13.07.2015 Views

Contents

Contents

Contents

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

CHAPTER 12: Data Analysis and Interpretation: Part II. Tests of Statistical Significance and the Analysis Story 415FIGURE 12.3 Mean responses as a function of Variable A (a1, a2) and Variable B (b1, b2, b3). The 95%confidence interval is shown around each mean.2520Mean Responses15105b 1 b 2 b 3Variable Bb 1 b 2 b 3A a 1 19 19 20a 1a 2a 2 10.6 15.8 18.2CIs (bars) are ±1.44 unitsdesign. The first independent variable is called the between-subjects factor(here symbolized as A). The second independent variable is called the withinsubjectsfactor (symbolized as B). The two-factor analysis for a mixed designis somewhat of a hybrid of the single-factor analysis for independent groupsand the single-factor analysis for the repeated measures designs. This particularcomplex design was discussed in Chapter 8 when we reported the results of astudy by Kaiser et al. (2006) using the emotional Stroop test.As you should now be aware, it is important to review the appropriate summarystatistics and to appreciate the trends in the data before looking at theANOVA Summary Table. An outline of a typical computer output for a two-factoranalysis of variance for a mixed design is presented below. The details of the experimentproviding the data for this analysis need not concern us. Be aware thatsome computer programs separate the output of a mixed design, showing firstthe output for the between-groups analysis and then the output for the withinsubjectsanalysis (which includes the interaction effect). You may find that youhave to scroll the computer screen to get all of the information.Between SubjectsSource SS df MS F pGroup 0.225 1 0.225 1.718 0.226Error 1.049 8 0.131Within SubjectsPresent 15.149 2 7.574 58.640 0.000Present Group 0.045 2 0.022 0.173 0.843Error 2.067 16 0.129

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!