The information contained in this website is of a general nature, is for informational purposes only and does not constitute professional advice
Study of disease in populations
Need for denominators, person time at risk
Measures of disease frequency (prevalence/incidence)
Measures of effect (relative [RR, OR, RR] and difference [risk/rate difference] measures)
Continuous and categorical variables
Descriptive statistics
Statistical tests of association
p values and confidence intervals
OR, RR
Controlling for confounding: logistic regression
Sample size and power
Describe major study designs used in epidemiological research:
Strengths and weakness of different designs
Exposures, outcomes, other exposures (potential confounders)
Learning objectives
Define and calculate sensitivity, specificity, PPV, NPV
Describe the relationship between prevalence and predictive values
Describe accuracy and likelihood ratios as alternative methods of evaluating a diagnostic test
Notes
Sensitivity (% of positive test results in people with a disease): important for screening tests. The test is "sensitive" i.e. good at identifying people with the disease
Specificity (% of negative results in people without the disease): important as definitive tests (e.g. HIV). The test is "specific" for the disease, or "not-specific" (e.g. syndromic approach to vaginal discharge
Predictive value: % of positive/negative results that are true positive/negative (depends on sensitivity/specificity of the test & the prevalence of disease in the population)
Likelihood ratio (alternative way of describing test performance): probability of disease after a positive or negative test result (e.g. LR+=sensitivity/1-specificity)
Critically appraise a published paper
Evaluate the relevance of a published paper to your clinical practice or work
To develop an appropriate study design for the investigation of a real problem
To put into practice the methods discussed in the study design lecture
Basic principles of an outbreak investigation
Infectious diseases epidemiology and modelling