© Associated Asia Research Foundation (AARF)
A Monthly Double-Blind Peer Reviewed Refereed Open Access International e-Journal - Included in the International Serial Directories.
Page | 40
APPLICATION OF BAYESIAN ESTIMATION IN ANALYZING
CONFIRMATORY FACTOR ANALYSIS MODEL OF PHYSICS
CLASSROOM PSYCHO-SOCIAL COVARIATES
Fidelis O. Nnadi (Ph.D) and Rose C Anamezie Ph.D)
Department of Science & Computer Education, Enugu State University of Science and
Technology, Enugu-Nigeria.
ABSTRACT
The problem of poor achievement of students in Physics warranted the study. Researchers
have linked poor Physics achievement to poor quality of instrument and Physics classroom
psycho-social covariates (PCSC). The gap which this study filled was to use Bayesian
estimation to reaffirm the result of exploratory factor analysis of PCSC and achievement
through confirmatory factor analysis. The study adopted an instrumentation design.. The
sample for the study comprised 420 SS3 Physics students sampled using random sampling
from ten schools in Agbani Education zone. The instrument used to collect data included
Physics classroom psycho-social covariates (PCSC) and students’ results. The alpha values
of PCSC ranged between .67 to .78 for its clusters and .74 for the overall. The data collected
were analyzed using regression weights, correlation and deviance information criterion
values. The results indicated that the indicators of each latent construct positively loaded on
them. There were moderately positive correlation between the underlying constructs. The
sub-models were invariant.
International Research Journal of Human Resources and Social Sciences
ISSN(O): (2349-4085) ISSN(P): (2394-4218)
Impact Factor- 5.414, Volume 5, Issue 08, August 2018
Website- www.aarf.asia , Email : editor@aarf.asia , editoraarf@gmail.com