Furthermore, like other nearest neighbor techniques, k-NN allows for both univariate and multivariate predictions of continuous and categorical variables [25, 26].
Furthermore, like other nearest neighbor techniques, k-NN allows for both univariate and multivariate predictions of continuous and categorical variables [ 25, 26].
Numerical outcome variables were analyzed using multivariate analysis with standard linear regression, and categorical variables with logistic linear regression.
When appropriate, numerical outcome variables were analyzed using multivariate analysis with standard linear regression, and categorical variables with logistic linear regression.
This was achieved through bivariate and multivariate analyses including categorical analysis, concentration ratios, and hierarchical cluster analysis.
The impact of gender and parenthood on the continuous variables was investigated by means of multivariate and univariate analyses of variance; categorical variables were analyzed using Chi-square tests.
Latent class analysis (LCA) is a statistical method for analyzing and understanding multivariate categorical data.
d Multivariate odds ratios are adjusted for continuous variables (body mass) and categorical variables (hypertension, family history, smoking, and alcohol intake).
b Multivariate odds ratios are adjusted for continuous variables (body mass) and categorical variables (hypertension, family history, smoking, and alcohol intake).
d Multivariate odds ratios are adjusted for continuous variables (age and body mass) and categorical variables (parity, menopausal status, family history, smoking, and alcohol intake).
