Analyzing complex survey data, Issue 71

Social scientists are demanding more analytic studies of social survey data in order to examine a variety of emerging issues. Answering this need, Analyzing Complex Survey Data offers an effective means of examining and analyzing complex surveys -- and how to overcome problems that often arise. It includes discussions on the choices involved in variance estimates, simple random sampling without replacement, stratified random sampling and two-stage cluster sampling, and outlines the different computer programs that are currently available. 1. Introduction -- 2. Sample Design And Survey Data -- Types Of Sampling -- The Nature Of Survey Data -- 3. Survey Data Analysis -- Adjusting For Differential Representation: The Weight -- Developing The Weight: An Example -- Assessing Loss Or Gain Of Precision: The Design Effect -- 4. Strategies For Variance Estimation -- Replicated Sampling: A General Approach -- Balanced Repeated Replication -- Jackknife Repeated Replication -- The Taylor Series Method -- 5. Preparing For Survey Data Analysis -- Importance Of Preliminary Analysis -- Choices Of The Method For Variance Estimation -- Data Requirements For Weights And The Design Effect -- Available Computing Resources -- 6. Conducting A Regression Analysis -- The Linear Model For Complex Survey Data -- An Example Of Regression Analysis From Nhanes Ii -- 7. Conducting Contingency Table Analysis -- The Weighted Least Squares Method For Complex Survey -- The Wls Method: An Example From Nhanes Ii -- Log-linear Models For Complex Survey Data -- Log-linear (logit) Models: An Example From Nhanes Ii -- Wls Method And Log-linear Models: Which To Use? -- 8. Concluding Remarks. Eun Sul Lee, Ronald N. Forthofer, Ronald J. Lorimor. Includes Bibliographical References (p. 75-78).