Adjusting degrees of freedom


!DF n alters the error degrees of freedom from nu to nu + n. This qualifier might be used when analysing pre-adjusted data to reduce the degrees of freedom ( n negative) or when weights are used in lieu of actual data records to supply error information ( n positive). The degrees of freedom is only used in the calculation of the residual variance in a univariate single site analysis. The option will have no effect in analyses with multiple error variances (for sites or traits) other than in the reported degrees of freedom.

Use !ADJUST r rather than !DF n if r is not a whole number.

Use !YSS r to add r to the total sum of squares. It would be usual to also increase the degrees of freedom. For example, when analysing summarised data, you may have an independent estimate of the variance. To include that variation to the analysis, use !YSS 100 !DF 20 say, to add the equivalent of 20 observations with a variance of 5.

Return to start