Several different least squares methods appear superficially similar to the conventional analysis of variance and yield identical results when applied to data from balanced experimental designs. When applied to complex problems involving unequal and disproportionate cell frequencies, the several methods yield quite different results. In such cases, the effects tested by the different methods are different; hence, interpretation of results should depend upon the method used. It is not enough merely to state that a general least squares regression method was employed to accomplish the analysis of variance.

Much of the controversy surrounding dummy variate multiple regression approaches to nonorthogonal analysis of variance would be cleared up if a criterion could be accepted for deciding what constitutes a proper generalization of the classical analysis of variance for orthogonal factorial designs. It is proposed that a general multiple regression solution be interpreted as testing analysis of variance effects only if it results in an estimation of the same parameters and tests of the same hypotheses that might otherwise be estimated and tested in an orthogonal design involving the same factors. A method which satisfies this criterion is identified, and a simple procedure for examining equivalence in orthogonal and nonorthogonal cases is suggested.

No abstract

Comparisons were made between male and female gerbils reared by ventral gland-excised and intact parents. Repeated measurements before and after puberty failed to reveal an effect of gland odor exposure on body weight, ventral gland size, open-field defecation, and time of vaginal opening. Exposed animals were more attracted than nonexposed animals to a strange male's gland odor during preference tests involving "marked" and "unmarked" paper strips. Opposite-sex pairs of exposed animals engaged in more social behavior than did nonexposed pairs, but there was no difference in fighting frequency or, during extended cohabitation, in fecundity. While early exposure to gland odor apparently does not affect physical maturation, it may enhance later responsiveness to stimuli (gland odors) that are useful in locating conspecifics and that facilitate social interactions between previously unacquainted gerbils.

No abstract