INFLUENCE OF SELF-EFFICACY, ACADEMIC SELF-CONCEPT AND (101)

.pdf
School
Walden University **We aren't endorsed by this school
Course
PSYC RESEARCH P
Subject
Statistics
Date
Sep 29, 2023
Pages
1
Uploaded by PresidentKouprey5615 on coursehero.com
85 peer pressure) on dependent variable (career decision making) as stated in hypotheses one to three. Multinomial logistic Regressionwas used because dependent variable had more than two nominal categories. Like binary logistic regression, multinomial logistic regression uses maximum likelihood estimation to evaluate the probability of categorical membership. Unlike other multivariate statistics, Tabanick, Fidell & Osterlind (2001) argued that multinomial logistic regression technique has a number of advantages as: i) it is more robust to violations of assumptions of multivariate normality and equal variance matrices across groups, ii) most importantly, MLR does not assume a linear relationship between the dependent and independent variables, iii) independent variables need not be interval, iv) MLR does not require that the independents be unbounded and lastly v) normally distributed error terms are not assumed (Tabanick, et al., 2001 ; Chan, 2005). With these advantages, MLR was found suitable to be used particularly in the field of educational psychology especially for likelihood estimation to evaluate the probability of categorical membership in the present study. Data analysis was carried out with aid of both descriptive and inferential analysis (Garson, 2010). The MLR model assigns a reference category to which all other levels of the dependent variable are compared as shown in appendix III, part E.The relative risk ratio (rrr) of the alternatives were estimated simultaneously by comparing the choice of disagree, undecided, agree and strongly agree with strongly disagree which was the reference category. If the rrr is less than 1, then the relative risk of choosing the comparison category of student career decision making compared to strongly disagree is reduced controlling for other variables in the model. If relative risk ratio is greater than 1, then the relative risk of choosing the comparison category of student career decision making compared tostrongly disagree is increased controlling for other variables
Page1of 1
Uploaded by PresidentKouprey5615 on coursehero.com