Trend Evaluation with Ordinary Least Squares Regression

1 Trend Evaluation with Ordinary Least Squares Regression 

Regression techniques are most frequently used for detection of trends in a series. For evaluating nonparametric trend tests see BERRYMAN et al. [1988]. This example series concerning the nitrate concentrations in the storage reservoir will be tested for any trends over the Ml time of observation. 

Values on the x-axis in time series analysis are mostly data like day, month, or year. In order to test a trend, one needs a linearly increasing x-axis for that particular section of the series which has to be tested for a trend. So one has to create a series with running numbers as the independent variable. 

The second task is to deseasonalize the series. Differencing by 12 can be used to achieve this. To evaluate a trend, regression analysis as basically described in Section 

4 was performed for the time interval between August 1989 and the end of the series. The model equation was  

---