MOTE (version 1.0.2)

ges.partial.SS.mix: Partial Generalized Eta-Squared for Mixed Design ANOVA from F

Description

This function displays partial generalized eta-squared (GES) from ANOVA analyses and its non-central confidence interval based on the F distribution. This formula works for mixed designs.

Usage

ges.partial.SS.mix(dfm, dfe, ssm, sss, sse, Fvalue, a = 0.05)

Arguments

dfm

degrees of freedom for the model/IV/between

dfe

degrees of freedom for the error/residual/within

ssm

sum of squares for the model/IV/between

sss

sum of squares subject variance

sse

sum of squares for the error/residual/within

Fvalue

F statistic

a

significance level

Value

Partial generalized eta-squared (GES) with associated confidence intervals and relevant statistics.

ges

effect size

geslow

lower level confidence interval for ges

geshigh

upper level confidence interval for ges

dfm

degrees of freedom for the model/IV/between

dfe

degrees of freedom for the error/residual/within

F

F-statistic

p

p-value

estimate

the generalized eta squared statistic and confidence interval in APA style for markdown printing

statistic

the F-statistic in APA style for markdown printing

Details

To calculate partial generalized eta squared, first, the sum of squares of the model, sum of squares of the subject variance, sum of squares for the subject variance, and the sum of squares for the error/residual/within are added together. The sum of squares of the model is divided by this value.

partial ges = ssm / (ssm + sss + sse)

Learn more on our example page.

Examples

# NOT RUN {
#The following example is derived from the "mix2_data" dataset, included
#in the MOTE library.

#Given previous research, we know that backward strength in free
#association tends to increase the ratings participants give when
#you ask them how many people out of 100 would say a word in
#response to a target word (like Family Feud). This result is
#tied to people<U+2019>s overestimation of how well they think they know
#something, which is bad for studying. So, we gave people instructions
#on how to ignore the BSG.  Did it help? Is there an interaction
#between BSG and instructions given?

library(ez)
mix2_data$partno = 1:nrow(mix2_data)

library(reshape)
long_mix = melt(mix2_data, id = c("partno", "group"))

anova_model = ezANOVA(data = long_mix,
                      dv = value,
                      wid = partno,
                      between = group,
                      within = variable,
                      detailed = TRUE,
                      type = 3)

#You would calculate one partial GES value for each F-statistic.
#Here's an example for the interaction with typing in numbers.
ges.partial.SS.mix(dfm = 1, dfe = 156,
                   ssm = 71.07608,
                   sss = 30936.498,
                   sse = 8657.094,
                   Fvalue = 1.280784, a = .05)

#Here's an example for the interaction with code.
ges.partial.SS.mix(dfm = anova_model$ANOVA$DFn[4],
               dfe = anova_model$ANOVA$DFd[4],
               ssm = anova_model$ANOVA$SSn[4],
               sss = anova_model$ANOVA$SSd[1],
               sse = anova_model$ANOVA$SSd[4],
               Fvalue =  anova_model$ANOVA$F[4],
               a = .05)
# }