Analysis of classic assumption test and multiple linear regression coefficient test for employee structural office recommendation

Autor: Debby Alita, Ade Dwi Putra, Dedi Darwis
Jazyk: English<br />Indonesian
Rok vydání: 2021
Předmět:
Zdroj: IJCCS (Indonesian Journal of Computing and Cybernetics Systems), Vol 15, Iss 3, Pp 295-306 (2021)
Druh dokumentu: article
ISSN: 1978-1520
2460-7258
DOI: 10.22146/ijccs.65586
Popis: The performance appraisal process in Religious High Court Bandar Lampung has not been carried out objectively, but rather a subjectivity element (relationship closeness). Some employees occupy structural positions but do not fulfil competence and promotion principles, so that it has an impact on providing promotion to a position in the judiciary. Multiple Linear Regression method can provide a predictive model for employee recommendations entitled to occupy positions in the agency. The method implementation using SPSS produces an equation Y = 74.177 + 0.035X1 + 0.020X2 - 0.026X3 + 0.045X4 + 0.001X5. This equation is applied to the employee performance values, and it is obtained from 40 employees 26 employees deserve to be given recommendations promotion. Regression performance testing results using 10-cross validation get the correlation coefficient value is 80.66% with MAE value of 2.24% and RMSE 3.88%, which mean has good performance.
Databáze: Directory of Open Access Journals