Department of Psychology and Human Development, Peabody College, Vanderbilt University, Nashville, TN, USA.
Behav Genet. 2020 Mar;50(2):127-138. doi: 10.1007/s10519-020-09993-9. Epub 2020 Feb 10.
The univariate bootstrap is a relatively recently developed version of the bootstrap (Lee and Rodgers in Psychol Methods 3(1): 91, 1998). DeFries-Fulker (DF) analysis is a regression model used to estimate parameters in behavioral genetic models (DeFries and Fulker in Behav Genet 15(5): 467-473, 1985). It is appealing for its simplicity; however, it violates certain regression assumptions such as homogeneity of variance and independence of errors that make calculation of standard errors and confidence intervals problematic. Methods have been developed to account for these issues (Kohler and Rodgers in Behav Genet 31(2): 179-191, 2001), however the univariate bootstrap represents a unique means of doing so that is presaged by suggestions from previous DF research (e.g., Cherny et al. in Behav Genet 22(2): 153-162, 1992). In the present study we use simulations to examine the performance of the univariate bootstrap in the context of DF analysis. We compare a number of possible bootstrap schemes as well as more traditional confidence interval methods. We follow up with an empirical demonstration, applying results of the simulation to models estimated to investigate changes in body mass index in adults from the National Longitudinal Survey of Youth 1979 data.
单变量自举是自举的一个相对较新的版本（Lee 和 Rodgers 在 Psychol Methods 3(1): 91, 1998 中）。DF 分析是一种用于估计行为遗传模型中参数的回归模型（DeFries 和 Fulker 在 Behav Genet 15(5): 467-473, 1985 中）。它因其简单性而吸引人；然而，它违反了某些回归假设，例如方差同质性和误差独立性，这使得计算标准误差和置信区间成为问题。已经开发了一些方法来解决这些问题（Kohler 和 Rodgers 在 Behav Genet 31(2): 179-191, 2001 中），但是单变量自举代表了一种独特的方法，这是先前 DF 研究的建议所预示的（例如，Cherny 等人在 Behav Genet 22(2): 153-162, 1992 中）。在本研究中，我们使用模拟来研究单变量自举在 DF 分析中的表现。我们比较了几种可能的自举方案以及更传统的置信区间方法。我们通过实证演示进行跟进，将模拟的结果应用于从 1979 年全国青年纵向调查数据中估计的成年人体重指数变化模型。
