Creates a fixed-effects ANOVA table in APA style
apa.aov.table(lm_output, filename, table.number = NA, conf.level = 0.9, type = 3)
| lm_output | Regression (i.e., lm) result objects. Typically, one for each block in the regression. |
|---|---|
| filename | (optional) Output filename document filename (must end in .rtf or .doc only) |
| table.number | Integer to use in table number output line |
| conf.level | Level of confidence for interval around partial eta-squared (.90 or .95). A value of .90 is the default, this helps to create consistency between the CI overlapping with zero and conclusions based on the p-value. |
| type | Sum of Squares Type. Type II or Type III; specify, 2 or 3, respectively. Default value is 3. |
APA table object
Smithson, M. (2001). Correct confidence intervals for various regression effect sizes and parameters: The importance of noncentral distributions in computing intervals. Educational and Psychological Measurement, 61(4), 605-632.
Fidler, F., & Thompson, B. (2001). Computing correct confidence intervals for ANOVA fixed-and random-effects effect sizes. Educational and Psychological Measurement, 61(4), 575-604.
#Example 1: 1-way from Field et al. (2012) Discovery Statistics Using R options(contrasts = c("contr.helmert", "contr.poly")) lm_output <- lm(libido ~ dose, data = viagra) apa.aov.table(lm_output, filename = "ex1_anova_table.doc")#> #> #> ANOVA results using libido as the dependent variable #> #> #> Predictor SS df MS F p partial_eta2 CI_90_partial_eta2 #> (Intercept) 180.27 1 180.27 91.66 .000 #> dose 20.13 2 10.06 5.12 .025 .46 [.04, .62] #> Error 23.60 12 1.97 #> #> Note: Values in square brackets indicate the bounds of the 90% confidence interval for partial eta-squared #># Example 2: 2-way from Fidler & Thompson (2001) # You must set these contrasts to ensure values match SPSS options(contrasts = c("contr.helmert", "contr.poly")) lm_output <- lm(dv ~ a*b, data = fidler_thompson) apa.aov.table(lm_output,filename = "ex2_anova_table.doc")#> #> #> ANOVA results using dv as the dependent variable #> #> #> Predictor SS df MS F p partial_eta2 CI_90_partial_eta2 #> (Intercept) 150.00 1 150.00 150.00 .000 #> a 1.50 1 1.50 1.50 .238 .09 [.00, .32] #> b 12.00 3 4.00 4.00 .027 .43 [.04, .57] #> a x b 4.50 3 1.50 1.50 .253 .22 [.00, .38] #> Error 16.00 16 1.00 #> #> Note: Values in square brackets indicate the bounds of the 90% confidence interval for partial eta-squared #>#Example 3: 2-way from Field et al. (2012) Discovery Statistics Using R # You must set these contrasts to ensure values match SPSS options(contrasts = c("contr.helmert", "contr.poly")) lm_output <- lm(attractiveness ~ gender*alcohol, data = goggles) apa.aov.table(lm_output, filename = "ex3_anova_table.doc")#> #> #> ANOVA results using attractiveness as the dependent variable #> #> #> Predictor SS df MS F p partial_eta2 #> (Intercept) 163333.33 1 163333.33 1967.03 .000 #> gender 168.75 1 168.75 2.03 .161 .05 #> alcohol 3332.29 2 1666.14 20.07 .000 .49 #> gender x alcohol 1978.12 2 989.06 11.91 .000 .36 #> Error 3487.50 42 83.04 #> CI_90_partial_eta2 #> #> [.00, .18] #> [.28, .60] #> [.15, .49] #> #> #> Note: Values in square brackets indicate the bounds of the 90% confidence interval for partial eta-squared #>