University of Texas at Austin, College of Pharmacy, Austin, TX, USA.
Addict Behav. 2013 Aug;38(8):2378-83. doi: 10.1016/j.addbeh.2013.03.015. Epub 2013 Apr 3.
Large-scale surveys frequently assess smoking-related attitudes, self-efficacy and intention to understand differences in smoking behavior. However, a critical assumption is that measures of these determinants should be equivalent across different subgroups of a target population. The current study examined the factorial invariance of measures of smoking-related attitudes, self-efficacy, and intention with a large sample (N=13,733) of middle school students from 25 schools in Texas. We examined five levels of factorial invariance using a sequential process, in which increasingly constrained models assess the equivalence of a measure across subgroups. Strong factorial invariance provided a good fit for the model across all of the subgroups: race/ethnicity (CFI=.93), gender (CFI=.96), age (CFI=.95), and grade level (CFI=.95). Invariance results provide strong empirical support for the validity of smoking-related attitudes, self-efficacy, and intention measures across race/ethnicity, gender, age, and grade level for middle school students.
大规模调查经常评估与吸烟相关的态度、自我效能感和戒烟意愿，以了解不同吸烟行为之间的差异。然而，一个关键的假设是，这些决定因素的测量方法在目标人群的不同亚组中应该是等效的。本研究使用来自德克萨斯州 25 所学校的 13733 名中学生的大样本，检验了与吸烟相关的态度、自我效能感和戒烟意愿测量的因子不变性。我们使用逐步过程检验了五个层次的因子不变性，其中越来越受限制的模型评估了该测量方法在各个亚组之间的等效性。在所有亚组中，该模型都具有良好的因子不变性：种族/民族（CFI=.93）、性别（CFI=.96）、年龄（CFI=.95）和年级（CFI=.95）。不变性结果为中学生在种族/民族、性别、年龄和年级水平上与吸烟相关的态度、自我效能感和戒烟意愿测量的有效性提供了强有力的实证支持。
