MENY
This is the study programme for 2019/2020. It is subject to change.


The aim of this course is to provide students with a good understanding of basic analytical tools with relevance for their Phd-work. Factor- and regression analysis are the main approaches covered, for the most part using the statistical program SPSS. When discussing mediation and moderation, the students will be introduced to Hayes' Process on top of SPSS. In addition, we will go into Confirmatory Factor analysis (CFA) and Structural Equation Modelling (SEM) via the Lisrel program, also with eye on the Mplus package. The course will also take up elements of logistic regression and multi-level analysis. Main focus will be on applications of the various techniques introduced.

Learning outcome

Knowledge
After completing the course the students should:
  • have an thorough knowledge of advanced causal modelling in the social sciences
  • be able to identify and evaluate alternative statistical uses in current quantitative research
  • be able to develop new knowledge by applying modern factor and regression approaches, including Confirmatory Factor analysis (CFA) and Structural Equation modelling (SEM)
  • understand how the frequentists methodology differ from Bayesian approaches
  • have good knowledge of how imputation and boot strapping strategies could be applied to improve data quality and statistical analysis

Competence
After completing the course the students should:
  • be able to develop new research questions and specify suitable methodological frameworks for carrying out a realistic research plan
  • be able to apply modern multivariate analysis in research at an international level
  • be able assess appropriate quantitative statistical methods in a real research context
  • be able to refine and revise causal models in the present research literature, in order to challenge existing knowledge, and to push the research frontier further
  • be able to handle diverse and supplementary quantitative methods in large research projects

General Skills
After the course students should be able to
  • specify appropriate causal models for her own research project
  • clarify main statistical assumptions of relevant analytical approaches
  • identify potential ethical challenges linked to statistical testing, the use of p-/t-values and publication bias, etc.
  • analyze complex data in a skillful manner, applying factor/regression/CFA/SEM techniques
  • interpret results from advanced data analysis, and critically consider alternative methods
  • explore mechanisms of mediation and moderation, using regression approaches (such as Hayes’ Process) and Structural Equation modelling (modelling indirect effects, sub-group comparisons)
  • develop and test competing causal models within the Lisrel or Mplus framework
  • use imputation and boot strapping methods to strengthen the trustworthiness of empirical/statistical results

Contents

The course takes at a starting point research questions and studies from the international literature, and apply appropriate methodological approaches when analyzing these. Such queries together with relevant data provide the basis for presenting statistical analyzes and interpretations.

Required prerequisite knowledge

Participants must be enrolled in a PhD programme.

Recommended previous knowledge

It is mandatory that the students have basic knowledge of quantitative methods at Master Level.

Exam

Weight Duration Marks Aid
Term paper (8-10 pages)1/1 Pass - Fail
Full participation during the whole course is required. (One week on intensive lectures and PC-lab exercises, Monday through Friday, 9 -16). In addition, there is a term paper requirement ( 8-10 pages, demonstrating knowledge and application skills).

Course teacher(s)

Course coordinator
Knud Knudsen

Method of work

The course will consist of one week of intensive lectures and PC-lab exercises, Monday through Friday, from 0915 to 1600. Students are expected to prepare for and review lecture materials on their own.
The expected work loads of this course are:
Lectures: 15 hours
Computer Lab sessions: 20 hours
Preparations and reviews of materials: 65 hours
Paper requirement: 50 hours
TOTAL: 150 hours
Coursework requirements
  • Prepare a 1 p. (ca.) note on methodological questions departing from your PhD project, which outlines the planned topic for the course paper. This note must be submitted one week in advance of the course.
  • An individual presentation at the end of the course week. The presentation should be a reflection on the 1 p. note submitted in advance. Students may then highlight elaborations and possible alterations of as result of discussions over the week.
  • Generally active participation in discussions in general.

Open to

Single Course Admission to PhD-Courses
PhD programme in Social Sciences

Course assessment

Evalutation according to UiS rules and regulations.

Literature

Basic Factor Analysis
Pett, Marjorie, A., Nancy R. Lackey, og John. J. Sullivan, Making Sense of Factor Analysis. Thousand Oaks, CA: Sage 2003. Please read chapters 1 - 7 (225 pages).
Basic Regression, plus Dummy-variable, Interaction effects, Logistic Regression
From Sages "Series" (a-c): a) Michael S Lewis-Beck, Applied Regression, An Introduction. Second edition. Volume:22. 2016. (This is mainly a reprint of previous versions)
b) Melissa A Hardy, Regression with Dummy Variables Volume: 93 1993.
c) James Jaccard, Robert Turrisi and Choi K Wan, Interaction Effects in Multiple Regression Volume:72 1990.
d) Scott Menard , Applied Logistic Regression Analysis Volume:106 1995
CFA/SEM/Lisrel
Byrne, Barbara M., Structural Equation Modeling with Lisrel, Prelis and Simplis. Basic Concepts, Applications and Programming London: Lawrence Erlbaum Associates 1998. Should be available in paper back.
Please read chapters 1,2,4,7,8, (excluding SIMPLIS and PRELIS parts) approximately 150 pages.
Article:
Knudsen, Knud (2009) "Striking a different balance; Work-family conflict for female and male managers in a Scandinavian context". Gender in Management 24 4: 252 - 269. A copy will be made available at the start of the course.
Participants who may want a supplementary text in Norwegian, covering the main regression topics, could also read: Ole-Jørgen Skog, Å forklare sosiale fenomener. Ad Notam 2004 .
Recommended reading for more advanced Causal analysis: Pearl, J. (2009). Causality. Cambridge university press.


This is the study programme for 2019/2020. It is subject to change.

Sist oppdatert: 10.12.2019