Abstract
OBJECTIVE: This report compares results between survey analysis software and the National Cancer Institute Joinpoint Regression Software for trend analysis of survey data. The "National Center for Health Statistics Guidelines for Analysis of Trends" recommends that analysts use record-level data and survey analysis software to fit desired trend models of survey data. When changes in a trend will be assessed using piecewise regression models, the guidelines recommend that analysts use the most recent version of the Joinpoint software with aggregated data to identify the number and location of joinpoints, then survey analysis software with record-level data to obtain final slope estimates and to conduct tests of hypothesis for the model identified by the Joinpoint software. In practice, the Joinpoint software sometimes produces results that appear incongruent with those generated by the survey analysis software. The purpose of this report is to provide guidance for conducting trend analyses on NCHS survey data to handle and explain these apparent inconsistencies. This report should be considered a supplement to the "National Center for Health Statistics Guidelines for Analysis of Trends." METHODS: Cases were identified where apparent inconsistencies between the Joinpoint software and survey analysis software could occur. Plausible explanations for the apparent differences are discussed through text, examples, and frequently asked questions. Solutions are not provided; rather, recommendations, cautions, and additional information are provided to assist analysts in making the best decisions for their analysis and data. RESULTS: Most frequently, inconsistencies occur when the prespecified piecewise regression model provided by the Joinpoint software is estimated using survey analysis software and successive slopes are not statistically significantly different from one another, resulting in one or more joinpoints being removed from the final model. Potential explanations are divided into five main categories.