Modeling Treshold Liner in Transfer Function to Overcome Non Normality of the Errors

9th Annual Basic Science International Conference 2019

自然科学（总论）

Kusdarwati, Heni^1 ; Handoyo, Samingun^1

Department of Statistics, Faculty of Mathematics and Natural Science, Brawijaya University, Malang, Indonesia^1

关键词: Moving averages;    Non-normality;    P-values;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/546/5/052039/pdf
DOI  :  10.1088/1757-899X/546/5/052039

学科分类：自然科学（综合）

来源: IOP

【 摘 要 】

The purposes of the paper are to apply a model of Double Seasonal AutoregressiveIntegrated Moving Average with transfer function (DSARIMAX) on the number of selecta tourist visitors in Batu city, which contain multiple seasonal elements and to add a threshold element to the DSARMAX model. The DSARIMAX model produced is a feasible model but it has a low p-value because the assumption of normality of the errors is not fulfilled. Addition of the threshold to the DSARIMAX model makes the model feasible with high p-value and satisfies the normality assumption of the errors.