
Course unit
STATISTICAL METHODS FOR BIOENGINEERING
INP9087105, A.A. 2019/20
Information concerning the students who enrolled in A.Y. 2019/20
ECTS: details
Type 
ScientificDisciplinary Sector 
Credits allocated 
Core courses 
INGINF/06 
Electronic and Information Bioengineering 
9.0 
Course unit organization
Period 
Second semester 
Year 
1st Year 
Teaching method 
frontal 
Type of hours 
Credits 
Teaching hours 
Hours of Individual study 
Shifts 
Lecture 
9.0 
72 
153.0 
No turn 
Examination board
Board 
From 
To 
Members of the board 
1 A.A. 2019/2020 
01/10/2019 
15/03/2021 
BERTOLDO
ALESSANDRA
(Presidente)
DALLA MAN
CHIARA
(Membro Effettivo)
DEL FAVERO
SIMONE
(Supplente)
FACCHINETTI
ANDREA
(Supplente)
PEDERSEN
MORTEN GRAM
(Supplente)
SACCOMANI
MARIAPIA
(Supplente)
SAWACHA
ZIMI
(Supplente)
SCHIAVON
MICHELE
(Supplente)
SPARACINO
GIOVANNI
(Supplente)
VISENTIN
ROBERTO
(Supplente)

Prerequisites:

Elements of Probability and Statistics 
Target skills and knowledge:

Use the descriptive statistics for the representation of experimental data; understand the main statistical tests; knowing how to use the method of linear least squares with familiarity; make the student able to perform regression and correlation analysis, principal component analysis (PCA), independent component analysis (ICA), clustering. 
Examination methods:

The verification of knowledge and skills will be evaluated with a written exam, based on the material presented in the course and a computer test based on the material presented in the laboratory. 
Assessment criteria:

The written examination is divided into two parts. In the first, students must answer simple questions aimed at verifying the knowledge of a single technique or property discussed in the course.
The second part is of a more theoretical nature and concerns the knowledge of the theoretical bases of the main methods presented in class.
The computer test verifies the learning of both the most relevant notions and the processing techniques, which were presented during the laboratory hours carried out during the course.
The overall grade is the sum of the marks obtained in the individual parts. 
Course unit contents:

Descriptive statistics: frequency distributions, percentiles, graphical representations, position, dispersion and shape indices, average and variance calculation for grouped data, boxplots, comparative analyzes, variable correlations
Random variables: expected value, variance, confidence intervals, Chebychev inequality. The theorem of expectation. Discrete probability distributions: binomial, negative binomial, Poisson. Continuous probability distributions: exponential, gamma, normal. Vector random variables: independence, multivariate normal distribution.
Data acquisition: random sampling, distortions, experimental and observational studies, randomized controlled clinical trials, doubleblind, crossover studies.
Statistical tests: Normality test. Test to evaluate the difference between groups: Test T (coupled or not), ANOVA. The meaning of the pvalue. Nonparametric tests. Repeated measurements and posthoc comparisons: Bonferroni correction, False Discovery Rate, correction with permutations.
Calculation of the power of a test: sample power and amplitude
Experiment project: type of design (2 or more parallel groups, 1 paired group (prepost drawing), 2 crossed groups (crossover drawing), 2x2 parallel groups (factorial design), ranomized), exchangeability, systematic bias
Statistical inference: Linear regression; the linear least squares method, properties, bias, MSE, residuals, estimation error (variance of the estimator)
Verification of the relationship between variables: regression and correlation, rank correlation (Spearman). BlandAltman method.
Principal component analysis (PCA)
Regularization methods for linear models: Ridge regression, Lasso regression, Elastic Net, logistic regression
Independent component analysis (ICA)
Clustering: Kmeans, Fuzzy cmeans, Spectral, Hierarchical 
Planned learning activities and teaching methods:

The course will be perfomed by:
 lectures (around 65% of the total lesson hours)
 "hands on" lessons developing codes in Matlab (35%) and working on concrete case studies. 
Additional notes about suggested reading:

All the teaching material presented during the lectures (in pdf format) is made available using the Elearning platform. 
Textbooks (and optional supplementary readings) 

Hastie, Trevor J.; Tibshirani, Robert, The elements of statistical learningdata mining, inference, and predictionTrevor Hastie, Robert Tibshirami, Jerome Friedman. New York: Springer, 2009.

Innovative teaching methods: Teaching and learning strategies
 Case study
 Problem solving
Innovative teaching methods: Software or applications used
 Moodle (files, quizzes, workshops, ...)
 Matlab
Sustainable Development Goals (SDGs)

