Heywood case

Occurs in factor analysis when the iterative maximum likelihood estimation method converges to unique (specific) variances values that are less than a prefixed lower bound value. Minitab sets the value for these unique variances equal to 0 and their corresponding communalities equal to 1. Heywood cases occur frequently when too many factors are extracted or the sample size is too small.

When a Heywood case occurs, Minitab displays "* NOTE * Heywood case" in the Session window output.