Item-Total Correlation
In order to determine whether any of the statements on the survey were problematic, a correlation between each statement and the total score was computed. This was done for the survey as a whole and for each of the subscales. The corrected item-total correlations ranged from 0.47 to 0.83 for the entire scale, 0.61 to 0.85 for the confidence subscale, 0.65 to 0.85 for the usefulness subscale, and 0.51 to 0.83 for the enjoyment subscale. Since the elimination of none of the statements from the subscales would increase the value of the Cronbach's alpha by much for that subscale or the entire survey, no statements were eliminated from the survey. Robinson, Shaver, and Wrightsman (1991) suggested that all corrected item-total correlations less than 0.30 should be deleted; however, upon inspection all were well above this value.
Item-Total CorrelationIn order to determine whether any of the statements on the survey were problematic, a correlation between each statement and the total score was computed. This was done for the survey as a whole and for each of the subscales. The corrected item-total correlations ranged from 0.47 to 0.83 for the entire scale, 0.61 to 0.85 for the confidence subscale, 0.65 to 0.85 for the usefulness subscale, and 0.51 to 0.83 for the enjoyment subscale. Since the elimination of none of the statements from the subscales would increase the value of the Cronbach's alpha by much for that subscale or the entire survey, no statements were eliminated from the survey. Robinson, Shaver, and Wrightsman (1991) suggested that all corrected item-total correlations less than 0.30 should be deleted; however, upon inspection all were well above this value.
การแปล กรุณารอสักครู่..