1. Why do we use the deviance statistic rather rather than log-likelihood as our goodness of fit statistic in logistic regression? 2. Assuming we have a logistic regression model with a binary outcome and a categorical (binary) predictor variable. When our odds ratio is greater than 1, how is that interpreted? 1. Why do we use the deviance statistic rather rather than log-likelihood as our goodness of fit statistic in logistic regression? 2. Assuming we have a logistic regression model with a binary outcome and a categorical (binary) predictor variable. When our odds ratio is greater than 1, how is that interpreted