Combination of F Statistics for Multiply Imputed Datasets Using a Chi Square Approximation
Several F statistics from multiply imputed datasets are combined using
an approximation based on χ^2 statistics
(see micombine.chisquare
).
micombine.F(Fvalues, df1, display=TRUE, version=1)
Fvalues |
Vector containing F values. |
df1 |
Degrees of freedom of the numerator. Degrees of freedom of the numerator are approximated by ∞ (large number of degrees of freedom). |
display |
A logical indicating whether results should be displayed at the console |
version |
Integer indicating which calculation formula should be used.
The default |
The same output as in micombine.chisquare
Allison, P. D. (2002). Missing data. Newbury Park, CA: Sage.
Enders, C. K. (2010). Applied missing data analysis. Guilford Press.
Grund, S., Luedtke, O., & Robitzsch, A. (2016). Pooling ANOVA results from multiply imputed datasets: A simulation study. Methodology, 12(3), 75-88. doi: 10.1027/1614-2241/a000111
############################################################################# # EXAMPLE 1: F statistics for 5 imputed datasets ############################################################################# Fvalues <- c( 6.76, 4.54, 4.23, 5.45, 4.78 ) micombine.F(Fvalues, df1=4 ) ## Combination of Chi Square Statistics for Multiply Imputed Data ## Using 5 Imputed Data Sets ## F(4, 52.94)=3.946 p=0.00709
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.