Kattamuri S. Sarma, PhD, is an economist and statistician with 30 years of experience in American business, including stints with IBM and AT&T. He is the founder and president of Ecostat Research Corp., a consulting firm specializing in predictive modeling and forecasting. He has been a SAS user since 1992, and he has extensive experience with multivariate statistical methods, econometrics, decision trees, and data mining with neural networks. Dr. Sarma is a SAS Certified Professional and a SAS Alliance Partner. Dr. Sarma received his PhD in economics from the University of Pennsylvania, where he worked under the supervision of Nobel Laureate Lawrence R. Klein.
To make accurate predictions, it is necessary that the sample data you use for model development is compatible with the target population. The distribution of each input used in the model should be similar in the sample and the target population. In your model you should include only those variables
In this post I describe the important tasks of data preparation, exploration and binning.These three steps enable you to know your data well and build accurate predictive models. First you need to clean your data. Cleaning includes eliminating variables which have uneven spread across the target variable. I give an
To build accurate predictive models you need clean data. Having a good understanding of the data helps you to interpret the models correctly and enables you to make sound intelligent business decisions. SAS Enterprise Miner can help you to achieve the twin goals of improving the quality of data and
