Degree | Type | Year | Semester |
---|---|---|---|
4316222 Research in Clinical and Health Psychology | OT | 0 | 2 |
Knowledge of Module 1, especially those related to research methodology and research designs, for their direct link with statistical modeling, those related to descriptive and bivariate analysis, and about functionning of the software Stata.
Provide the necessary skills (theoretical and instrumental) so that the student is able to:
- Analyze the psychometric properties of a questionnaire relative to internal structure and reliability.
- Analyze the data of a research using linear or logistic regression models, both in order to predict the response and to study the influence of an exposure on the response.
- Incorporate the phenomena of interaction and confusion into the statistical modeling process.
- Perform the diagnosis of the conditions of application of linear and logistic regression models.
- Distinguish a moderator variable from a mediator variable, and propose together with the estimation of models of structural equations for the analysis of mediation models.
- Interpret the results of the regression models and SEM, being able to select those most suitable to be included in the research report.
Block A
- Internal structure: principal components analysis (A1) and confirmatory factor analysis (A2)
- Reliability (A3)
Block B
- Linear regression: predictive models and to evaluate effects
- Statistical modeling in the presence of interaction and confusion
- Diagnosis of the linear regression model
Block C
- Logistic regression: predictive models and to evaluate effects
- Logistic regression and diagnostic tests
- Diagnosis of the logistic regression model
Block D
- Moderation vs mediation
- Structural equation models for the analysis of mediating variables
Directed:
- Master classes. Using a material published by the teachers, explanation is made based on examples and matrices of real research data in psychology. Each master class ends with a space dedicated to the debate with students, who are expected to provide feedback on the understanding, usefulness and applicability of the presented concepts.
- Practical sessions with Stata. The results presented in the master class are replicated using Stata. New exercises with a similar structure are also added.
N.B. The proposed teaching and assessment methodologies may experience some modifications as a result of the restrictions on face-to-face learning imposed by the health authorities. The teaching staff will use the Moodle classroom or the usual communication channel to specify whether the different directed and assessment activities are to be carried out on site or online, as instructed by the Faculty.
Title | Hours | ECTS | Learning Outcomes |
---|---|---|---|
Type: Directed | |||
Master class + practical sessions with Stata | 30 | 1.2 | 1, 16, 15, 9, 2, 14, 5, 8, 7, 13, 3, 4, 10, 11, 12, 17, 6 |
Type: Autonomous | |||
Elaboration of reports | 16 | 0.64 | 1, 16, 15, 9, 2, 14, 5, 8, 7, 13, 3, 4, 10, 11, 12, 17, 6 |
Personal work | 100 | 4 | 1, 16, 15, 9, 2, 14, 5, 8, 7, 13, 3, 4, 10, 11, 12, 17, 6 |
The continuous evaluation process will integrate 4 evaluative elements:
Evidence 1 (40%): Online delivery of the results of individual self-analysis of a practical problem related to internal structure and reliability
Evidence 2 (40%): Computer examination on linear regression models.
Evidence 3 (25%): Computer examination of logistic regression models.
Evidence 4 (10%): Attendance and active participation in class.
The students who have obtained a final qualification between 3.5 and 5 points and who have made evidence of evaluation with a minimum weight of 2/3 of the total, will be able to take the second-chance test, which will allow them to re-evaluate evidences 1, 2 and 3 that were not succesfully passed. The maximum score that can be obtained on each retest evidence will be 6 points.
The final grade of the continuous evaluation will be obtained as the weighted average of the 4 evaluation evidences. The module will be passed with grades equal to or greater than 5 points (on a scale of 0 to 10 points), with a minimum of 3 points in Ev2 and Ev3.
Students who have obtained a final grade between 3.5 and less than 5 points and who have carried out evaluation evidence weighing at least 2/3 of the total grade, will be able to take resit (week 12), to carry out again evidences 2 and/or 3 that have not been succesfully passed. The maximum grade that can be obtained in each evidence recovered will be 6 points. The grade obtained in the evidence/s recovered will replace the respective original grade and the final grade will be recalculated.
A student who has presented evidence that exceeds 40% of the total may not be qualified as "Not Evaluable".
No unique final synthesis test for students who enroll for the second time or more is anticipated.
The document with the evaluation guidelines of the Faculty can be found at: https://www.uab.cat/web/estudiar/graus/graus/avaluacions-1345722525858.html
Title | Weighting | Hours | ECTS | Learning Outcomes |
---|---|---|---|---|
Ev1 Practical report on internal structure and reliability (week 2-4) | 25 | 0 | 0 | 1, 16, 3, 10, 12, 17, 6 |
Ev2 Test about linear regression (week 9) | 32,5 | 2 | 0.08 | 1, 16, 15, 9, 2, 14, 5, 8, 7, 13, 3, 4, 10, 11, 12, 17, 6 |
Ev3 Test about logistic regression (week 9) | 32,5 | 2 | 0.08 | 1, 16, 9, 2, 14, 5, 8, 7, 3, 4, 11, 12, 17 |
Ev4 Report on mediation (week 11) | 10 | 0 | 0 | 1, 16, 15, 9, 2, 14, 5, 8, 7, 13, 3, 4, 10, 11, 12, 17, 6 |
Abad, Francisco J.; Olea, Julio; Ponsoda, Vicente; García, Carmen. (2011). Medición en ciencias sociales y de la salud. Madrid: Síntesis.
American Educational Research Association, American Psychological Association, National Council on Measurement in Education (2014). The standards for educational and psychological testing. Washington: Autor.
Ato, Manuel; Vallejo, Guillermo. (2011). Los efectos de terceras variables en la investigación psicológica. Anales de Psicología, 27, 550-561.
Kleinbaum, David G.; Kupper, Lawrence L.; Nizam, Azhar; Rosenberg, Eli S. (2014). Applied regression analysis and other multivariable methods. (5ª ed.). Boston (MA): Cengage Learning, Inc
Kleinbaum, David G.; Klein, Mitchel. (2010). Logistic regression. A Self-learning text. 3rd ed. New York: Springer-Verlag. [https://www.springer.com/gp/book/9781441917416][https://www.springer.com/gp/book/9781441917416]
Shmueli, Galit. (2010). To Explain or to predict? Statistical Science, 25, 289-310.