Authors’ Response to: Alternatives to principal components analysis to derive asset-based indices to measure socio-economic position in low- and middle-income countries: the case for multiple correspondence analysis
Authors’ Response to: Alternatives to principal components analysis to derive asset-based indices to measure socio-economic position in low- and middle-income countries: the case for multiple correspondence analysis
复制标题
作者的回应：主成分分析的替代方案，以得出基于资产的指数来衡量低收入和中等收入国家的社会经济地位：多重对应分析的案例
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
J. Hargreaves
中科院分区：
文献类型：
--
作者：
David Gordon;L. Howe;B. Galobardes;A. Matijasevich;D. Johnston;O. Onwujekwe;R. Patel;E. Webb;D. Lawlor;J. Hargreaves
我们欢迎 Traissac 和 MartinPrével 的评论，并分享他们对使用主成分分析 (PCA) 来得出基于资产的家庭福利指数权重的担忧。我们完全同意，为此目的使用 PCA 是有问题的，并且还有其他几种可能更好的方法，例如多重对应分析、非线性典型相关分析和潜在特征分析。我们没有详细讨论这些替代方案以及项目反应理论的相关问题，因为本文旨在对衡量中低收入国家研究人群社会经济地位的主题提供更广泛的概述。我们欢迎有机会在这里进一步讨论这些问题。
We welcome the comments of Traissac and MartinPrével and share their concerns about the use of principal components analysis (PCA) to derive weights for asset-based household welfare indices. We are in complete agreement that the use of PCA for this purpose is problematic and that several other potentially better methods are available, such as multiple correspondence analysis, non-linear canonical correlation analysis and latent trait analysis. We did not discuss in detail these alternatives and the related issue of item response theory, because the article aimed to provide a broader overview of the topic of measuring socio-economic position in lowand middle-income country study populations. We welcome the opportunity to discuss these issues further here.