ANOVA Features

• One to five factors
• Crossed, nested or mixed designs
• Fixed and/or random factors
• Multiple responses
• Randomization of runs
• Option to visualize design
• 1 to 25 Replications
• ANOVA table for factors
• ANOVA table for models
• Statistics
  • Average
  • Standard deviation
  • Coefficient of variation
  • R square
  • Adjusted R square
• 95% confidence intervals for treatment means (fixed factors)
• Comparison of treatment means and variances (fixed factors)
  • Treatment means
    • Tukey's method
    • Bonferroni's method
    • Fisher's LSD method
    • Option to plot pairwise comparisons
  • Treatment  variances
    • Bartlett's Test
    • Levene's Method
• Variability Plots
  • Plots each treatment versus factor levels
  • Option to plot treatment averages and oveall averages
  • Option to re-order factors on plot
  • Option to color-code by a factor's levels
• Components of Variance Plots
  • % of total by factor
  • Estimates of variance and standard deviation by factor
• Xbar and R/s charts
  • Xbar: Plots treatment means
  • R: plots treatment ranges
  • s: plots treatment standard deviations
• Expected Mean Square
• F Calculation Information
  • Source, error degrees of freedom, error mean square, errro mean square calculation
• Rollup Control Charts
  • Rollup control charts (primarily for nested designs)
• Residuals analysis
  • Residuals
  • Leverage
  • Standardized residuals
  • Internally studentized residuals
  • Externally studentized residuals
  • DFFITS
  • Cook's distance
  • Potential outliers in red
• Residuals charts (select raw, standardized, internally or externally studentized residuals)
  • Normal plot
  • Versus predicted values
  • Versus actual run number
• Other charts
  • Predicted vs actual
  • DFFITS, Cook's distance and leverage versus actual run number
• p values < 0.05 in red

Our SPC software, SPC for Excel, performs ANOVA for one to five factors. ANOVA allows you to determine if there are significant differences between treatments. The ANOVA output for the factors and models is shown above. More of the ANOVA output is shown below. Our software includes, among the features listed below, a full residual analysis with potential outliers in red. It also includes three methods for determining which means are significantly different as well as two methods for checking the equality of variances.

Examples of ANOVA Output

ANOVA Statistics

Treatment Statistics

Bonferroni's Method for Differences in Means

Pairwise Treatment Mean Plots

Bartlett's Test for Equality of Variances

Variability Chart

Variability Chart - Color Coded by Factor Levels

Xbar-R Control Chart

Components of Variance Chart

Expected Mean Squares and F Calculation Information

Portion of Residuals Analysis Worksheet

Normal Plot of Raw Residuals

Externally Studentized Residuals versus Predicted Values