Course outline

Learning outcomes

Objective

Upon completion of the course, students will be able to understand the importance of the application of regression models in medical research. They will be able to model the relationship between a dependent variable with one or more explanatory (independent) variables. Students will be capable to use, evaluate and interpret results taking into account possible confounding and effect modification as well as clinical outcomes. An additional objective of this course is the understanding of biostatistics methodology through practical guidance and use of R program.

Knowledge

Upon completion of the course, graduate students will be familiar with:

  • Simple and multiple linear models applied to medical data (linear, logistic, Poisson, Cox)
  • Assumptions and conditions that should be met for the application of these models
  • The goodness of fit test to evaluate the performance of the models
  • The necessary conditions that must exist in order to qualify as one or more variables as confounding in a relationship of outcome and exposure
  • The concept of effect modification, and how it differs from confounding
  • The usefulness of multiple regression techniques to analyze the relationship of an exposure to a predictive variable in the possible presence of confounding factors by using adjusted analysis
  • Sample size calculation for multivariable models

Capacities

The course participants upon completion will be able to:

  • Have a methodology in order to build appropriate multivariable linear models
  • Investigate the existence of confounding or effect modification in medical research and manage them appropriately
  • Interpretation of the results obtained from the corresponding models
  • Using the fast-growing and evolving R software as a tool for statistical analysis and the creation of elegant graphs
  • Make critical review of data

Course contents

During the course, students will work on their own research question, and will experience the process of review at all stages. So they will learn how to:

  1. Data investigation and editing, guidance for constructing graphs using R program (practice R)
  2. Linear relationship between two quantitative variables (Scatter plots, Pearson’s & Spearman’s correlation) (practice R)
  3. Theory of Linear Regression Models and their importance in medical research and practice
  4. Confounding and effect modification
  5. Simple and multiple linear regression analysis and applications in medical data (in practice R)
  6. Simple and multiple logistic regression analysis and applications in medical data (in practice R)
  7. Simple and multiple Poisson regression analysis and applications in medical data (in practice R)
  8. Simple and multiple Cox regression and applications in medical data (in practice R)

Recommended Bibliography

  1. Aho, Ken A. Foundational and applied statistics for biologists using R. CRC Press, 2013.
  2. Bland, Martin. An introduction to medical statistics. 3rd Edition. Oxford University Press, 2000.
  3. Crawley, Michael J. Statistics: an introduction using R, 2nd Edition. John Wiley & Sons, 2014.
  4. MacFarland, Thomas W. Introduction to Data Analysis and Graphical Presentation in Biostatistics with R. Springer, 2014.
  5. Daniel, Wayne W., and Chad L. Cross. Biostatistics: A Foundation for Analysis in the Health Sciences: A Foundation for Analysis in the Health Sciences. Wiley Global Education, 2012.
  6. Logan M. Biostatistical Design and Analysis Using R: A Practical Guide. Wiley-Blackwell, 2010.
  7. Aviva Petrie, Caroline Sabin. Medical Statistics at a Glance, 3rd Wiley  2009.
  8. David G. Kleinbaum, Mitchel Klein. Survival Analysis: A self-learning text. 3rd Edition. Springer 2012.
  9. David G. Kleinbaum. Logistic Regression: A self-learning text. 3rd Edition. Springer 2010.
  10. Faraway, J. J. (2014). Linear Models with R (Chapman & Hall/CRC Texts in Statistical Science) (2nd ed.). Chapman and Hall/CRC.