MULTILEVEL NON-LINIER REGRESSION FOR REPEATED MEASURMENT DATA AS STUDY OF PEANUT GROWTH

Peanut is one of the most important legume commodities in Indonesia. In its implementation, a lot research has been done related to this plant. However, studies conducted by growth models, it very rarely studied. Therefore, researchers are interested modeling peanuts. One models that can be used multilevel regression model for case repeated measurement data. Multilevel was chosen because considered provide more information than other models. On hand, nonlinear based on tendency initial plot data obtained. The method study peanut growth. This aims build best tested model. Restricted Estimator Maximum Likelihood (REML) parameter estimation have unbiased estimates. lowest Akaike Information Criterion (AIC) generated from predetermined results obtained indicate parabolic with AIC size. addition, found there an Interclass Correlation (ICC) 81.19% which indicated difference variability between levels.