Designing Experiments and Analyzing Data: A Model Comparison PerspectiveThis text is intended for advanced undergraduate- or graduate-level courses in statistics, experimental design, or analysis of variance found in departments of psychology, education and business or in schools of public health and medicine. Employing a single unifying theme throughout, and a model comparisons approach, the authors aim to give students a sense of how various design and statistical methods are interrelated, a sense of the big picture of statistics. |
Contents
Trend Analysis | 20 |
Threats to the Validity of Inferences from Experiments | 25 |
Exercises | 34 |
Copyright | |
68 other sections not shown
Other editions - View all
Common terms and phrases
analysis ANOVA approach appropriate assume assumption average behavioral biofeedback Bonferroni calculated cell means Chapter compute condition consider correlation covariate critical F critical value degrees of freedom denominator dependent variable deviation diet difference discussion drug therapy equal Equation error term experiment experimental F statistic F test Figure full model grand mean group means homogeneity of variance individual interaction least-squares estimates linear trend logic main effect marginal means measure method nonorthogonal normally distributed null hypothesis number of subjects numerical example observed F value obtained omnibus test orthogonal pairwise comparisons parameters particular performed population means predicted procedure psychologist quadratic trend regression restricted model result sample means Scheffé scores simply slope squared errors statistically significant sum of squares test statistic theory treatment effect Tukey's two-way Type I error validity within-group within-subjects design Y₁ Y₂ Yijk zero μ₁ μ₂