Gross Alden L, Power Melinda C, Albert Marilyn S, Deal Jennifer A, Gottesman Rebecca F, Griswold Michael, Wruck Lisa M, Mosley Thomas H, Coresh Josef, Sharrett A Richey, Bandeen-Roche Karen
From the aDepartment of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD; bJohns Hopkins University Center on Aging and Health, Baltimore, MD; cDepartment of Neurology, Johns Hopkins School of Medicine, Baltimore, MD; dCenter of Biostatistics and Bioinformatics, University of Mississippi Medical Center, Jackson, MS; eDepartment of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD; fDepartment of Biostatistics, UNC Gillings School of Global Public Health, Chapel Hill, NC; and gDepartment of Medicine, University of Mississippi Medical Center, Jackson, MS.
Epidemiology. 2015 Nov;26(6):878-87. doi: 10.1097/EDE.0000000000000379.
The way a construct is measured can differ across cohort study visits, complicating longitudinal comparisons. We demonstrated the use of factor analysis to link differing cognitive test batteries over visits to common metrics representing general cognitive performance, memory, executive functioning, and language.
We used data from three visits (over 26 years) of the Atherosclerosis Risk in Communities Neurocognitive Study (N = 14,252). We allowed individual tests to contribute information differentially by race, an important factor to consider in cognitive aging. Using generalized estimating equations, we compared associations of diabetes with cognitive change using general and domain-specific factor scores versus averages of equally weighted standardized test scores.
Factor scores provided stronger associations with diabetes at the expense of greater variability around estimates (e.g., for general cognitive performance, -0.064 standard deviation units/year, standard error = 0.015, vs. -0.041 standard deviation units/year, standard error = 0.014), which is consistent with the notion that factor scores more explicitly address error in measuring assessed traits than averages of standardized tests.
Factor analysis facilitates use of all available data when measures change over time, and further, it allows objective evaluation and correction for differential item functioning.
在队列研究随访中，对结构的测量方式可能有所不同，这使得纵向比较变得复杂。我们展示了如何使用因子分析将不同访视中的不同认知测试组合与代表一般认知表现、记忆、执行功能和语言的共同指标联系起来。
我们使用了社区动脉粥样硬化风险神经认知研究（N = 14252）三次访视（超过26年）的数据。我们允许各个测试根据种族差异提供信息，种族是认知衰老中一个需要考虑的重要因素。使用广义估计方程，我们比较了糖尿病与认知变化的关联，使用一般和特定领域因子得分与等权重标准化测试得分的平均值。
因子得分与糖尿病的关联更强，但估计值周围的变异性更大（例如，对于一般认知表现，每年-0.064标准差单位，标准误 = 0.015，而每年-0.041标准差单位，标准误 = 0.014），这与因子得分比标准化测试平均值更明确地处理评估特质测量误差的观点一致。
当测量随时间变化时，因子分析有助于利用所有可用数据，此外，它还允许对项目功能差异进行客观评估和校正。
