C8349 - STATISTIC PLANNING OF EXPERIMENT AND DATA ANAYSIS

Learning outcomes

By the end of the course, the student has knowledge of the main experimental designs and understands the basic concepts and statistical methods for analyzing problems in the biomedical sciences. The student is able to plan biological studies, identify and apply the appropriate statistical tests using dedicated software, and interpret the results. Moreover, the student can organize and present data in a methodologically rigorous manner.

Course contents

SPECIFIC PREREQUISITES FOR THIS COURSE

Basic knowledge of biology and mathematics is recommended. No advanced knowledge of statistics or programming is required.

SPECIFIC CONTENTS OF THE COURSE

The course provides an applied introduction to experimental design and statistical data analysis in the biomedical and animal biotechnology fields. Statistical methods will be presented mainly from a practical perspective, with particular attention to the selection of appropriate analyses, the use of statistical software and the correct interpretation and presentation of results.

The syllabus is structured as follows:

Lectures (12 hours)

• The scientific method and experimental research: formulation of research questions and hypotheses; observational and experimental studies; identification of experimental objectives and outcomes.

• Types of biological data: qualitative and quantitative variables; categorical, discrete and continuous data; independent and dependent variables; experimental units and biological versus technical replicates.

• Principles of experimental design: control groups, randomization, replication and blocking; sources of variability; bias, confounding factors and pseudoreplication.

• Planning biological experiments: definition of treatment groups and experimental conditions; selection of appropriate controls; basic concepts of sample size, statistical power and effect size.

• Data organization and quality control: preparation of datasets for statistical analysis; identification of missing values, data-entry errors and outliers; principles of data transformation and normalization.

• Descriptive statistics and graphical representation of data: measures of central tendency and variability; frequency distributions; tables, box plots, histograms, scatter plots and other graphical methods commonly used for biological data.

• Introduction to statistical inference: populations and samples; probability distributions; confidence intervals; null and alternative hypotheses; p-values; type I and type II errors.

• Comparison between groups: parametric and non-parametric tests for independent and paired samples, including Student’s t-test, Mann–Whitney test and Wilcoxon signed-rank test.

• Analysis of categorical data: contingency tables; chi-square test and Fisher’s exact test.

• Analysis of variance: principles and applications of one-way and two-way ANOVA; comparison of multiple experimental groups; interaction between factors; post-hoc multiple-comparison procedures.

• Correlation and regression: evaluation of associations between biological variables; Pearson and Spearman correlation; introduction to simple linear regression and interpretation of regression models.

• Repeated measurements and dependent observations: introduction to experimental designs involving repeated measurements, longitudinal observations or matched biological samples.

• Introduction to the analysis of high-dimensional biological data: hierarchical clustering and principal component analysis for the exploration of omics datasets.

• Interpretation and presentation of statistical results: distinction between statistical and biological significance; interpretation of software outputs; preparation of tables and figures; transparent and methodologically rigorous reporting of methods and results

Seminars and educational visits (8 hours)

Seminars will be delivered by specialists in biostatistics and health-related research. These sessions will present practical applications of experimental design and statistical analysis in biomedical, veterinary and animal biotechnology research, with particular attention to real research questions, methodological challenges and the interpretation of results. In addition, educational visits to research centres or technological infrastructures may be organized to provide students with direct exposure to real-world contexts in which data are generated, analysed and used to support scientific and technological decision-making.

Laboratory/Practical Sessions (20 hours)

Practical sessions will involve the organization, graphical exploration and statistical analysis of biological datasets using dedicated statistical software. Students will learn how to select an appropriate statistical test, verify its main assumptions, perform the analysis and interpret the resulting output.

Exercises and case studies will be based on experimental problems relevant to animal biotechnology and biomedical research.

Each student will conduct an in-depth analysis of a case study based on a real dataset, organize the data, perform the appropriate statistical analyses, and finally write a short paper presenting and discussing their results.

Particular attention will be given to the applications in comparative and animal biotechnology: examples based on cell cultures, gene and protein expression, comparison of treatments, animal studies, diagnostic data and other experimental contexts relevant to biomedical and veterinary research.

Readings/Bibliography

The teaching materials for this course are available on the Virtuale Learning Environment (https://virtuale.unibo.it/?lang=en ).

Teaching methods

The course combines theoretical lectures, guided practical sessions, case studies and expert seminars. Lectures introduce the main principles of experimental design and statistical data analysis through examples drawn from biomedical, veterinary and animal biotechnology research.

During the practical sessions, students will work with biological datasets using dedicated statistical software. They will learn how to organize and explore data, select appropriate statistical tests, interpret software outputs and present results using suitable tables and graphs.

Case studies and group discussions will be used to identify experimental units, variables, controls, sources of bias and the most appropriate analytical approaches for different research questions. Seminars delivered by experts in biostatistics and health-related research will provide examples of the application of statistical methods in real research settings.

Assessment methods

The examination is designed to assess the achievement of the course learning outcomes, with particular reference to the student’s ability to plan a statistical analysis, select appropriate methods, interpret the results and present them in a methodologically rigorous manner.

Each student will conduct an in-depth analysis of a case study based on a real dataset. The student will be required to organize and explore the data, identify the appropriate statistical methods, perform the analyses using dedicated software, and write a short scientific paper presenting and discussing the results.

The paper must include the research question, a description of the dataset and variables, the statistical methods applied, the main results, appropriate tables and figures, and a critical interpretation of the findings.

The paper will be presented and discussed orally. During the discussion, the instructor will ask questions concerning the analytical choices, the interpretation of the results and the topics covered throughout the course. The aim is to assess the student’s theoretical knowledge, practical skills, critical thinking and command of discipline-specific terminology.

The examination is considered passed only if both the written report and the oral discussion are satisfactory. The minimum passing grade is 18/30. The final result will be communicated at the end of the oral examination.

The following grading criteria will be applied:

• 18–22: basic knowledge of the course topics and limited ability to analyse and interpret the results;

• 23–26: adequate knowledge and correct application of the main bioinformatics methods;

• 27–29: broad knowledge, good analytical autonomy and appropriate use of discipline-specific terminology;

• 30–30 with honours: comprehensive knowledge, excellent analytical and critical skills, and a clear and rigorous presentation of the project.

Students can register for exams through the AlmaEsami platform (http://almaesami.unibo.it/ ). Exams are scheduled during the designated periods in the academic calendar. Additional sessions are available for students beyond the standard program duration.

Students with learning disorders and/or temporary or permanent disabilities: please, contact the office responsible (https://site.unibo.it/studenti-con-disabilita-e-dsa/en/for-students ) as soon as possible so that they can propose acceptable adjustments. The request for adaptation must be submitted in advance (15 days before the exam date) to the lecturer, who will assess the appropriateness of the adjustments, taking into account the teaching objectives.

With regard to the learning assessment, limited, declared, and non-substantive use of AI is permitted for support activities, such as summarization and rephrasing. Substantive use of AI to complete parts of the assessment task is not permitted.

Teaching tools

Slide presentations will be used during lectures. Practical activities will be carried out through group work using students’ personal computers or the computers available in the computer room. Dedicated statistics software, public databases and online resources will also be used during the practical sessions.

In case of difficulty understanding the course content, the instructor is available for clarification meetings, which must be scheduled via email.

Office hours

See the website of Valentina Indio