Penerapan Uji Asumsi Klasik Untuk Mendeteksi Kesalahan Pada Data Sebagai Upaya Menghindari Pelanggaran Pada Asumsi Klasik

Nurcahya, Wilma Arum
Arisanti, Nadia Prasista
Hanandhika, Audrey Nabilla

Madani: Multidisciplinary Scientific Journal
Vol 1, No 12 (2024): Madani, Vol. 1 No. 12 2024

In this research, the focus of discussion is on solving problems from 4 tests, including the normality test, multicollinearity test, heteroscedasticity test, and autocorrelation test. The aim is to find out the efforts that researchers can make in overcoming problems in testing classical assumptions so that research data is valid and can be accounted for. This research was carried out with a literature review adopting a comparative descriptive approach which was carried out to examine problems theoretically in comparing modern econometrics with various methods of violating classical assumption tests, namely the normality test, multicollinearity test, heteroscedasticity test and autocorrelation test. The normality test is a test to find out whether research data has a normal distribution or not. The purpose of the multicollinearity test is to detect whether there is a relationship between the independent variables. The heteroscedasticity test is to test whether the error variance in each time period is different. And the last one is the autocorrelation test which is used to conceptualize the correlation between variables and time periods.