Select Academic Year:     2017/2018 2018/2019 2019/2020 2020/2021 2021/2022 2022/2023
Professor
ERALDO FRANCESCO NICOTRA (Tit.)
Period
Second Semester 
Teaching style
Convenzionale 
Lingua Insegnamento
ITALIANO 



Informazioni aggiuntive

Course Curriculum CFU Length(h)
[30/48]  CLINICAL AND COMMUNITY PSYCHOLOGY [48/00 - Ord. 2020]  PERCORSO COMUNE 8 60

Objectives

The multivariate analysis methods course aims to provide the student with a set of notions suitable for structuring simple experimental designs, which are widely used in psychological research.
The course is divided into two sections. The first section approaches statistical some analysis methods which are related to simple and multiple linear regression, also addressing analysis of variance techniques to be used in main experimental designs (for independent groups and repeated tests).

The second section includes both data automatic processing in statistical programming environment and primarily geared, so to provide the basic knowledge for managing organization and structuring methods of statistical databases and consequent computerized statistical treatment. To this purpose, the course is equipped with the statistical package R, whose increasing use is now widely recognized for a proper data statistical analysis in science. The acquisition of skills on statistical software R is a constituent part of the output competencies provided by the program of the course.

The fundamental aim of the course is to enable the student to work out, in complete independence, the programming of the experimental evidence provided appropriate experimental design, an effective definition of the sample-data and its appropriate statistical modeling which involves data analysis.

The student will be allowed to develop a clear definition of the objectives of experimental research, to approach them properly in line with statistical analysis and interpretation, and to develop explanatory report of the results; all these substantive aspects are considered the main professional skills that students should acquire from the course..

Prerequisites

The student is requested to know the basic knowledge of the formal theory of probability and the major distributions of univariate probability (d.p.), as well as their univariate distribution functions (f.d.p.).

Among these, the student should possess an adequate knowledge of discrete and continuous probabilistic distributions such as binomial and hypergeometric distribution, normal distribution, student t-distribution (t), chi-square distribution (χ), Fisher distribution (F).

The student should also be able to implement a formal system of assumption verification involving inference test statistic Z, T and F, to formulate correct statistical hypotheses and to draw appropriate statistical and scientific conclusions.

Students should possess adequate language comprehension and logic text processing capabilities in referment to the structure of scientific hypotheses and their articulation in a statistical sense of view.

Within the course, the presentation of scientific manuals and reports of international importance requires an adequate knowledge of English.

It is also necessary to possess basic skills in using elementary computer functions in Windows or McIntosh environment.

Contents

Below is depicted a detailed program on the topics covered in the classroom.
Presentation of the R statistical "package" and the R-Studio development environment.
Installing the software in a Windows or Mac environment;
Use of the R-Studio work environment for the implementation of statistical analysis commands.
Installation of additional command libraries to the basic package;
Structuring of the data file and relative definition of the variables observed on the sample-data;

Linear Regression Analysis:
Direct and indirect causal relationships;
Linear algebraic model;
Linear statistical model;
Least squares method;
Estimation of linear parameters;
Normal equations of the regression line;
Sum of squares of the linear regression;
Pearson's R coefficient and covariances;
Simple linear regression;
Multiple linear regression;
R squared as a data-model fit index;
Standard error of parameters;
T test on single parameters;

Analysis of variance:
Between subjects model with single experimental factor;
Between subject models with two completely randomized experimental factors;
Model with single experimental factor within subjects.

Teaching Methods

The main teaching method consists of lectures with a duration of two hours. Frontal activities will address issues related to the program of the course, with examples of the calculation methods. If health emergency reasons may impede frontal lectures be held, alternative online connection will be activated throughout the telematics system Adobe Connect, whose access has been predisposed by the Athenaeum. All lessons given in the online mode will be recorded. Students will attend them through the Internet connection by following the specific links which is related to the lesson content. The links will be accessible to students from the teacher's personal page of the course in the section “Didactic materials”.

Additional educational materials are presented within the Multivariate Analysis Methods online course inside the Moodle platform accessible at the following link:
https://elearning.unica.it/,
or, alternatively, in the section linked to the educational materials of the teacher's personal page using the link:
http://people.unica.it/eraldofrancesconicotra/didattica/materiale-didattico/metodi-di-analisi-multivariata/,

Students who are regularly enrolled will have access to the subsidiary teaching materials present therein. To access the online course, it will be sufficient to digit the own credentials normally used for accessing to the University's telematic services. To register for the online course, simply connect via the following link:
https://elearning.unica.it/course/view.php?id=117.

The exam is in written form. Students must demonstrate their theoretical and methodological knowledge which lead to the establishment of a statistical analysis plan as outlined:
analysis and identification of structural relationships that are related to the variables involved in the experimental protocols proposed in place of examinations;
realization of a statistical analysis program, under the R programming environment, focusing on the draft of a statistical analysis output;
Quantitative and qualitative assessment of the parameters estimated by the analysis model;
drafting of a report in scientific format of the results with particular reference to:
formulation of the scientific objective of the research;
Statistical evaluation on the consistency of the obtained results;
Synthetic scientific conclusions on the results coming from the analysis.

As for the evaluation of the level of competence reached on the use of statistical models covered in the course, this assessment will be based on the degree of logical and argumentative coherence of statistical analysis model adopted, with clear reference to the structuring of the hypothesis under study and to the scientific conclusions described. Finally, the ability to synthetize and the linguistic correctness of the expressions will also be evaluated (correct use of written language).

Verification of learning

The exam is in written form. Students must demonstrate their theoretical and methodological knowledge which lead to the establishment of a statistical analysis plan as outlined:
analysis and identification of structural relationships that involve the variables involved in the experimental protocols proposed in place of examinations;
realization of a statistical analysis program, under the R programming environment, aimed at drafting a statistical output of the analyzes;
Quantitative and qualitative assessment of the parameters estimated by the analysis model;

drafting of a report in scientific format of the results with particular reference to:
formulation of the scientific objective of the research;
Statistical evaluation of the consistency of the results obtained;
Synthetic scientific evaluation of the results from the analysis.

As for the assessment of the level of competence reached on the use of statistical models covered in the course, this assessment will be based on the degree of logical and argumentative coherence of statistical analysis model adopted, with clear reference to the structuring of the hypothesis under study and to the scientific conclusions described. Finally, the ability to synthesis and linguistic correctness of the expressions will still be evaluated (correct use of written language).

Texts

Reference books:
Keppel, G., (1991). Design and Analysis: a researcher's handbook. Prentice-Hall, Toronto, CA. ISBN: 0-13-200775-4.

Additional educational materials are present within the Psychometrics online course inside the Moodle platform accessible at the following link:
https://elearning.unica.it/.

Students who are regularly enrolled will have access to the subsidiary teaching materials present therein. To access the online course, it will be sufficient to register using their own credentials for access to the University's telematic services. To register for the online course, simply connect via the following link:
https://elearning.unica.it/course/view.php?id=117.

More Information

The office hours will take place on Wednesday, from 16.00 to 18.00, weekly, at the Department of Pedagogy, Psychology, Philosophy wherever possible in function of health emergency. Alternatively, on Skype using the platform Skype name: live: nicer_24, prior appointment request to the teacher which should be sent at: enicotra@unica.it.

Questionnaire and social

Share on: