SciELO - Scientific Electronic Library Online

 
vol.29 issue119Alternatives to Randomized Control Trials: A Review of Three Quasi-experimental Designs for Causal Inference author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • Have no similar articlesSimilars in SciELO

Share


Actualidades en Psicología

On-line version ISSN 2215-3535Print version ISSN 0258-6444

Abstract

PRIETO-ADANEZ, Gerardo. Analysis of a Writing Test with the MFRM Model. Act.Psi [online]. 2015, vol.29, n.119, pp.3-19. ISSN 2215-3535.  http://dx.doi.org/10.15517/ap.v29i119.19822.

This paper describes how a Rasch model (Many-Facet Rasch Measurement) can be applied to performance assessment focusing on analysis of examinee, raters, tasks and variables. The article provides an introduction to MFRM, a description of analysis procedures, and an illustrative example to examine the effects of various sources of variability on students’ performance on a writing test by means of the FACETS program. Results highlight the usefulness of the MFRM to detect raters that have extreme values on the continuum of severity/leniency as well as providing objective measurement of examinee (scores free of rater severity).

Keywords : Rater-Mediated Assessment; Performance Assessment; Writing Assessment; Rasch Model; Many-Facet Rasch Measurement.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )