The article by Sandro Sperandei from the Federal University of Rio de Janeiro provides an in-depth explanation of logistic regression analysis, a statistical method used to estimate the odds ratio in the presence of multiple explanatory variables. The author emphasizes that logistic regression is similar to multiple linear regression but is specifically designed for binomial response variables. The key advantage of logistic regression is its ability to handle continuous and categorical variables simultaneously, reducing the impact of confounding effects. The article begins with a brief introduction to odds ratios and their interpretation, using a fictional study on the effects of drug treatments on *Staphylococcus Aureus* endocarditis. It then discusses the limitations of calculating odds ratios for multiple variables independently, which can lead to biased results and inflated Type I error rates. The Mantel-Haenszel OR is introduced as a solution, but it is noted that this method becomes cumbersome with more variables and is limited to categorical data. Logistic regression is then defined and explained, highlighting its ability to model the logarithm of the odds of an event based on individual characteristics. The article provides a step-by-step guide on how to interpret the results of a logistic regression model, including the interpretation of intercepts and coefficients. It also addresses common pitfalls, such as the distinction between odds and probabilities, and the importance of correctly setting the reference group. The article concludes with a discussion on variable selection and the importance of pre-selection strategies to avoid spurious results and ensure sufficient statistical power. It emphasizes the need for researchers to be cautious and knowledgeable about the procedures used in model building, rather than relying solely on automated software. Overall, the article serves as a comprehensive guide for understanding and applying logistic regression, particularly in epidemiological studies, while highlighting the importance of careful model building and interpretation.The article by Sandro Sperandei from the Federal University of Rio de Janeiro provides an in-depth explanation of logistic regression analysis, a statistical method used to estimate the odds ratio in the presence of multiple explanatory variables. The author emphasizes that logistic regression is similar to multiple linear regression but is specifically designed for binomial response variables. The key advantage of logistic regression is its ability to handle continuous and categorical variables simultaneously, reducing the impact of confounding effects. The article begins with a brief introduction to odds ratios and their interpretation, using a fictional study on the effects of drug treatments on *Staphylococcus Aureus* endocarditis. It then discusses the limitations of calculating odds ratios for multiple variables independently, which can lead to biased results and inflated Type I error rates. The Mantel-Haenszel OR is introduced as a solution, but it is noted that this method becomes cumbersome with more variables and is limited to categorical data. Logistic regression is then defined and explained, highlighting its ability to model the logarithm of the odds of an event based on individual characteristics. The article provides a step-by-step guide on how to interpret the results of a logistic regression model, including the interpretation of intercepts and coefficients. It also addresses common pitfalls, such as the distinction between odds and probabilities, and the importance of correctly setting the reference group. The article concludes with a discussion on variable selection and the importance of pre-selection strategies to avoid spurious results and ensure sufficient statistical power. It emphasizes the need for researchers to be cautious and knowledgeable about the procedures used in model building, rather than relying solely on automated software. Overall, the article serves as a comprehensive guide for understanding and applying logistic regression, particularly in epidemiological studies, while highlighting the importance of careful model building and interpretation.