This tool performs a fully nested analysis of variance and estimates the variance components for the response variable. For unbalanced design, F values and P values will not be calculated. The design must be hierarchically nested with fixed factors. To use this tool, response variables and factors must be presented in columns. Factors must have at least 2 distinct levels and need not be balanced to analysis. The residuals and fitted values of the response are shown in Columns AA:AB.
Note: Limited to 10 variables at one time.
At the Excel Menu (For Excel 2007, go to Add-ins first)
Choose ProcessMA > Statistics > ANOVA > Fully Nested ANOVA
In Response, select the column containing the response data
In Term 1 to Term 10 , select the column containing data for the respective model terms (>= 2 distinct values)
Check Plot Residuals, to display residual plots
Click OK
You want to identify the sources of variability in the making of concrete. You conduct an experiment and measure strength of the concrete for four mixes over four different batches. You take three measurements at each batch. You want to use Fully Nested ANOVA to analyze your data.
Open data worksheet by choosing ProcessMA > Tools > Data
Choose ProcessMA > Statistics > ANOVA > Fully Nested ANOVA
In Response, select BG - Strength
In Term 1, select BH - Mix
In Term 2, select BI - Batch
Click OK
The ANOVA table indicates that there is significant evidence for mix and batch main effects at a = 0.05, since p < 0.05. The variance component estimates indicate that the variability attributable to mix and batch are 17.6% and 8.3% of the total variability respectively.
Copyright © ProcessMA