Application of Principal Component  Regression with Dummy Variable in  Statistical Downscaling to Forecast Rainfall

Sitti Sahriman; Anik Djuraidah; Aji Hamim Wigena

doi:10.4236/ojs.2014.49063

Home > Journals > Physics & Mathematics > OJS

Open Journal of Statistics > Vol.4 No.9, October 2014

Application of Principal Component Regression with Dummy Variable in Statistical Downscaling to Forecast Rainfall ()

Sitti Sahriman, Anik Djuraidah, Aji Hamim Wigena

Department of Statistics, Bogor Agricultural University, Bogor, Indonesia.

DOI: 10.4236/ojs.2014.49063 PDF HTML XML 3,192 Downloads 3,959 Views Citations

Abstract

Statistical downscaling (SD) analyzes relationship between local-scale response and global-scale predictors. The SD model can be used to forecast rainfall (local-scale) using global-scale precipitation from global circulation model output (GCM). The objectives of this research were to determine the time lag of GCM data and build SD model using PCR method with time lag of the GCM precipitation data. The observations of rainfall data in Indramayu were taken from 1979 to 2007 showing similar patterns with GCM data on 1^st grid to 64^th grid after time shift (time lag). The time lag was determined using the cross-correlation function. However, GCM data of 64 grids showed multicollinearity problem. This problem was solved by principal component regression (PCR), but the PCR model resulted heterogeneous errors. PCR model was modified to overcome the errors with adding dummy variables to the model. Dummy variables were determined based on partial least squares regression (PLSR). The PCR model with dummy variables improved the rainfall prediction. The SD model with lag-GCM predictors was also better than SD model without lag-GCM.

Keywords

Cross Correlation Function, Global Circulation Model, Partial Least Square Regression, Principal Component Regression, Statistical Downscaling

Share and Cite:

Sahriman, S. , Djuraidah, A. and Wigena, A. (2014) Application of Principal Component Regression with Dummy Variable in Statistical Downscaling to Forecast Rainfall. Open Journal of Statistics, 4, 678-686. doi: 10.4236/ojs.2014.49063.

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Notodiputro, K.A., Wigena, A.H. and Fitriadi (2005) Principal Component Regression Approach and ARIMA to Statistical Downscaling. Journal of Science and Technology, 11, 137-142.
[2]	Fernandez, E. (2005) On the Influence of Predictors Area in Statistical Downscaling of Daily Parameters. Norwegia Meteorological Institute, 9, 1-21.
[3]	Busuioc, A., Chen, D. and Hellstrom, C. (2001) Performance of Statistical Downscaling Models in GCM Validation and Regional Climate Change Estimates: Application for Swedish Precipitation. International Journal of Climatology, 21, 557-578. http://dx.doi.org/10.1002/joc.624
[4]	Wigena, A.H. (2011) Multirespon Partial Least Squares Regression Method for Statistical Downscaling. Statistics and Computation Forums, 16, 12-15.
[5]	Warawati, A.D. (2013) Sukadana Station Rainfall Forecasting Using Statistical Downscaling Technique Based on TRMM Satellite Data. Thesis, Bogor Agricultural University (in Indonesian), Indonesia.
[6]	Wigena, A.H. (2006) Modeling of Statistical Downscaling Using Projection Pursuit Regression for Forecasting Monthly Rainfall. Doctoral Dissertation, Bogor Agricultural University (in Indonesian), Indonesia.
[7]	Jollife, I.T. (2002) Principal Component Analysis. Springer-Verlag, New York.
[8]	Wold, S., Sjostrom, M. and Eriksson, L. (2001) PLS-Regression: A Basic Tool of Chemometrics. Chemometrics and Intelligent Laboratory Systems, 58, 109-130. http://dx.doi.org/10.1016/S0169-7439(01)00155-1