TY - GEN
T1 - Spatial modeling on the upperstream of the Citarum watershed
T2 - 2nd International Conference on Applied Statistics: Statistics and Its Applications, ICAS 2016
AU - Ningrum, Windy Setia
AU - Widyaningsih, Yekti
AU - Latif, Tito
N1 - Publisher Copyright:
© 2017 Author(s).
PY - 2017/3/30
Y1 - 2017/3/30
N2 - The Citarum watershed is the longest and the largest watershed in West Java, Indonesia, located at 106°51'36''-107°51' E and 7°19'-6°24'S across 10 districts, and serves as the water supply for over 15 million people. In this area, the water criticality index is concerned to reach the balance between water supply and water demand, so that in the dry season, the watershed is still able to meet the water needs of the society along the Citarum river. The objective of this research is to evaluate the water criticality index of Citarum watershed area using spatial model to overcome the spatial dependencies in the data. The result of Lagrange multiplier diagnostics for spatial dependence results are LM-err = 34.6 (p-value = 4.1e-09) and LM-lag = 8.05 (p-value = 0.005), then modeling using Spatial Lag Model (SLM) and Spatial Error Model (SEM) were conducted. The likelihood ratio test show that both of SLM dan SEM model is better than OLS model in modeling water criticality index in Citarum watershed. The AIC value of SLM and SEM model are 78.9 and 51.4, then the SEM model is better than SLM model in predicting water criticality index in Citarum watershed.
AB - The Citarum watershed is the longest and the largest watershed in West Java, Indonesia, located at 106°51'36''-107°51' E and 7°19'-6°24'S across 10 districts, and serves as the water supply for over 15 million people. In this area, the water criticality index is concerned to reach the balance between water supply and water demand, so that in the dry season, the watershed is still able to meet the water needs of the society along the Citarum river. The objective of this research is to evaluate the water criticality index of Citarum watershed area using spatial model to overcome the spatial dependencies in the data. The result of Lagrange multiplier diagnostics for spatial dependence results are LM-err = 34.6 (p-value = 4.1e-09) and LM-lag = 8.05 (p-value = 0.005), then modeling using Spatial Lag Model (SLM) and Spatial Error Model (SEM) were conducted. The likelihood ratio test show that both of SLM dan SEM model is better than OLS model in modeling water criticality index in Citarum watershed. The AIC value of SLM and SEM model are 78.9 and 51.4, then the SEM model is better than SLM model in predicting water criticality index in Citarum watershed.
UR - http://www.scopus.com/inward/record.url?scp=85017576361&partnerID=8YFLogxK
U2 - 10.1063/1.4979433
DO - 10.1063/1.4979433
M3 - Conference contribution
AN - SCOPUS:85017576361
T3 - AIP Conference Proceedings
BT - Statistics and Its Applications
A2 - Andriyana, Yudhie
A2 - Suparman, Yusep
A2 - Suprijadi, Jadi
PB - American Institute of Physics Inc.
Y2 - 27 September 2016 through 28 September 2016
ER -