Analysis of Probability Surveys using SAS®
Description
Scientific probability surveys based on complex sample designs require special methods to make statistically valid inferences from the sample to the study population. Researchers must analyze the data in ways that reflect the complex features of the sample design such as stratified selection, clustering, and unequal weighting.
The workshop will cover data exploration and descriptive statistical methods used in probability survey analysis. Linear and logistic regression and survival analysis will also be discussed. Different variance estimate methods, including Taylor Series, Balanced Repeated Replication, and Jackknife will be included.
Public use health surveys, such as the National Health and Nutrition Survey and others, will be used in the demonstrations. The exploratory and descriptive methods will be demonstrated using SAS procedures SURVEYMEANS, SURVEYFREQ and statistical graphics procedures. The regression demonstrations will use SAS procedures SURVEYREG, SURVEYLOGISTIC, and SURVEYPHREG.
Who should take the workshop?
Individuals experienced in classical regression methods that want to learn how to analyses complex probability survey data.
Materials
A workshop handout and the demonstration data and programs will be distributed to participants at the beginning of the workshop. Participants may bring their laptop and follow along with the demonstrations. SAS products BASE, STAT, and GRAPH version 9.3 are required for all of the demonstrations. Participants with SAS 9.2 will be able to follow along on the majority of the demonstrations.
Schedule
Sunday, 9 June, 2013. 9:00 AM to 5:00 PM with an hour lunch break at noon.
Short Course Instructor
Dr. Robert M. Lucas, Director, Analytical Education, SAS, has a PhD in Statistics from Colorado State University with more than 30 years’ experience as an applied statistician. Dr. Lucas worked for 17 years at Research Triangle Institute applying complex probability sampling and analysis techniques to collect and analyse data for a broad range of scientific and business problems. During his 16 years at SAS Institute, Dr. Lucas has developed and taught courses on advanced statistics (including designing and analyzing complex probability surveys), time series, data mining, and mathematical optimization. Dr. Lucas has also provided customized training or consulting to customers from many industries including government, pharmaceuticals, banking, manufacturing and retail.
