Aims of the workshop

• To introduce participants to statistical designs and models used in epidemiology, their use in practice and their interpretations.
• To introduce participants to sample size computation in epidemiology and longitudinal data analysis
• To demonstrate the use of R for carrying out statistical computations and analysis of epidemiological data.

Course description

Module 1: Statistical methods in Epidemiology or Statistical evaluation of epidemiological data (16-18 November, 2009)

Description: Introduction to statistical concepts and quantities used in Epidemiology, cohort and case-control studies, confounding, stratification, logistic regression, interactions, introduction to survival data analysis, case-cohort studies. Basic programming skills necessary to analyse data sets for cohort and case-control studies were also taught.

Module 3: Longitudinal data analysis (19-21 November, 2009)

Description: In longitudinal studies repeated measurements are taken from the same individual over time. This makes it possible to separate changes in the outcome variable over time (or age). The course concentrated on general concepts in longitudinal data analysis, different ways of modelling longitudinal data (both continuous and binary). The applications were mostly from medicine and epidemiology but the statistical models were generic so that they could be applied in many different fields where repeated measurements are required. Examples were taken to try model building using R and Bayesian computation using OpenBUGS.

Module 2: Sample size consideration in Epidemiology (22-24 November, 2009)

Description: Introduction to the statistical concepts of hypothesis testing, confidence intervals, power and sample size, normal distribution, binomial distribution, determination of sample size for a variety of situations based on study objectives, by taking into account other possible constraints, such as resources etc., collecting information about the unknown quantities needed for sample size calculations, sample size computation for one-sample mean or proportion, to compare two or more means and proportions, regression models, cohort and case-control studies, graphical tools for finding an appropriate balance between power and sample size, post-hoc power calculations, simulation techniques and ethical considerations. Examples were used to explain and interpret the results. Participants were given the opportunity to share their experiences on sample size determination for own research or studies.

Audience

About 30 participants, namely, epidemiologists and medical professionals, statisticians, university teachers, researchers and postgraduate students.

Faculty

Kari Auranen, PhD (Biometry),
Senior scientist, National Institute for Health and Welfare (THL), Finland,
Adjunct Professor of Biometry, University of Helsinki, Finland

Jukka Jokinen, PhD (Biometry),
Head of the Vaccines Research Unit, National Institute for Health and Welfare (THL), Finland

Sangita Kulathinal, PhD (Statistics),
Senior scientist, The Indic Society for Education and Development (INSEED), Nashik,
Adjunct Professor of Statistics, University of Helsinki, Finland,
Adjunct Professor of Biometry, University of Tampere, Finland
Adjunct faculty, Department of Statistics, Manipal University, India,

Bijoy Joseph, PhD (Geology) (Course co-ordinator)
Senior researcher, The Indic Society for Education and Development (INSEED), Nashik
Adjunct faculty, Department of Statistics, Manipal University, India

Host

Yashwantrao Chavan Maharashtra Open University,
'Dnyangangotri', Near Gangapur Dam,
Nashik - 422 222, Maharashtra, INDIA

Organisers

• The Indic Society for Education and Development,
  1, Swami Enterprises Complex,
  Tigrania road, Tapovan Bridge,
  Nashik - 422 011, Maharashtra, INDIA.
  
  
• Yashwantrao Chavan Maharashtra Open University,
  'Dnyangangotri', Near Gangapur Dam,
  Nashik - 422 222, Maharashtra, INDIA