Evaluación de las competencias investigativas en los estudiantes de maestría de la Universidad Nacional Experimental del Táchira mediante el uso de modelos de regresión multinivel Evaluación de las competencias investigativas en los estudiantes de maestría de la Universidad Nacional Experimental del Táchira mediante el uso de modelos de regresión multinivel

Abstract

The  objective  of  this  research  was  to  apply  multilevel analysis  for  the  adjustment  of  a  multilevel  model  aimed  at  evaluating the competencies of the masters students of the National Experimental. University  of  Táchira,  Venezuela.  Theoretically,  the  model  analyzes the  variability  among  the  students  within  each  master’s  degree  (level 1)  and  among  the  master’s  degrees  (level  2),  whose  initial  hypothesis establishes that the students of the same master’s degree possess similar investigative  competencies  with  respect  to  those  who  belong  to  other master’s  degrees.  It  was  supported  by  an  explanatory,  correlational and  quasi-experimental  study.  The  sample  consisted  of  225  students, applying  a  structured  instrument  in  two  parts:  one  of  12  items  on  a nominal scale to measure personal and academic variables, and another on a 40-item Likert scale to evaluate research competencies. It was found that there are significant differences between the masters with respect to  the  research  skills,  because  the  intraclass  correlation  coefficient (ρ=0.142)  of  the  null  model prevents  compliance  with  the  hypothesis  of  independence:  Students  of  the  same  master’s  degree  have  similar  investigative skills in comparison to those who are of another master’s degree, multilevel analysis is appropriate. Then, variables predictors of the levels were incorporated: masters, students and both levels, obtaining the  following  multilevel  model: COINij=1,3376*CMLC+2,5882*CML-1,0031*ST1*CMLC+ uoj+eij