Course description

Biostatistics I - M. Pagano (Harvard University)

Introduces the fundamental principles of statistics applied to biomedicine. The topics to be covered include: descriptive statistics, measures of central tendency, probability, diagnostic testing, population and sample, comparison of proportions. At the end of the course, students will be able to understand the descriptive statistical methodologies which are used in clinical and epidemiological studies and to utilize the estimates obtained from suitably selected samples, in order to draw statistical inferences.

Applied Linear Regression - R. Bellocco (Karolinska Institutet and University of Milano-Bicocca)

The course introduces students to the practice and application of regression modeling. Through the use of Stata®, students will learn how to fit a regression, estimate, and test regression coefficients. Particular emphasis will be placed on the interpretation of the regression coefficients of continuous and categorical predictors. Analysis of variance models and their correspondence with regression models will also be covered together with procedures and issues in model selection, including confounding and interaction. Model building, goodness of fit, residual analysis, and appropriate regression diagnostics will be discussed.

Applied Logistic Regression - D. Wypij (Harvard University)

This course introduces students to the practice and application of logistic regression modeling for binary outcomes. Students will fit, evaluate, and interpret binary data models arising from epidemiological studies, clinical trials, or other application areas. Topics include assessment of confounding and effect modification, use of indicator variables, model building methods, goodness-of-fit assessment, presentation of logistic regression models for reports and publications, and an introduction to conditional and ordinal logistic regression. Data sets from the medical and public health literature will be used as case studies to be analyzed using the Stata® statistical package.

Block 2

Principles of Epidemiology - J. Adami (Karolinska Institutet)

Introduction to epidemiology as a basic science for public health and clinical medicine. The course will cover the principles of the quantitative approach to clinical and public health problems such as the basic measures of frequency and association, discuss the design, feasibility and validity of epidemiologic studies, and give an overview of data analysis. At the end, students should be able to interpret critically the epidemiological literature.

Causal Inference - Andrea Rotnitzky (Harvard University and Universidad Di Tella)

Students will learn to critically evaluate the pitfalls of observational studies and of imperfect experimental studies, in particular all possible biases that can arise. Students will learn analytic tools, based on causal diagrams and new statistical models, that can help squeeze as much evidence as these imperfect studies carry about the causal effects of interventions, treatments and/or exposures of interest.

Survival Analysis - P. Dickman (Karolinska Institutet)

The course aim is to introduce statistical methods for survival analysis, that is, the analysis of studies where the outcome is a time-to-event. We will study methods for estimating patient survival (life table and Kaplan-Meier methods), comparing survival between patient subgroups (log-rank test), and modelling survival (primarily Poisson regression and the Cox proportional hazards model). Emphasis will be placed on describing how epidemiological cohort studies can be analysed in the framework of survival analysis. We will study the concept of 'time' as a potential confounder or effect modifier and discuss various approaches to defining 'time' (e.g., time since entry, attained age, calendar time). The course will emphasise the basic concepts of statistical modelling in epidemiology, such as controlling for confounding and assessing effect modification. The course will consist of lectures, classroom exercises, and computing exercises (using Stata®).

Block 3

Statistical Genomics - G. Parmigiani (Harvard University)

The analysis of genomic data is moving from the laboratories to a wide variety of population and clinical research settings. This course will cover the basic concepts of genomic analysis, and is designed for students with a background in biostatistics, and interest in population or clinical research. The goal is to provide a general orientation and pointers to simple and effective methodologies for analyzing genomic data in these contexts. Specific topics will include:
1) basics of genomic measurement technologies, preprocessing, and quality control;
2) multiple testing and identification of genomic features associated with phenotypes;
3) classification, prediction, and validtion, using genome-wide data;
4) analysis of genomic data by gene sets and pathways;
5) Bayesian hierarchical models for genomics research.

Applied Longitudinal Analysis - G. Fitzmaurice (Harvard University)

This course focuses on methods for analyzing longitudinal and repeated measures data. The defining feature of longitudinal studies is that measurements of the same individuals are taken repeatedly through time, thereby allowing the direct study of change over time. This type of study design encompasses epidemiological follow-up studies as well as clinical trials. The course covers many well-established methods for the analysis of longitudinal data when the response variable is continuous. Methods for discrete response variables (e.g., repeated binary responses and counts) are introduced, but not emphasized. An introductory course in biostatistics and a good background in linear regression analysis are prerequisites for this course.

Monitoring and Evaluation of Health Programs - M. Pagano (Harvard University)

This course covers the basic statistical tools necessary for monitoring and evaluation of health programs. The range of topics includes assessing modern and rapid testing methods; an overview of various methodologies and designs for estimating coverage and changes for a region; methods for evaluating subregional performance (ie the health districts of a region); and comprehensive M&E approaches that allow for both local and regional assessment. Emphasis will be on the practical aspects of design, analysis and presentation (including mapping), with a large number of examples presented, and training on the use of software.

Block 4

Biostatistics II - M. Bonetti (Bocconi University)

A course designed to provide the student with an understanding of the foundations of biostatistics and how useful the discipline is in tackling problems in the health sciences. Students will be introduced to graphical techniques, probability models, hypothesis testing, confidence intervals, correlation, regression. Topics include: comparison of two samples (t-test and non parametric tests), regression and correlation, analysis of contingency tables, life table and survival analysis. The afternoon sessions are devoted to discussion and learning to use Stata® to implement materials covered in the morning lectures.

Statistical Methods in Environmental Epidemiology - F. Dominici (Harvard University)

Evidence from environmental epidemiology research often contributes to the foundation of major policy decisions, driving policy makers to pose challenging questions to researchers. These questions are often best answered by using statistical methods that characterize the risk of a targeted environmental agent while taking other environmental variables into account. The nature and characteristics of environmental data and health outcomes make the risk estimation challenging and require the development of novel statistical methods.
In this course we will provide an overview of the most modern statistical approaches for estimating health effects of one or more environmental contaminants with a focus on air pollution exposures. We will review statistical methods for multi-site time series studies, for cohort studies and for confounding adjustment. We will also present more modern methods for integrated analyses of spatio-temporal data on exposure, health outcomes and covariates, incompletely observed and available at different levels of aggregation. R code and data sets will be made available to students.

Evidence Based Public Health - E. Savoia (Harvard University)

This course will introduce the core concepts of Evidence Based Public Health and present studies conducted in Europe, the United States and in the Developing World assessing the effectiveness of public health interventions and their relationship with the organizational structures, financing systems, workforce characteristics and delivery mechanisms of various practice settings. Topics will include: definition of Evidence Based Public Health, identification of sources and databases to search for scientific evidence in public health, study designs issues, development and validation of surveys to be used in public health practice (including teaching how to create online surveys), causality in public health research, methods for the assessment of public health programs and policies, assessment of performance in public health practice. Knowledge of basic concepts and methods in epidemiology and biostatistics is required for this course.

Stata 1

Introduction to Stata® - U-L. Bell (TStat)

This course is designed to introduce students to the basics of Stata. It will focus on the minimum set of commands everyone should know to organize their own work. Specific topics include data-management, data-reporting, graphics and basic use of do-files. By the end of this one-day course, the student should be capable of using Stata independently.

Epidemiology with Stata® - N. Orsini (Karolinska Institutet)

This course is designed to introduce students to basic Stata commands useful in epidemiological research: descriptive statistics to estimate the incidence of a binary response and to characterize the demographic information supplied by study participants; statistical tests to identify univariate predictors associated with the binary response; graph the incidence of a binary response as a function of a predictor; and estimation of measure of associations using logistic regression models.

Meta-analysis using Stata® - R. D'Amico (University of Modena and Reggio Emilia)

The aim of this course is to provide an overview of methods to perform meta-analysis using Stata. We will cover Stata commands for a variety of tasks: data preparation and input, fixed and random-effect models, forest plots (publication quality graph), heterogeneity across studies, publications bias, sensitivity analysis, and meta-regression models.

Stata 2

Introduction to Stata® - G. Capelli (University of Cassino)

Analysis of prospective studies with Stata® - R. Bellocco (Karolinska Institutet and University of Milano-Bicocca)

This course is designed to introduce student to the analysis of cohort studies, managing person-times, estimating counts and incidence rate ratios of both fixed and time-varying exposures and fitting count regression models. By the end of the course, the student will be familiar these epidemiogical techniques using Stata®.

Regression modelling strategies with Stata® - N. Orsini (Karolinska Institutet)

This course provides methods for estimating the shape of the relationship between predictors and response using linear and restricted cubic spline construction within the general framework of generalized linear models. The focus of the course will be on interpretation of model parameters, relaxing linearity assumption for continuous predictors, and producing publication quality graphs. Motivating examples from the medical and public health literature will be analyzed using Stata®. Students should have a background in linear regression methods prior to taking this course.

postmaster@biostatepi.org