I recently read an interesting article in The Economist, where they describe "The Big Mac index." This is an index they invented as a lighthearted guide to compare currencies in different countries. In their article they create a multi-panel display (similar to a dashboard) where they compare the index for several countries using
Are you an NFL fan, or curious about analyzing social media data? -- Well, in either case, this blog's for you! I recently read a fascinating Facebook article that included a U.S. county map showing which NFL (U.S. football) team had the most 'likes' in each county (based on ~35 million
We’re just coming back from SAS Global Forum, and what a show! SAS Books was there to provide users with the highest-quality resources for learning SAS, and our users were there to tell us what new books they were most looking forward to reading. Kevin Smith's PROC TEMPLATE Made Easy:
I recently received this interesting question regarding Multilevel Models after one of my last blog posts: Question: Can you tell me when a multilevel-model is not appropriate? I have data that by design is clustered but the random intercept in the null model is not significant. I have seen advice
In the previous blog on CLASS variables, we developed the idea of creating design variables and examined GLM and reference coding. Another coding scheme, known as ‘Effect Coding’ or ‘Deviation from the Mean Coding’ is also commonly used. Consider our previous scenario of modeling the average amount spent on a
I haven't seen an official definition of 'infographic' that I really like ... but in my mind it's something 1/2 way between data visualization & artwork. It borrows elements from graphs & dashboards, and combines that with an artistic poster. If you perform a Google image search on infographic you'll see
While many analysts understand how to interpret the parameter estimates from linear regression with continuous input variables, they may feel less comfortable with parameter estimates from models with categorical inputs. SAS modeling procedures (such as PROC REG and others) need numerical information to represent all inputs—including classification variables. Suppose we
I recently attended the O'Reilly Tools of Change for Publishing Conference in New York, and I have to confess, I had a Twitter eureka moment. I was sitting in a conference room, waiting for the next session to start and reading tweets from a publishing industry contact I've longtime admired
This week's SAS tip is from Lauren Haworth, Cynthia L. Zender, and Michele Burlew's book Output Delivery System: The Basics and Beyond. This monumental guide is packed with a wide-array of techniques and examples. As SAS programmer Christine Iodice said, "This book is one-stop shopping for all your ODS needs!"
Multilevel models (also called hierarchical linear models) are used to analyze clustered or grouped data, as well as longitudinal or repeated measures data. Consider the simple scenario shown below, where Y is continuous and is shown as a function of a continuous predictor variable, X (which has been standardized). If
