Online Program

The National Center for Health Statistics Guidelines for the Analysis of Trends (303787)

Keywords: nonlinear trend, joinpoint regression, linear spline regression, health surveys, vital statistics

Many reports present analyses of trends over time based on multiple years of data from surveys or administrative records. This is especially true at the National Center for Health Statistics (NCHS). Trend analyses of NCHS data involve analytic choices that can lead to different conclusions about the trends. This talk will summarize the recent NCHS publication: "National Center for Health Statistics Guidelines for Analysis of Trends" which covers the issues that should be considered when conducting a time trend analysis using NCHS data and presents general guidelines for making trend analysis choices for many types of data. Trend analysis issues discussed include: choosing the observed time points to include in the analysis, considerations for both survey data and administrative records data (such as vital systems), a general approach for conducting trend analyses, assorted other analytic issues, such as the use of logistic regression, ordinal regression, and joinpoint regression. In all, 12 general guidelines for trend analyses are outlined, examples of analyses using NCHS survey and vital records data are provided.