论文信息 - Linear models for the analysis of variability in factorial designs: an application to anthropometric indicators.

Linear models for the analysis of variability in factorial designs: an application to anthropometric indicators.

This paper has two aims. One is to evaluate, in a set of 9740 'reference' neonates born in five Italian centres (Trieste, Milan, Parma, Rome, Bari) during 1973-1976 the effects of gestational age and birthplace on the variability of crown-heel length and head circumference at birth; this is a preliminary step in the construction of 'Italian' intrauterine growth standards for such anthropometric measures. The other aim is to put the various techniques for the analysis of variability into a common framework of Linear Models, either Generalized or Classical, to compare their main features and provide some indications about their application.

S Milani | A Bossi

[1] A review of six multifactor tests for homogeneity of spread , 1983 .

[2] P. Gartside,et al. A Study of Methods for Comparing Several Variances , 1972 .

[3] E. Marubini,et al. Neonatal morbidity risk: a study of the relationship to birthweight and gestational age in four Italian centres. , 1983, Annals of human biology.

[4] P. McCullagh,et al. Generalized Linear Models , 1972, Predictive Analytics.

[5] M. E. Johnson,et al. A Comparative Study of Tests for Homogeneity of Variances, with Applications to the Outer Continental Shelf Bidding Data , 1981 .

[6] Bayesian Test of Homogeneity of Variance , 1976 .

[7] E. Marubini,et al. Structural analysis of a set of socioeconomic indexes as an aid in defining the socioeconomic level of a family: results from an italian multicentric survey. , 1983, Social science & medicine.

[8] John E. Overall,et al. A simple test for heterogeneity of variance in complex factorial designs , 1974 .