Page 308 - DECO504_STATISTICAL_METHODS_IN_ECONOMICS_ENGLISH

Unit 23 : Time Series Methods—Graphic, Method of Semi-averages

actuality. it is very time consuming to construct a freehand trend curve if a careful and Notes
conscientious job is to be done. For these reasons, the freehand method is not recommended for
fitting a trend line.
• This method of estimating trend is the simplest of all the methods of measuring trend. It involves
no calculation at all since it is purely non-mathematical.
• This method is more flexible than rigid mathematical function, hence fits the curve more closely
to the data i.e this method can be used even in cases where the size of the series is lengthy.
• This method lacks accuracy. Therefore, it is not suitable where a high degree of accuracy is
desired. This method gives us an approximate picture of the tendency in the long run. This
method should therefore be used only by experienced persons.
• This method is highly subjective because the trend line depends on the personal judgment of
the investigator and, therefore, different persons may draw different trend lines from the same
set of data. Moreover, the work cannot be left to clerks and it must be handled by skilled and
experienced people who are well conversant with the history of the particular concern.
• Although this method seems to be quite simple, in actual practice it is very time-consuming to
construct a freehand trend if a careful and conscientious job is to be done. It is only after long
experience in trend fitting that a person should attempt to fit a trend line by inspection.
• Lastly, a straight line passing through these two averages is drawn to provide the trend for the
series. Each average provides the trend value for the middle time period of the corresponding
segment. When the time series includes an odd number of periods.
• This method of determining the trend is not a subjective one. The slope of the trend line now
depends upon the difference between the averages that are computed from the original values,
with each average as typical of the level of that segment of the data. However, this method is
not entirely free from drawbacks. The major drawback here is due to the arithmetic mean which
can be unduly affected by the extreme values in the series. If one part of the series contains
more depressions or fewer prosperities than the other, then the trend line is not a true
representation of the secular movements of the series. Therefore, the trend values obtained by
this method are not accurate enough for the purpose either of forecasting the future trend or of
eliminating the trend from the original data.
• This method of determining the trend is not a subjective one. The slope of the trend line now
depends upon the difference between the averages that are computed from the original values,
with each average as typical of the level of that segment of the data. However, this method is
not entirely free from drawbacks. The major drawback here is due to the arithmetic mean which
can be unduly affected by the extreme values in the series. If one part of the series contains
more depressions or fewer prosperities than the other, then the trend line is not a true
representation of the secular movements of the series. Therefore, the trend values obtained by
this method are not accurate enough for the purpose either of forecasting the future trend or of
eliminating the trend from the original data.
• This method is simple to understand compared to the moving average method and the method
of least squares.
• This is an objective method of measuring trend as everyone who applies the method is bound
to get the same result (of course, leaving aside the arithmetic mistakes).
• This method assumes a straight-line relationship between the two points plotted on the graph,
regardless of the fact whether such relationship exists or not.
• In this method, there is no assurance that the influence of cycle is eliminated. The danger is
greater when the time period represented by average is small.

LOVELY PROFESSIONAL UNIVERSITY 303