Is adding more indicators to a latent class analysis beneficial or detrimental? Results of a Monte-Carlo study.

Is adding more indicators to a latent class analysis beneficial or detrimental? Results of a Monte-Carlo study.
复制标题

DOI:
10.3389/fpsyg.2014.00920
复制
发表时间:
2014
影响因子:
3.8
通讯作者:
Geiser C
Geiser C
中科院分区:
心理学3区
文献类型:
--
作者:
Wurpts IC;Geiser C

文献摘要

参考文献

被引文献

相似文献

本研究的目的是探讨在何种方式增加更多的指标或协变量影响潜在类分析(LCA)的性能。我们改变了样本量(100 ≤ N ≤ 2000)、数量和二进制指标的质量(4 - 12个指标,条件响应概率为[0.3,0.7]、[0.2,0.8]或[0.1,0.9]),以及协变量效应的强度(零,小,中,大)在2和3类模型的蒙特卡罗模拟研究。结果表明,样本量越大、指标越多、指标质量越高、协变量效应越大,模型的收敛性越好,重复性越好,边界参数估计值越少,参数偏差越小。此外,这些研究因素之间的相互作用表明,如何使用更多或更高的质量指标,以及更大的协变量效应大小,有时可以补偿小样本量。纳入协变量似乎通常是有益的,尽管协变量参数本身显示出相对较大的偏倚。我们的研究结果提供了有用的信息,从业者设计的LCA研究方面突出的因素,导致更好或更差的性能LCA。
The purpose of this study was to examine in which way adding more indicators or a covariate influences the performance of latent class analysis (LCA). We varied the sample size (100 ≤ N ≤ 2000), number, and quality of binary indicators (between 4 and 12 indicators with conditional response probabilities of [0.3, 0.7], [0.2, 0.8], or [0.1, 0.9]), and the strength of covariate effects (zero, small, medium, large) in a Monte Carlo simulation study of 2- and 3-class models. The results suggested that in general, a larger sample size, more indicators, a higher quality of indicators, and a larger covariate effect lead to more converged and proper replications, as well as fewer boundary parameter estimates and less parameter bias. Furthermore, interactions among these study factors demonstrated how using more or higher quality indicators, as well as larger covariate effect size, could sometimes compensate for small sample size. Including a covariate appeared to be generally beneficial, although the covariate parameters themselves showed relatively large bias. Our results provide useful information for practitioners designing an LCA study in terms of highlighting the factors that lead to better or worse performance of LCA.
DOI: 10.1080/10705511003659318
发表时间: 2010-04-01
期刊: Structural equation modeling : a multidisciplinary journal
影响因子: --
作者:
Tueller S;Lubke G
通讯作者: Lubke G
DOI: 10.1080/10705511.2013.824781
发表时间: 2013-10-01
期刊: Structural equation modeling : a multidisciplinary journal
影响因子: --
作者:
Tein JY;Coxe S;Cham H
通讯作者: Cham H
DOI: 10.1080/10705511.2013.769395
发表时间: 2013-04-01
影响因子: 6
作者:
Peugh, James L.;DiLillo, David;Panuzio, Jillian
通讯作者: Panuzio, Jillian
DOI: 10.1177/0193841x9902300404
发表时间: 1999-08-01
期刊: EVALUATION REVIEW
影响因子: 0.9
作者:
Krull, JL;MacKinnon, DP
通讯作者: MacKinnon, DP
DOI: 10.1207/s15328007sem1401_2
发表时间: 2007-01-01
影响因子: 6
作者:
Lubke, Gitta;Muthen, Bengt O.
通讯作者: Muthen, Bengt O.