424300 :Psychological and Sociological Measurement in Data Science

Algemeen

Voertaal Engels
Werkvorm: 14 Lectures (2 hours) and 6 Practicals (2 hours) (Geen informatie over collegetijden bekend)
Tentamenvorm: Written Exam (Tentamenrooster)
Niveau:Master
Studielast:6 ECTS credits
Inschrijving:Inschrijven via COMAP.
Blackboard informatieniet beschikbaar in Blackboard

Docent(en)


prof. dr. J.K. Vermunt (Coordinator)

dr. W.H.M. Emons (Lecturer)

dr. V.D. Schmittmann (Lecturer)


Doel van de cursus (alleen in het Engels beschikbaar)

This course has the following objectives:

  • Students can distinguish between discrete and continuous latent variable models, for different item-response types (binary, ordinal, continuous).
  • Students can describe and explain the concept of local independence in the context of latent variable modeling.
  • Students can describe and explain the basic assumptions of item response theory models, both statistically and substantively.
  • Students can describe and explain the role of latent variable measurement models for designing, validating, and revising scales and questionnaires.
  • Students can apply dichotomous and polytomous item response theory models to questionnaire data and judge the adequacy of the instrument for practical person measurement.
  • Students are able to apply the simple latent class model; that is, deal with model selection, model interpretation, and classification.
  • Students understand the most relevant extensions of the simple latent class model, such as local dependence models, models with multiple latent variables, and models with covariates.
  • Students can use the classifications obtained from a latent class model in subsequent analysis.
  • Students can apply latent variable models to explore dimensionality, to examine measurement invariance and to detect item bias.

  • Inhoud van de cursus (alleen in het Engels beschikbaar)

    This course provides an introduction to statistical models for latent variable measurement in the psychological and social sciences. The models to be discussed include latent class models, linear factor models, and latent trait models (item-response theory models). These models are routinely applied in various fields of the social sciences. We will focus on the conceptual foundations of the models, discuss the basic model and its generalizations or special cases, and practice different applications to real data sets. The relevant software in this course includes SPSS,LatentGOLD, and IRTPRO (student version).


    Bijzonderheden (alleen in het Engels beschikbaar)

    Lectures and practicals:

    The course consists of 14 two-hour lectures and 6 two-hour computer practicals. In the interactive lecture, the lecturer explains the subject matter, asks questions, and invites students to discuss the subject matter. In the practicals, the students apply the acquired methods and techniques to real-data sets using LatentGOLD or other dedicated software. Attendance at the practicals is required.

     

    Exam Grading:

    Every module of the course constitutes an equal part in the exam. As part of the exam analytic skills (doing analyses) might be required. The final grading of the course is the mean score of the three parts of the exam.

    A student passes the course if the final grade >= 5.5.

    The resit covers all modules of the course.


    Verplichte literatuur

    1. Collection of articles; to be announced on blackboard.


    Mogelijk interessant voor

    • Data Science: Business and Governance ( 2015, 2016 )

(24-jul-2017)