Interaction effects in multiple regression

作者: Robert Turrisi , Choi K. Wan , James Jaccard

DOI:

关键词:

摘要: This monograph is concerned primarily with the statistical analysis of moderated relationships or as they are more commonly known interaction effects where all variables involved continuous in nature. The focus on analyzing context multiple regression and structural equation analyses. There currently exists a great deal confusion about involving variables. substantive literatures replete contradictory advice admonitions best way to test models relationships. Further relevant literature scattered throughout range disciplines including sociology psychology political science economics biology statistics. major purpose this bring together rather diverse explicate central issues conducting analyses principal finding that most straightforward when it theoretically motivated; theory guides specification appropriate using analysis. Traditional product terms assess specific form namely bilinear interactions. authors organize their around 3 questions: 1) given sample data can be inferred an effect population; 2) if so what strength effect; 3) nature effect? When formulating research for one should consider related size (for purposes power analysis) levels measurement error potential multicollinearity other methodological/substantive discussed above. concludes 10 empirical applications have used

参考文章(0)