Whittaker Tiffany A, Pituch Keenan A, McDougall Graham J
Department of Educational Psychology, University of Texas at Austin.
The University of Alabama Capstone College of Nursing.
J Consult Clin Psychol. 2014 Oct;82(5):746-59. doi: 10.1037/a0036664. Epub 2014 Apr 28.
When several continuous outcome measures of interest are collected across time in experimental studies, the use of standard statistical procedures, such as multivariate analysis of variance or growth curve modeling, can be properly used to assess treatment effects. However, when data consist of mixed responses (e.g., continuous and ordered categorical [ordinal] responses), traditional modeling approaches are no longer appropriate. The purpose of this article is to illustrate the use of a more suitable modeling procedure when mixed responses are collected in longitudinal intervention studies.
Problems with traditional analyses of such data are discussed, as are potential advantages provided by the proposed modeling approach. The application of the multiple-domain latent growth modeling approach with mixed responses is illustrated for experimental designs with data from the SeniorWISE study (McDougall et al., 2010). This multisite randomized trial assessed memory functioning of 265 elderly adults across a 26-month period after receiving either a memory or health promotion training program.
The latent growth models illustrated allow one to examine treatment effects on the growth of multiple mixed outcomes while incorporating associations among multiple responses, which allows for better missing data treatment, greater power, and more accurate control of Type I error. The interpretation of parameters of interest and treatment effects is discussed using the SeniorWISE data.
Multiple-domain latent growth modeling with mixed responses is a flexible statistical modeling tool that can have substantial benefits for applied researchers. As such, the use of this modeling approach is expected to increase.
在实验研究中，当随时间收集多个感兴趣的连续结果测量指标时，可以合理使用标准统计程序，如多变量方差分析或生长曲线建模，来评估治疗效果。然而，当数据包含混合反应（如连续和有序分类[序数]反应）时，传统建模方法就不再适用了。本文的目的是说明在纵向干预研究中收集到混合反应时，使用更合适的建模程序的方法。
讨论了对此类数据进行传统分析时存在的问题，以及所提出的建模方法的潜在优势。通过来自SeniorWISE研究（麦克杜格尔等人，2010年）的数据，举例说明了具有混合反应的多领域潜在生长建模方法在实验设计中的应用。这项多地点随机试验评估了265名老年人在接受记忆或健康促进培训计划后的26个月内的记忆功能。
所示的潜在生长模型允许研究人员在考虑多个反应之间关联的同时，检查治疗对多个混合结果增长的影响，从而实现更好的缺失数据处理、更强的检验效能以及对I型错误更精确的控制。使用SeniorWISE数据讨论了感兴趣参数和治疗效果的解释。
具有混合反应的多领域潜在生长建模是一种灵活的统计建模工具，对应用研究人员可能有很大益处。因此，预计这种建模方法的使用将会增加。
