Identifying Data 2022/23
Subject (*) Multivariate Analysis of Social Data Code 615G01206
Study programme
Grao en Socioloxia
Descriptors Cycle Period Year Type Credits
Graduate 2nd four-month period
 Second Obligatory 6
Language
Spanish
Teaching method Face-to-face
Prerequisites
Department Socioloxía e Ciencias da Comunicación
Coordinador
Cotillo Pereira, Alberto
 E-mail
a.cotillo@udc.es
Lecturers
Cotillo Pereira, Alberto
 E-mail
a.cotillo@udc.es
Web
General description A asignatura de Análise Multivariante de Datos Sociais ten como obxectivo proporcionar as ferramentas conceptuais e prácticas necesarias para a análise de datos en ambientes de alta complexidade en que as ferramentas uni e bivariadas son insuficientes, é dicir, na gran maioría das situacións sociais. É posible que non hai fenómeno social que poda ser entendido correctamente só a partires da análise da distribución dunha variable, ou da relación entre dúas variables. Esta asignatura ten aplicación directa en calquera situación na que sexa necesario atender a máis de dúas variables. A súa visión é eminentemente sociolóxica, xa que ten como obxectivo a formación de graduados en socioloxía. Os artigos de investigación, os estudos de casos e os exemplos que iden usarse refírense ao importante fluxo da investigación sociolóxica e só neste fluxo ten sentido.

Study programme competencies
Code Study programme competences
A5 Aprendizaje de los conceptos y de las técnicas estadísticas aplicadas a la sociedad humana.
A7 Conocimiento y dominio de la metodología de las ciencias sociales y de sus técnicas básicas y avanzadas (cuantitativas y cualitativas) de investigación social; con especial atención a los aspectos de muestreo y de los programas informáticos de aplicación.
A14 Capacidades en elaborar, utilizar, e interpretar indicadores sociales e instrumentos de medición social.
A15 Conocimientos y habilidades para plantear y desarrollar una investigación aplicada en las diferentes áreas de la sociedad.
A16 Conocimientos y habilidades técnicas para la produción y el análisis de los datos cuantitativos y cualitativos.
A26 Saber elegir las técnicas de investigación social (cuantitativas y cualitativas) pertinentes en cada momento.
B3 Capacidad de análisis y síntesis.
B4 Resolución de problemas.
B5 Capacidad de gestión de la información.
B6 Comunicación oral y escrita en la lengua nativa.
B7 Conocimientos de informática relativos al ámbito de estudio.
B12 Trabajo en equipo.
B21 Aprendizaje autónomo.
B27 Capacidades en reconocer la complejidad de los fenómenos sociales.
C1 Expresarse correctamente, tanto de forma oral como escrita, en las lenguas oficiales de la comunidad autónoma.
C3 Utilizar las herramientas básicas de las tecnologías de la información y las comunicaciones (TIC) necesarias para el ejercicio de su profesión y para el aprendizaje a lo largo de su vida.

Learning aims
Learning outcomes Study programme competences
Upon successful completion of this course, students will be able to select the multivariate analysis technique appropriate to the research question A5
A7
A26
 B21
Upon successful completion of this course, students will be able to handle the SPSS statistical package for the analysis of social data A7
A14
A16
 B4
B7
B21
 C3
Upon successful completion of this course, students will be able to differentiate the phases and tasks involved in the systematic application of each of the multivariate analysis techniques exposed A7
 B21
Upon successful completion of this course, students will be able to analyze social data of different types by applying multivariate analysis techniques A5
A7
A16
 B3
B27
 C1
Upon successful completion of this course, students will be able to interpret the results of research involving the use of multivariate analysis techniques A5
A7
A16
 B3
B27
 C1
Upon successful completion of this course, students will be able to extract the relevant information from large sets of social data A15
A16
 B3
B5
B12
B27
 C1
Upon successful completion of this course, students will be able to exhibit in public a scientific article in which the studied techniques of multivariate analysis are applied B3
B6
 C1
Upon successful completion of this course, students will be able to apply the techniques studied to real research situations A7
A14
A15
A16
A26
 B3
B4
B12
 C1

Contents
Topic Sub-topic
LESSON 1: EXPLORATORY DATA ANALYSIS Exploratory data analysis with SPSS. Descriptive statistics. Graphic examination of the data: Boxplots and Stem-and-Leaf Graphics. Construction and interpretation of tables. Construction and interpretation of tables based on multiple responses. Social data applications.
LESSON 2: MULTIVARIATE ANALYSIS TECHNIQUES CLASSIFICATION Relevance of multivariate analysis. Definition. Measurement types. Types of variables. Relationship. Description of multivariate analysis techniques. Classification criteria. Types of research problems.
LESSON 3: SIMPLE AND MULTIPLE REGRESSION ANALYSIS Definition of regression analysis. Least squares criterion. Forecast errors. Predictive ability. Special features of the multiple regression analysis. Variable selection methods. The problem of multicollinearity. The research process: objectives, design, assumptions, extraction, interpretation and validation.
LESSON 4: FACTOR AND PRINCIPAL COMPONENT ANALYSIS Historical background. Definition. Factor solution. Common and specific variance. Factor Analysis vs. Principal component analysis. Applications and uses. The research process: objectives, design, assumptions, extraction, interpretation and validation.
LESSON 5: CORRESPONDENCE ANALYSIS Scopes. Definition of correspondence analysis. Research objectives. Limitations of correspondence analysis. The basic structure of the data matrix. Central concepts. Multiple correspondence analysis. The research process: objectives, design, assumptions, extraction, interpretation and validation.
LESSON 6: CLUSTER ANALYSIS Definition of cluster analysis. Objectives. Procedure. Similarity measures. Clustering methods. Limitations of cluster analysis. The research process: objectives, design, assumptions, extraction, interpretation and validation.
LESSON 7: DISCRIMINANT ANALYSIS Historical background. Definition of discriminant analysis. Objectives. Multivariate profiles. Discriminating variables. Discriminant functions. Reclassification. The research process: objectives, design, assumptions, extraction, interpretation and validation.
LESSON 8: LOGISTIC REGRESSION ANALYSIS The logic of logistic regression. Preconditions for logistic regression. Logistic regression assumptions. Extraction and estimation of regression model fit. Interpretation of logistic regression coefficients. Probit analysis. The research process: objectives, design, assumptions, extraction, interpretation and validation.

Planning
Methodologies / tests Competencies Ordinary class hours Student’s personal work hours Total hours
Guest lecture / keynote speech A5 A7 A26 B21 30 0 30
ICT practicals A5 A7 A14 A16 B3 B6 B7 B27 C1 C3 10 30 40
Mixed objective/subjective test A5 A7 A26 B6 B21 2 38 40
Supervised projects A5 A7 A14 A15 A16 A26 B3 B4 B5 B6 B12 B27 C1 0 30 30
 
Personalized attention 10 0 10
 
(*)The information in the planning table is for guidance only and does not take into account the heterogeneity of the students.

Methodologies
Methodologies Description
Guest lecture / keynote speech The explanation of the theoretical content of each of the topics will take place in the classroom from previous readings that students had to perform. These readings are the basic bibliography of the subject and are available in the school library. The objective test will be based on the knowledge of those basic readings.
ICT practicals Throughout the development of the sessions, some ICT practices will be made about any of the analytical techniques taught. The completion of each practice will involve mastering any computer application for data analysis.
Mixed objective/subjective test At the end of the sessions there will be a theoretical mixed test for students to show their understanding of the concepts studied.
Supervised projects The teacher will assign a research topic to each group in order to apply the analytical techniques studied to a secondary database. This supervised work will be done in groups of no more than three students.

Personalized attention
Methodologies
ICT practicals
Supervised projects
Description
Practices through ICT will have personalized attention from the teacher in the classroom.
Throughout the performance of the tutored project, students must attend at least twice tutorials. That tutored project will be done in groups of no more than three students. As far as possible it will be avoided that the students do the work alone.

Assessment
Methodologies Competencies Description Qualification
Mixed objective/subjective test A5 A7 A26 B6 B21 The mixed test will consist of an exam at the end of the lessons.
All students who do not wish to be evaluated through continuous evaluation may take the exams of the official announcements. That exam will have a theoretical and a practical part. 		50
ICT practicals A5 A7 A14 A16 B3 B6 B7 B27 C1 C3 Throughout the course, practices that will involve the application of the studied technique to a particular case will be held. 30
Supervised projects A5 A7 A14 A15 A16 A26 B3 B4 B5 B6 B12 B27 C1 The supervised project will consist in the performance of a research work from the beginning to the end.
Thus, students should use software for data processing, analyze the results and write the research report. Teamwork is fostered, so that work must be done in groups of two or three pupils. 		20
 
Assessment comments

For the purposes of
the evaluation in the subject, a distinction will be made between students in
continuous evaluation and students in non-continuous evaluation. Those students
who do not deliver any of the assessable activities (practicals, supervised
work or exam) will be considered to have opted for the non-continuous
assessment. Students who submit some practice, the supervised work and the exam
will be understood to have opted for continuous assessment.

The evaluation of
the effort of the students who choose the continuous evaluation will be based
on a system of points that they will have to accumulate throughout the
semester. The maximum number of points that students can obtain will be 100 (30
in the practices, 20 in the work and 50 in the mixed test). Their final grade
will depend directly on the number of points they accumulate. Students in the
continuous assessment will successfully pass the subject when they meet each
and every one of the following three conditions: (1) attend at least 75% of the
classes in which attendance is controlled; (2) accumulate 50 or more points and
(3) obtain in each of the tests, at least, a third of the points in play (10 in
practices, 7 in supervised work and 17 in the exam). In some of the classes the
teacher will pass a signature sheet to the students to control their
attendance.

Students in the
non-continuous assessment should only take the exam of the official call in
June. To pass, they must obtain at least 50 points to pass, since the
theoretical part will award a maximum of 50 points and the practical part will
award a maximum of 25 points.







On the second opportunity in July, no distinction will be made between
students in continuous assessment or not. The grades of any of the practices,
assignments or any other assessable activity from past courses will not be
saved. In no case will the grades obtained in any of the assessable activities
of an opportunity be saved in any of the others.















The teacher reserves the right
to make changes along the course, provided they are not in contradiction with
any of the information contained herein.

Sources of information
Basic Cea D'Ancona, M. A. (2002). Análisis multivariable. Teoría y práctica en la investigación social. Madrid. Síntesis
Hair, Joseph F.; Anderson, Rolph E.; Tatham, Ronald L. y Black, William C. (2001). Análisis multivariante. Madrid. Prentice-Hall
Bisquerra Alzina, Rafael (1989). Introducción conceptual al análisis multivariable. Barcelona. PPU
Pardo Merino, A. y Ruiz Díaz, M.A. (2002). SPSS 11. Guía para el análisis de datos. Madrid. McGraw-Hill
Díaz de Rada, Vidal (2002). Técnicas de análisis multivariante para investigación social y comercial. Madrid. Ra-Ma

Complementary Peña, Daniel (2002). Análisis de datos multivariantes. Madrid. McGraw-Hill
Pérez López, César (2009). Análisis de datos. Técnicas con SPSS 15. Madrid. Prentice-Hall
Levy Mangin, J.P. y Varela Mallou, J. (2003). Análisis multivariable para las Ciencias Sociales. Madrid. Prentice-Hall
Pérez López, César (2004). Técnicas de análisis multivariante de datos. Aplicaciones con SPSS. Madrid. Pearson Education


Recommendations
Subjects that it is recommended to have taken before
Statistics Applied to the social sciences 1/615G01101
Social Research Methods and Techniques/615G01105
Statistics Applied to the social sciences 2/615G01201

Subjects that are recommended to be taken simultaneously

Subjects that continue the syllabus

Other comments


(*)The teaching guide is the document in which the URV publishes the information about all its courses. It is a public document and cannot be modified. Only in exceptional cases can it be revised by the competent agent or duly revised so that it is in line with current legislation.