| Summary: | In this thesis discussed on the detection and correction of data containing the additive
outlier (AO) on the model ARIMA (p, d, q). The process of detection and correction
of data using an iterative procedure popularized by Box, Jenkins, and Reinsel (1994).
By using this method we obtained an ARIMA models were fit to the data containing
AO, this model is added to the original model of ARIMA coefficients obtained from
the iteration process using regression methods. In the simulation data is obtained that
the data contained AO initial models are ARIMA (2,0,0)
1 2 0,0600 0,209 0, 417 t t t Z Z Z ï� ï� ï�½ ï�« ï�« with MSE = 36,780, after the detection and
correction of data obtained by the iteration of the model ARIMA (2,0,0) with the
coefficients obtained from the regression
ï�¨ ï�© ï�¨ ï�© ï�¨ ï�© 1 2 1 2 3 0,106 0,204 0,401 329 115 35,9 t t t Z Z Z X t X t X t ï� ï� ï�½ ï�« ï�« ï� ï�« ï�« and MSE =
19,365. This shows that there is an improvement of forecasting error rate data.
|
|---|