Introduction - Hydrologic Time Series Analysis: Theory and Practice - page 10

sciences include development of mathematical models to generate synthetic
hydrologic data, to forecast hydrologic events, to identify trends and shifts in
hydrologic data, to fill in missing observations, and to extend short hydrologic
records (Salas, 1993). Certainly, time series analysis has become a vital tool
in hydrological sciences and its importance has dramatically enhanced in the
recent past due to ever-increasing interest in the scientific understanding of
climate change.
In epilogue, statistics is just one of the several tools available for application
in hydrological sciences. Like other tools and techniques of hydrology/water
resources engineering, statistical models and methods can serve as valuable
tools in the analysis and solution of several real-world water problems. It
should be noted that the usefulness of any tool or technique, and hence the
reliability of a hydrologic analysis/estimate depends squarely on the proficiency
and knowledge of the hydrologists/water resources engineers. Unfortunately,
the time and energy associated with the development of a model and the
complexity involved in modelling or analysis often so focus the modellers,
especially novice modellers, that they believe that the model is indeed a full
representation of reality/natural systems. However, in reality, no model whether
statistical or mathematical or some combination of the two can describe the
actual and complete hydrology of any natural system (Haan, 2002); it is
always simpler than the prototype/natural system. We should never forget that
a model is a simplified form of reality and that it is simply a tool to assist in
decision making, not a replacement for it! No models or techniques, no matter
how complex they are, can replace the vital role of hydrologists' competency
and their in-depth knowledge of water systems in making efficient decisions
for solving water problems.
References
Adeloye, A.J. and Montaseri, M. (2002). Preliminary streamflow data analyses prior
to water resources planning study. Hydrological Sciences Journal , 47(5): 679-692.
Arrow, K., Bolin, B., Costanza, R., Dasgupta, P., Folke, C., Holling, C., Jansson, B.-
O., Levin, S., Maler, K.-G., Perrings, C. and Pimentel, D. (1995). Economic growth,
carrying capacity and the environment. Science , 268: 520-521.
Bras, R.L. and Rodriguez-Iturbe, I. (1985). Random Functions and Hydrology. Addison-
Wesley, Reading, M.A.
Capodaglio, A.G. and Moisello, U. (1990). Simple stochastic model for annual flows.
Journal of Water Resources Planning and Management, ASCE , 116(2): 220-232.
Chen, H.-L. and Rao, A.R. (2002). Testing hydrologic time series for stationarity.
Journal of Hydrologic Engineering, ASCE , 7(2): 129-136.
Clarke, R.T. (1998). Stochastic Processes for Water Scientists: Development and
Applications. John Wiley and Sons, New York.
Cryer, J.D. (1986). Time Series Analysis. PWS Publishers, Duxbury Press, Boston,
MA.