The group selection of variables that effected science scores of Indonesia’s Pisa using group LASSO

Scientific literacy is a person’s ability to apply knowledge and develop a reflective mindset so that they can participate in overcoming issues and ideas related to science. The quality of Indonesian scientific literacy based on the Program for International Students Assessment (PISA) followed from 2000 to 2018 is still relatively low. In 2018, Indonesia’s PISA science score was still well below the Organization for Economic Cooperation and Development (OECD) average. PISA data has a high data complexity and multicollinearity, so it requires appropriate statistical methods in conducting analysis. Unfortunately, it is still infrequent to conduct research quantitatively. The group LASSO method can use to select groups of variables that affect science literacy in Indonesian PISA while overcoming multicollinearity. The analysis showed that 11 explanatory variables affect Indonesia’s PISA science score with an RMSE value of 25.00 and an R2 value of 0.31. It means that only 31% of the variance of the average science score can be explained by the explanatory variables, while other factors outside the study demonstrate the rest.