Skip to Main Content
 

Global Search Box

 
 
 
 

ETD Abstract Container

Abstract Header

Applying Longitudinal IRT Models to Small Samples for Scale Evaluation

Keum, EunHee

Abstract Details

2016, Doctor of Philosophy, Ohio State University, Psychology.
Item response theory (IRT) modeling can provide detailed information about the performance of questionnaires/scales. Despite the benefit of IRT models, they often require larger sample sizes for reliable estimation compared with simpler models. Small sample sizes can even potentially impact the calibration of simple unidimensional IRT models. In psychological assessment, however, the same scale is often administered to a small number of respondents on multiple occasions. To the extent the repeated measures from the same individual are not perfectly correlated, we can gain extra information regarding both respondents and the scale of interest. To obtain useful psychometric information about a scale, we have to be able to recover the parameters of IRT models fairly well and demonstrate that other ancillary procedures also function well. Therefore, we explored under what conditions proposed longitudinal IRT models can be reliably estimated and their parameters can be reasonably recovered through simulations. We further discussed how these models can be applied in psychometric assessment of a scale when only a small sample is available.
Michael Edwards (Advisor)
219 p.

Recommended Citations

Citations

  • Keum, E. (2016). Applying Longitudinal IRT Models to Small Samples for Scale Evaluation [Doctoral dissertation, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1460996452

    APA Style (7th edition)

  • Keum, EunHee. Applying Longitudinal IRT Models to Small Samples for Scale Evaluation. 2016. Ohio State University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1460996452.

    MLA Style (8th edition)

  • Keum, EunHee. "Applying Longitudinal IRT Models to Small Samples for Scale Evaluation." Doctoral dissertation, Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1460996452

    Chicago Manual of Style (17th edition)