The data for the low birth weight study are described in Section 1.6.2. These data are used in Section 8.2 to illustrate ordinal logistic regression models via the four category outcome BWT4,

BWT4= [0 if BWT > 3500 1 if 3000 Use the outcome variable BWT4 and fit the multinomial or baseline logistic regression model. In each of the above problems the steps in fitting the model should include: (1) a complete univariate analysis, (2) an appropriate se- lection of variables for a multivariate model (this should include scale identification for continuous covariates and assessment of the need for interactions), (3) an assessment of fit of the multivariate model, (4) preparation and presentation of a table containing the re- sults of the final model (this table should contain point and interval estimates for all relevant odds ratios), and (5) conclusions from the analysis.