Expected predictive least squares for model selection in covariance structures.
Expected predictive least squares for model selection in covariance structures.
复制标题
协方差结构中模型选择的预期预测最小二乘法。
DOI：
10.1016/j.jmva.2016.12.007
复制
发表时间：
2017
影响因子：
1.6
通讯作者：
H.
中科院分区：
文献类型：
--
作者：
Ogasawara;H.
在协方差结构分析中定义了使用当前数据预测未来数据的预测最小二乘法 (PLS)。通过 PLS 的两倍期望得到的期望预测最小二乘法 (EPLS) 是未知的拟合指标。使用当前数据给出的加权最小二乘的渐近偏差来估计协方差结构中的 EPLS，与 Takeuchi 信息准则类似地导出的修正最小二乘准则显示在任意分布下是渐近无偏的。探索性因子分析中模型选择的模拟显示了相对于典型的当前拟合指数（如 RMSEA 和 AIC）的改进。
Predictive least squares (PLS) using future data to be predicted by current data are defined in covariance structure analysis. The expected predictive least squares (EPLS) obtained by two-fold expectation of PLS are unknown fit indexes. Using the asymptotic biases of weighted least squares given by current data for estimation of EPLS in covariance structures, corrected least square criteria derived similarly to the Takeuchi information criterion are shown to be asymptotically unbiased under arbitrary distributions. Simulations for model selection in exploratory factor analysis show improvements over typical current fit indexes as RMSEA and AIC.