Teaching code

4S007231

Teacher

Simone Accordini

Credits

3

Language

Italian

Scientific Disciplinary Sector (SSD)

SECS-S/02 - STATISTICS FOR EXPERIMENTAL AND TECHNOLOGICAL RESEARCH

Period

Lm Sio BZ 1A 1S (Coorte 2021) dal Nov 15, 2021 al Mar 31, 2022.

Lessons timetable Moodle Seminars 0

To show the organization of the course that includes this module, follow this link:  Course organization

Learning outcomes

The course is aimed at providing the theoretical tools to assess the frequency of diseases in human populations and the associated risk factors, i.e. skills in epidemiology and biostatistics.
At the end of the course the student must demonstrate to have acquired knowledge and skills concerning the main designs of an observational epidemiological study and the statistical methods for the analysis of biomedical data, and to know how to interpret and communicate the results of an analysis in a clear and concise way.

Program

DESCRIPTIVE STATISTICS:
- measurement of a statistical variable (measurement scales, validity, precision and accuracy);
- univariate and bivariate distributions (contingency tables);
- how to summarize the distribution of a statistical variable (measures of central tendency and measures of dispersion).
PROBABILITY:
- elements of probability theory (definitions of probability, axiomatic theory of probabilities, rules of probability calculation, independent and conditional probabilities, probability estimates);
- expected events;
- discrete random variables (Bernoulli distribution);
- continuous random variables (Gauss, Student's T and chi-squared distributions);
- standardised normal deviate;
- validity of a diagnostic test (sensitivity, specificity and ROC curves);
- performance of a diagnostic test (positive predictive value and negative predictive value).
INFERENTIAL STATISTICS:
- an outline of sampling theory;
- point estimation (sampling distribution of a mean and a proportion);
- interval estimation (confidence interval of a mean and a proportion);
- statistical hypothesis test (null and alternative hypotheses, test statistic, regions of rejection and non-rejection of the null hypothesis, type I and type II errors, power of a statistical test);
- statistical significance test (p-value);
- Z and Student's T tests;
- Pearson's chi-squared test;
- relationship between confidence interval and hypothesis testing.
PRINCIPLES OF THE OBSERVATIONAL EPIDEMIOLOGICAL RESEARCH:
- definition and objectives of the epidemiological research;
- statistical variables of interest in the epidemiological research (outcome and determinant);
- measures of disease frequency (prevalence, cumulative incidence and incidence rate);
- the occurrence relation and measures of association (attributable risk, relative risk and odds ratio);
- design and analysis of the observational epidemiological studies (ecological, cross-sectional, case-control, cohort);
- effect modification;
- causal interpretation of an empirical association: random variability, systematic variability (selection and information bias), confounding.

The module is structured in frontal lessons during which the topics listed in the program are presented and discussed, exercises are solved and results of statistical analyses of biomedical data are interpreted. The didactic material (slides of the lessons, exercises with solutions) is made available to the students on the e-learning web page of the course (Moodle platform).

Bibliography

Examination Methods

The final examination is a written test (duration of the test: 2 hours). The written test covers potentially all the topics listed in the program and is structured in groups of questions related to solving exercises and understanding the theory. Items are formulated as short answer questions and multiple-choice questions.
The questions in the written test aim to assess the ability:
- to calculate probabilities and epidemiological measures, and to perform basic inferential statistical analyses, critically using the methodological tools learnt during the course;
- to identify the design of an observational epidemiological study and to justify its choice in a research context described in the examination text;
- to identify the presence of effect modification and confounding using descriptive analyses of contingency tables.
Each question is assigned a score. The grade of the test (expressed in thirtieths) is given by the sum of the scores obtained by correctly answering the individual questions. The test is considered passed if the student gains a minimum grade of 18/30.