Citation

Ghosh S. Journal of Comparative Asian Development 2018; 17(1): 118-158.

Copyright

(Copyright © 2018)

DOI

unavailable

PMID

unavailable

Abstract

PURPOSE-Suicide mortality cases is a cause for concern in Japan. During 2013 the suicide rate in Japan is 21.4 deaths per 100 000 people, greater than many high income countries. WHO reports to the urgency to recognize suicide prevention as an immediate public health agenda. (WHO, Suicide Report, 2014). The purpose of this research is to investigate the causality of such high suicide in Japan and also to forecast the future situation of suicide. Materials and method-This paper applies the Autoregressive Integrated Moving Average (ARIMA) time series model to study the trends and patterns of suicide mortality in Japan as well as makes a six-year out of sample forecast. Second the study has developed a causality analysis of suicide based on multivariate Vector Error Correction model. The annual (1960-2013) data sets are obtained from The Organization for Economic Co-operation and Development and World Development Indicators of the World Bank.

FINDINGS-The study chooses ARIMA (0, 2, and 1) as the best fitting model, based on the principle of parsimony. The forecast six periods beyond the sample of observations (2014-2019) shows that suicide would be on a declining trend in Japan. The augmented Dickey Fuller test was utilized to test the stationarity across the variables. The variables are found to be integrated of order one I (1). The same integration order leads to a Johansen maximum likelihood procedure, where the existence of a long run equilibrium relation is established across gross domestic product, unemployment, divorce rates, urbanization, alcohol consumption and marriages. The estimated cointegrating residual is then used as an error correction term in the VECM where the short run dynamics are revealed along with the statistical significance. © 2018, City University of Hong Kong. All rights reserved.

Language: en

Keywords

Suicide mortality; Time series; ARIMA model; Cointegration analysis; F63; Japan Subject classification codes: C22; O53