Measurement Error and Methodologic Issues in Analyses of the Proportion of Variance Explained in Cognition.

IF 5.4 2区心理学 Q1 NEUROSCIENCES

Neuropsychology Review Pub Date : 2024-11-20 DOI:10.1007/s11065-024-09655-1

Emma Nichols, Vahan Aslanyan, Tamare V Adrien, Ryan M Andrews, David W Fardo, Brandon E Gavett, Theone S E Paterson, Indira C Turney, Christina B Young, James O Uanhoro, Alden L Gross, For The Alzheimer's Disease Neuroimaging Initiative

{"title":"Measurement Error and Methodologic Issues in Analyses of the Proportion of Variance Explained in Cognition.","authors":"Emma Nichols, Vahan Aslanyan, Tamare V Adrien, Ryan M Andrews, David W Fardo, Brandon E Gavett, Theone S E Paterson, Indira C Turney, Christina B Young, James O Uanhoro, Alden L Gross, For The Alzheimer's Disease Neuroimaging Initiative","doi":"10.1007/s11065-024-09655-1","DOIUrl":null,"url":null,"abstract":"<p><p>Existing studies examining the predictive ability of biomarkers for cognitive outcomes do not account for variance due to measurement error, which could lead to under-estimates of the proportion of variance explained. We used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (N = 1084) to estimate the proportion of variance explained by Alzheimer's disease (AD) imaging biomarkers in four cognitive outcomes: memory, executive functioning, language, and visuospatial functioning. We compared estimates from standard models that do not account for measurement error, and multilevel models that do account for measurement error. We also examined estimates across diagnostic subgroups (normal, MCI, AD). Estimates of the proportion of variance explained from multilevel models accounting for measurement error were larger (e.g., for language, 9-47% vs. 7-34% under standard modeling), with relatively greater differences between standard and multilevel measurement models for cognitive outcomes that have larger measurement error variance. Heterogeneity across subgroups also emphasized the importance of sample composition. Future studies should evaluate measurement error adjustments when considerable measurement error in cognitive outcomes is suspected.</p>","PeriodicalId":49754,"journal":{"name":"Neuropsychology Review","volume":" ","pages":""},"PeriodicalIF":5.4000,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuropsychology Review","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1007/s11065-024-09655-1","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NEUROSCIENCES","Score":null,"Total":0}

引用次数: 0

Abstract

Existing studies examining the predictive ability of biomarkers for cognitive outcomes do not account for variance due to measurement error, which could lead to under-estimates of the proportion of variance explained. We used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (N = 1084) to estimate the proportion of variance explained by Alzheimer's disease (AD) imaging biomarkers in four cognitive outcomes: memory, executive functioning, language, and visuospatial functioning. We compared estimates from standard models that do not account for measurement error, and multilevel models that do account for measurement error. We also examined estimates across diagnostic subgroups (normal, MCI, AD). Estimates of the proportion of variance explained from multilevel models accounting for measurement error were larger (e.g., for language, 9-47% vs. 7-34% under standard modeling), with relatively greater differences between standard and multilevel measurement models for cognitive outcomes that have larger measurement error variance. Heterogeneity across subgroups also emphasized the importance of sample composition. Future studies should evaluate measurement error adjustments when considerable measurement error in cognitive outcomes is suspected.

查看原文本刊更多论文

认知变异解释比例分析中的测量误差和方法问题。

现有的研究在检验生物标志物对认知结果的预测能力时没有考虑测量误差造成的方差，这可能会导致对所解释的方差比例估计不足。我们利用阿尔茨海默病神经影像倡议（ADNI）（N = 1084）的数据，估算了阿尔茨海默病（AD）影像生物标志物在记忆、执行功能、语言和视觉空间功能这四种认知结果中所解释的变异比例。我们比较了不考虑测量误差的标准模型和考虑测量误差的多层次模型的估计值。我们还考察了不同诊断亚组（正常、MCI、AD）的估计值。对于测量误差方差较大的认知结果，标准测量模型和多层次测量模型之间的差异相对较大。亚组之间的异质性也强调了样本组成的重要性。如果怀疑认知结果存在较大的测量误差，未来的研究应该对测量误差调整进行评估。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Neuropsychology Review 医学-神经科学

CiteScore

11.00

自引率

1.70%

发文量

期刊介绍： Neuropsychology Review is a quarterly, refereed publication devoted to integrative review papers on substantive content areas in neuropsychology, with particular focus on populations with endogenous or acquired conditions affecting brain and function and on translational research providing a mechanistic understanding of clinical problems. Publication of new data is not the purview of the journal. Articles are written by international specialists in the field, discussing such complex issues as distinctive functional features of central nervous system disease and injury; challenges in early diagnosis; the impact of genes and environment on function; risk factors for functional impairment; treatment efficacy of neuropsychological rehabilitation; the role of neuroimaging, neuroelectrophysiology, and other neurometric modalities in explicating function; clinical trial design; neuropsychological function and its substrates characteristic of normal development and aging; and neuropsychological dysfunction and its substrates in neurological, psychiatric, and medical conditions. The journal''s broad perspective is supported by an outstanding, multidisciplinary editorial review board guided by the aim to provide students and professionals, clinicians and researchers with scholarly articles that critically and objectively summarize and synthesize the strengths and weaknesses in the literature and propose novel hypotheses, methods of analysis, and links to other fields.