LO1. To develop knowledge about the new challenges and potential for data access in digital societies;
LO2. Identify the main sources of data in social sciences and develop skills to enable access to them;
LO3. Develop skills in database preparation, management and data screening and validation;
LO4. To develop knowledge and skills to apply basic methods of descriptive analysis of data (univariate and bivariate) and presentation of results;
LO5. To develop basic skills in the use of SPSS software.

1. Social sciences research in the era of "big data". Types of data, challenges, opportunities and ethical issues;
2. Data sources: primary and secondary data;
3. Secondary data: types of sources and modes of access; structured and unstructured data;
4. Primary data: information collection tools, information collection methods, construction of databases (SPSS);
5. Preparation of databases (SPSS): validation (basic operations for error detection and correction); managing aggregated data from micro data; recoding of variables and construction of new variables;
6. Descriptive statistical analysis with SPSS: univariate analysis, bivariate analysis, report of tables and graphs, export of results to other programs.

Two possibilities:
1. Assessment throughout the semester: Individual report, approximately 10 pages.
2. Evaluation by examination: Individual exercise or individual report at the end of the school year (PGADCS examination season).

LO1: Identify the main statistical concepts for hypotheses tests
LO2: Select the most adequate hypothesis test, given the problem under analysis, the objective and the type of variables
LO3: Interpret and report the results
LO4: Use the statistical package SPSS to conduct inferential data analysis

PC 1. Hypotheses tests: main concepts
PC 2. Parametric tests: presentation, interpretation and implementation
PC 2.1.T Test for two independent samples
PC 2.2.T Test for two paired samples
PC 2.3. Two-way ANOVA
PC 3. Non parametric Tests: presentation, interpretation and implementation
PC 3.1. Non-parametric Tests: Kolmogorov-Smirnov, Shapiro-Wilk and Chi-Square
PC 3.2. Chi-Square independence test
PC 3.3. Mann-Whitney test
PC 3.4. Wilcoxon test
PC 3.5. Kruskall-Wallis test

The student can choose one of the following assessment methods:

1) Throughout the semester: individual essay with a minimum score of 10 required. The essays must be original, authored by the students themselves, both from the point of view of writing, as well as the organisation of ideas and construction of the argument, in accordance with the Iscte Code of Academic Conduct and the Iscte Code of Ethical Conduct in Research.

2) By examination: individual exercise with a minimum score of 10 points.

Students who successfully complete this curricular unit will be able to:
LO1. Identify the main goal of each of the methods explored in the course.
LO2. Apply and interpret the results of a Linear Regression model.
LO3. Apply and interpret the results of Binary Logistic Regression model.
LO4. Conduct, with SPSS, a Linear Regression and a Binary Logistic Regression.
LO5. Summarize, present and interpret the results in order to write a data analysis report.

1. Linear Regression Model
1.1.Definition and assumptions
1.2.Estimation of parameter; multiple correlation coefficient and coefficient of multiple determination; Inference about the model
1.3.Partial and semi-partial correlation coefficients
1.4.Discussion and presentation of the results
1.5. Hierarchical regression
1.6.Applications with SPSS
2. Categorical regression: Binary Logistic
2.1.Logistic Regression versus Linear regression: models comparison
2.2.Logit transformation
2.3.Effect size of the model
2.4. Testing the model: Qui-square test
.2.5. Logistic Regression Coefficients: odds and odds ratio
2.6. Testing the coefficients: Wald test
2.7.Outliers: analysis of the residuals
2.8.Analyses with SPSS

There are two options for evaluation:
1. During the semester: individual written test at the end of the curricular unit (100%).
The student has to have a minimum of 70% attendance in class.
2.Evaluation by final exam: individual assignment at the end of the semester (100%).

LO1 | Define concepts of moderation and mediation; identify and distinguish the different effects
LO2 | To design moderated and mediated models
L03 | To evaluate the adequacy of Linear Regression for testing moderated and mediated models
L04 | To evaluate the assumptions of Multiple Linear Regression
L05 | Upgrade and deepen knowledge of linear regression models to test moderation and mediation models
L06 | Apply multiple linear regression to test moderation and mediation models
L07 | Analyze and interpret the results of different models
L08 | To present the results in a report or in a scientific paper

1. Moderator and mediated models
1.1. Moderation: interaction effect
1.2. Mediation: chain of effects
1.3. Exploring papers with moderation and mediation
2. Modelling moderation using OLS regression
2.1. Main effect and interaction effect
2.2. Quantitative moderator
2.3. Dummy moderator
2.4. Applying software (SPSS and PROCESS)
2.5. Report results in a thesis/paper
3. Modelling mediation by OLS regression
3.1. Modelling with quantitative mediator
3.2. Estimate and test indirect effect using bootstrapping
3.3. Partial and complete mediation
3.4. Applying software statistics (SPSS and PROCESS)
3.5. Report results in a thesis/paper

There are two options for assessment:

1. Assessment during the semester - individual work (100%)

Delivery of this work requires attendance at at least 70 per cent of the course unit's lessons.

2. Assessment by exam: written test to be taken at the end of the semester (100%).

At the end of this unit students will be able to:
LO1 - Design a Report
LO2 - Select adequate statistical methods according the objectives of the research
LO2 - Present, analyse and interpret data.

1. Structure of a data analysis report: main sections of a report and dimension
2. Selection the suitable statistical methods to answer the research questions/hypotheses
3. Report of the main results (tables and graphs)
4. Joint the main report and appendices.

Students prepare a report of data analysis where should be applied some of the statistical methods developed during the different curricular units.
For that purpose, students can use own research data or, alternatively, data provided by the coordination of the curricular unit.
In the performance evaluation, students have to have a minimum of 60% attendance of all classes of the post-graduation curricular unit.
This curricular unit does not include the possibility of evaluation by final exam.

LG1. Collect and organize information that best suits the goals of visual communication.
LG2. Distinguish between different types of statistical indicators and understand when and how they should be used.
LG3. Apply visual variables according to its properties, depending on the nature of the quantitative or qualitative information.
LG4. Using the most appropriate chart models and maximize its power of communication.
LG5. To analyze critically informative graphic expressions of in a variety of disciplinary contexts.
LG6. Make a graphical storytelling (or alternatively, a scientific poster, an abstract or graphic lead, a comic informative band, a visual/graphic explanation or an infographic), from the stage of collection, processing and selection of relevant information to the stage of portrayal, communication and construction of a visual storytelling.

Programatic contents (PC) articulated with the learning objectives.
I.Graphical and statistical literacy: learning a new language
PC1. Statistical indicators
PC2. Semiotics of communication and perception
PC3. Pictography
II.Charts: turning the trivial into the unusual
PC4. Communicating Graphics
PC5. Mixed or doble-use graphics
PC6. Exploratory graphics
PC7. Make a graphic story

Evaluation during the semester:
Preparation of a report with visual representations appropriate to the data and work objectives - 100%
Minimum score of 10 required.
Final exam:
Individual assignment (100%).

LO1: Identify the main statistical concepts with relevance in sampling and estimation
LO2: Select samples and calculation of sample size
LO3: Use and calculate weights
LO4: Diagnose the non-response pattern and propose forms of imputation.
LO5: Estimation ant test of parameters
LO6: To evaluate the quality of the adjustment of the sample to the target population.

Programatic contents (PC) articulated with the learning objectives.
PC1. Introduction
1.1 Statistics and parameters
1.2 Probabilities
1.3 Normal Distribution
PC2. Sampling
2.1 Population list
2.2 Sample selection
2.3 Errors
2.4 Sample size
PC3. Weights
Construction and activation of weights
PC4. Non-response
5.1 Diagnosis and pattern analysis
5.2 Imputation
PC5. Estimation
5.1 Point estimation
5.2 Interval estimation
5.3 Robust estimation (the problem of outliers)
PC6. Statistical tests
6.1 Hypotheses, Errors, Decision.
6.2 One sample t-test
PC7. Quality of the adjustment
7.1 Kolmogorov-Smirnov and Shapiro-Wilk
7.2 Chi-square test of goodness of fit

There are two options for evaluation:
1. Assessment throughout the semester:
Resolution of a case study (group exercise): 40%.
Individual assignment: 60%.
In order to get a positive grade in the curricular unit, the mark of each of the assignments cannot be below 8.
In the performance evaluation, the student has to have a minimum of 70% attendance in class.
2. Evaluation by final exam: individual assignment (100%).

It is intended that students achieve the following objectives during the learning process:
LO. Acquire and develop knowledge about Multiple Correspondence Analysis (MCA)
LO2. Acquire and develop knowledge about Cluster Analysis
LO3. Apply and articulate cluster analysis with multivariate analysis methods
LO4. Analyze and interpret the statistical results
LO5. Use statistical analysis software to carry out a Multiple Correspondence Analysis and a Cluster Analysis.
LO6. Report the results in a paper.

1.Multiple Correspondence Analysis (MCA)
1.1.Introduction
1.2.MCA input matrices
1.3.Optimal and multiple quantification of qualitative data
1.4.Eigenvalues, inertia and discrimination measures
1.5.Selection and interpretation of the dimensions
1.6.Graphical display of the variables, categories and objects
1.7.Suplementar (or non-optimal) variables
2.Cluster analysis - hierarquical methods:
2.1.Objectives
2.2.Measures of similarity / distance
2.3.Cluster methods
2.4.Reading the dendrogram and selection of the number of the clusters
2.5.Validation and description of the clusters
3.Cluster analysis - non-hierarchical Cluster Analysis
3.1.Distinction between optimization and hierarchical methods
3.2.K-Means method
4.Clusters analysis combined with Principal Component Analysis
5 Clusters analysis combined with Multiple Correspondence Analysis.

There are two options for evaluation:
1. During the semester: individual written test at the end of the curricular unit (100%).
The student has to have a minimum of 70% attendance in class.
2.Evaluation by final exam: individual assignment at the end of the semester (100%).

LO1 | Acquire and develop knowledge of Principal Component Analysis (PCA)
LO2 | Situate and compare Principal Component Analysis (PCA) with Exploratory Factor Analysis (EFA)
LO3 | Acquire and develop knowledge of Confirmatory Factor Analysis (CFA)
LO4 | Apply Principal Component Analysis using appropriate software
LO5 | Apply Confirmatory Factor Analysis using appropriate software
LO6 | Analyse and interpret the results (PCA and CFA)
LO7 | Report the results in a scientific article, dissertation or thesis

1. Principal Component Analysis (PCA)
1.1. Introduction
1.2. Definition of principal components
1.3. Eigenvalues and communalities
1.4. Criteria's for extraction the principal components
1.5. Rotation of the components: orthogonal and non-orthogonal methods
1.6. Definition and interpretation of factor scores
1.7. Reliability analysis (Cronbach's Alpha) and computing summated scales
1.8. Applying with SPSS software or equivalent
1.9. Interpretation and reporting results in a paper, a thesis
1.10. Comparison with Exploratory Factor Analysis (EFA)
2. Confirmatory Factorial Analysis (CFA)
2.1. Comparison between PCA and CFA
2.2. Measurement model
2.3. Variables, constructs and errors
2.4. Specifying the model
2.5. CFA Goodness-of-Fit Statistics
2.6. Construct validity
2.7. CFA Assumptions
2.8. Applying with AMOS software or equivalent
2.9. Interpretation and reporting results in a paper, a thesis

There are two options for evaluation:
1. Assessment during the semester: individual written test at the end of the curricular unit.
Access to assessment requires attendance at least 70% of the classes in the course.
2. Assessment by final exam: Individual exam to be taken at the end of the academic year during the postgraduate exam season.

Students who successfully complete this curricular unit will be able to:
LO1 ? Identify different strategies to develop content analysis with MaxQda and know how to adapt and use their potential to diverse documents such as interview, focus groups, press articles, among other;
LO2 -Plan and execute a content analysis methodological design using MAXQDA, adapted to the material in questions and to the analytical goals;
LO3 - Present MAXQDA outputs in reports and other scientific products.

1 Introduction to Content Analysis
1.1 Qualitative traditions and Research
1.2 Content Analysis (Theory): history, myths and definitions
1.3 Content Analysis (practice): goals, organization and examples
2 Data set organization
2.1 Documents and material
2.2 Rules in constructions. categories
2.3 The variables
3 Coding
3.1 Types of coding (and implications)
3.2 Colors and types of categories
4 Outputs
4.1 Classic textual
4.2 Words
4.3 Graphs
Document portraits
Codeline
Document comparison chart
World cloud
4.4 Quantitative
Categories frequencies Frequências das categorias
Subcodes statitsics
Code Matrix Browser
Code Relation Browser
Crosstabs
Similarity Analysis
5 Presentation and discussion of results
5.1 Content Analysis Design
5.2 Presentation and discussion of results

here are two options for the assessment:
1. During the semester: students will be assessed based on carrying out a content analysis report of individual interviews, group interviews or document analysis of the student's choice (100% of the final grade).
Access to the assessment requires attendance at at least 70% of the classes in the curricular unit.
2. Assessment by exam: practical test in MaxQda (100% of the grade).


I

LO1 - Understand the methodological implications related to the complex structure of data.
LO2 - Understand the theoretical framework and assumptions associated with multilevel modelling
LO3 - Specify appropriate multilevel models, considering the research questions.
LO4 - Conduct two-level model analyses using the statistical software (JAMOVI and JASP).
LO5 - Interpret and present results of MLM analyses.

1. Multilevel models
1.1. Hierarchical structure of the data
1.2. Data requirements to use multilevel analysis
1.3. Intraclass correlation
2. Linear mixed effects model
2.1. Fixed effects and random effects
2.2. Mixed-linear model equations
2.3. Selection of random effects
3. Model interpretation and inferential objectives
4. Extensions ? nonlinear mixed effects models
5. Applications
6. Report data in a paper /thesis

Assessment during the semester" takes the form of an individual assignment (100%).

Submission of this work requires attendance at at least 70% of the course unit's classes.

This course does not include assessment by examination.