Longitudinal Data Analysis

Code:

PDCD007

Acronym:

MTI

Keywords
Classification	Keyword
OFICIAL	Sports Sciences

Instance: 2013/2014 - SP

Active?	Yes
Course/CS Responsible:	Sport Sciences

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
PDCD	2	Plano em vigor a partir de 2009	1	-	5	45	135

Teaching language

Suitable for English-speaking students

Objectives

1º Have a clear understanding of the relationship among working hypothesis, research design and longitudinal data analysis, namely from Linda Collins (2008) perspective.

2º Have a clear and precise understanding of the relevancy of longitudinal data analysis in the context of Sport Sciences.

3º Understand the significance and value of intra-individual change and inter-individual differences based on the notions of tracking and prediction.

4º Have a thoughtful search for hierarchical data structures and recognize the need for multilevel data analysis with longitudinal data.

5º Have a appropriate knowledge and self-regulating working capacity when dealing with SPSS, LDA, TIMEPATH and HLM software’s; commands and output interpretation are expected to be closely linked to students data analysis problems.

Learning outcomes and competences

The syllabus contents are coherent with curricular unit aims, as they enable students to understand and appraise the relevancy of Longitudinal Data Analysis in their future work in other curricular units as well as in their final dissertation. From a theoretical basis concerning multiple research questions and longitudinal data analysis, students with gain sufficient knowledge in diverse research designs context specific. We also aim to have students with plentiful autonomous knowledge in SPSS, LDA, TIMEPATH and HLM use. Syllabus contents will give students opportunities to present published papers allowing for the critical analysis of their content given the knowledge they have.

Working method

Presencial

Program

1. Historical aspects of longitudinal research and analysis within the Sport Sciences arena.

2. Research designs with examples: purely longitudinal, mixed-longitudinal and panel.

3. Fundamental issues: main hypothesis; sample size; time-age-cohort effects; attrition; data quality control; instrumentation, variables and measurement time effects.

4. Tracking and prediction: concepts; auto-correlations, Cohen´s Kappa, Foulkes & Davies g, Goldstein consistency index; Rao and Carter & Young linear and nonlinear models. Practical examples in SPSS, LDA, and TIMEPATH softwares.

5. Multilevel modeling: main problems and information levels; balanced and non-balanced designs; data reshaping; time metric, linear and nonlinear models; fixed and dynamic predictors; model testing. Practical examples in HLM.

Mandatory literature

Catrien CJH et al (eds); Longitudinal data analysis. Designs, models and methods. , Sage, 1998
Pedhazur EJ, Schmelkin LP; Measurement, design and analysis: an integrated approach, 1991
Singer JD, Willet JB ; Applied longitudinal data analysis. Modeling change and evento occurrence, 2003

Teaching methods and learning activities

Classes have a triple format. Theoretical presentations and discussions of syllabus contents will be firstly addressed. Secondly, practical sessions include the use of SPSS, LDA, TIMEPATH and HLM dealing with problem solving. Thirdly, all students will present a published paper of his/her interest, putting themselves in a “researcher skin”.

Evaluation will be done with two types of task. The first one relates to the presentation of a written paper by groups of two students with read data; the second one is a written exam concerning all syllabus contents. The final mark will be the weighted sum of the two marks, given that the second task weights 60%.

Evaluation Type

Distributed evaluation with final exam

Assessment Components

designation	Weight (%)
Exame	60,00
Trabalho escrito	40,00
Total:	100,00

Calculation formula of final grade

Final mark: (paper work*40+exam*60)/100