The statistical technique of analysis of variance is often used by biologists as a measure of the relative strength or importance of causal factors. I argue that it is a tool ill-suited to this purpose, on several grounds. I suggest a superior alternative and outline its implications. I finish with a diagnosis of the source of error-an unwitting inheritance of bad philosophy that now requires t...

A computational scheme for fitting smoothing spline ANOVA models to large data sets with a (near) tensor product design is proposed. Such data sets are common in spatial-temporal analyses. The proposed scheme uses the backfitting algorithm to take advantage of the tensor product design to save both computational memory and time. Several ways to further speed up the backfitting algorithm, such a...

Bonferroni’s Adjustment (also known as Dunn’s procedure). This procedure is simple to use and can be applied in a wide variety of situations where alpha correction is needed (and is perhaps most appropriate for situations other than the post hoc situation discussed here). To obtain a corrected critical value the desired alpha is divided by the number of comparisons or tests performed and that v...