Un estudio de potencia y tasa de error tipo I del estadístico de razón de verosimilitud en la TRI
PDF (Español (España))

How to Cite

López Pina, J. A., & Hidalgo Montesinos, M. D. (2001). Un estudio de potencia y tasa de error tipo I del estadístico de razón de verosimilitud en la TRI. Psicothema, 13(Número 2), 330–334. Retrieved from https://reunido.uniovi.es/index.php/PST/article/view/7838

Abstract

A study of power and type I error rate to the likelihood ratio statistics in IRT. In this report we studied the power (and the type I error rate) of the likelihood ratio statistic used in BILOG (v. 3.04) to prove de fit of the model to the items. For this, we used a test size fixed (75 items) and four sample sizes (100, 250, 500 and 1000). Further, we used three ability distributions: one centered N(0,1) and another two noncentered: N(-1,1) and N(1,1). We also manipulated the mean discrimination in 25 of 75 items in six conditions (.3, .6, 1.0, 1.2, 1.5 and 1.8). The results showed that the power of the likelihood ratio statistic is low when the sample size was 100, although the discrimination parameter was .3 or 1.8. The power increased with the sample size, although this statistic cannot detect items that not follow the 1-p model, independently if the discrimination parameter was 1.0, 1.2 or 1.5. Finally, the type I error rate adjusted to the nominal levels, except when the sample size was high.
PDF (Español (España))