Learning objectives

Referring to knowledge

• Getting to know the basic principles and phases of a scientific investigation.
• Becoming familiar with the necessary ingredients of scientific research: variables, hypothesis, etc.
• Identifying different types of research designs used in Cognitive Sciences.
• Selecting correctly the research design when planning an investigation.
• Applying the appropriate statistical analysis for each type of design and variables.
• Being critical when reading others’ research and reports.

Referring to abilities, skills

• Using statistical software: SPSS, R, jamovi
• Interpreting the results of statistical software
• Being capable of planning a research, starting for the precise definition of the aim and ending with its dissemination

Referring to attitudes, values and norms

• Avoid questionable research practices: confirmation bias, selective reporting
• Be critical when reviewing one’s own research and reports.

 

Teaching blocks

1. Bases of scientific research

1.1. Scientific method: need, characteristics, principles
1.2. Approaches to scientific research
1.3. Hypothesis, theories, models
1.4. Variables: definitions and classifications
1.5. Validity: internal, external

2. Phases of scientific research

2.1. Research problem and bibliographic search
2.2. Research design
2.3. Sampling
2.4. Data collection
2.5. Data organization
2.6. Data analysis: principles and options
2.7. Interpretation of results
2.8. Dissemination: scientific articles

3. Research designs and their analyses 
3.1. Independent groups designs
3.2. Matched groups designs
3.3. Repeated measures designs
3.4. Factorial designs
3.5. Mixed factorial designs
3.6. Single-case experimental designs
3.7. Nonexperimental designs: studying association

4. Linear regression
4.1. Bases: estimation, predictive capacity, assumptions, diagnostics
4.2. Simple linear regression
4.3. Multiple linear regression: selecting predictors, collinearity
4.4. Analysis of covariance: statistical control of extraneous variables

5. Extensions of regression model
5.1. Polynomial regression
5.2. Linearizing nonlinear models
5.3. Intrinsically nonlinear models

Teaching methods and general organization

The course consists of four types of sessions: (a) theoretical: presenting the main content of the course via slides with explanations and examples; (b) exercises: interpreting output of statistical software implementing the data analytical techniques which are object of the theoretical sessions; (c) practice: interacting with the software to obtain results for different analytical techniques; and (d) discussion of scientific articles, related to language and cognitive sciences, to identify their key elements and to critically assess the data analytical steps taken. In terms of the software to learn to use, the University of Barcelona pays a licence for IBM SPSS, whereas R (https://cran.r-project.org/) and jamovi (https://www.jamovi.org/) can be downloaded for free.

Official assessment of learning outcomes

The continuous evaluation will consist of both practical activities that are carried out throughout the course and an exam at the end of the course. The practical activities entail both interpreting output from statistical software (SPSS, R, and jamovi) and interacting with the software (i.e., clicking) to obtain the results. These practical activities allow scoring 4 points out of the 10 points for the course. The final exam entails applying the knowledge constructed to specific situations and it is answered with all materials (slides, books, articles) available, in order to represent a real-world situation in which researchers have access to knowledge, but need to decide how to apply it correctly. The exam allows scoring 6 points out of the 10 points of the course.

Re-evaluation: if students do not sum at least 5 out of the 10 points of the course, they will answer a new exam (similar in characteristics to the final exam answered) that entails a new opportunity to score 10 points.

Examination-based assessment

The single-test evaluation consists only of answering the final exam, which entails applying the knowledge constructed to specific situations and it is answered with all materials (slides, books, articles) available, in order to represent a real-world situation in which researchers have access to knowledge, but need to decide how to apply it correctly. The exam allows scoring all 10 points of the course.

Re-evaluation: if students do not sum at least 5 out of the 10 points of the course, they will answer a new exam (similar in characteristics to the final exam answered) that entails a new opportunity to score 10 points.

References

Ato  y Vallejo (2007). Diseños experimentales en Psicología. Madrid: Pirámide.

Balluerca y Vergara (2002). Diseños de investigación experimental en Psicología. Madrid: Prentice Hall.

Cohen, J. & Cohen, P. (1975). Applied multiple regression/correlation analysis for the behavioral sciences. Hillsdale, NJ: Lawrence Erlbaum.

Chalmers, A.F. (1999). What is this thing called science? Indianapolis: Hackett Pub. Traducción española: ¿Qué es esa cosa llamada ciencia? Madrid: Siglo XXI.

Chaterjee, S., & Hadi, A. S. (2006). Regression analysis by example (4th ed.) London: John Wiley & Sons.

Field, A. (2005). Discovering statistics using SPSS. London: Sage.

Field, A. & Hole, G. (2003). How to design and report experiments. London: Sage.

Fox, J. (2016). Applied regression analysis and generalized linear models (3rd ed.). London, UK: Sage

Keppel., G. (1991). Design and analysis: A researcher’s handbook (3rd ed.). Englewood Cliffs Prentice Hall.  

Kirk, R.E. (1995). Experimental Design. Procedures for the Behavioral Sciences. International Thomson Publishing Company

Maxwell S.E. y Delaney, H.D. (2004). Designing experiments and analyzing data. Lawrence Erlbaum Associates.

Mendenhall, W., & Sincich, T. (2012). A second course in statistics: Regression analysis (7th ed.). Boston, MA: Prentice Hall.

Pedhazur E.J. & Pedhazur-Schmelkin, L. (1991). Measurement, design, and analysis: an integrated approach. Lawrence Erlbaum Associates.

Peña, D. (2002). Regresión y diseño de experimentos. Madrid: Alianza Editorial.

Peró, M., Leiva, D., Guàrdia, J. y Solanas, A. (Eds.) (2012). Estadística aplicada a las ciencias sociales mediante R y R-Commander. Madrid: Garceta. (Cap. 9)

Salafranca, Ll., Sierra, V., Núñez, M. I., Solanas, A. y Leiva, D. (2005). Análisis estadístico mediante aplicaciones informáticas. SPSS, StatGraphic, Minitab y Excel. Barcelona: Edicions Universitat de Barcelona.

Solanas, A., Salafranca, Ll., Fauquet, J. y Núñez, M. I. (2005). Estadística descriptiva en ciencias el comportamiento. Madrid: Thomson.

Tabachnick, B. G., & Fidell, L. S. (2013). Using multivariate statistics (6th Ed.). Boston, MA: Pearson. (Chapter 6).

Wright, D. B., & London, K. (2009). Modern regression techniques using R: A practical guide for students and researchers. London, UK: Sage.