amazon, with a discounted price.