Page 150 - DECO504_STATISTICAL_METHODS_IN_ECONOMICS_ENGLISH

Statistical Methods in Economics

Notes correlation is found exist between two variables, it implies that there must be a reason for such
close relationship, but the cause and effect relation can be revealed specifically when other
knowledge of the factor involved being brought to bear on the situation. This means, to establish
a ‘functional relationship’ between two or more variables, one has to go beyond the confines of
statistical analysis to other factors. (Functional relationship means that two or more factors are
interdependent.
• When the values of the two variables move in the same direction, i.e., an increase in one is
associated with an increase in other, or vice versa, the correlation is said to be positive. If the
values of two variables move in the opposite directions i.e., an increase in the value of one
variable is associated with fall in other, or vice versa, the correlation is said to be negative. For
example, the price and supply are positively correlated but price and demand are negatively
correlated.
• When relation between two variables is studied, it is simple correlation. When three or more
factors are studied together to find relationships, it is called multiple correlation. In partial
correlation, two or more factors are agreed to be involved but correlation is studied between
only two factors, considering other factors to be constant.
• The cause and effect relation existing between economic events is especially difficult to ascertain
because of the presence of innumerable variable elements. In solving his problems the economist
can not, like the physicist or chemist, eliminate all causes except one and then by experiment
determine the effect of that one. Causes must be dealt with en masse. Since any effect is the result
of many combined causes the economist is never sure that a given effect will follow a given
cause. In stating an economic law he always has to postulate “other things remaining the same,”
with, perhaps, little appreciation of what the other things may be. It is rarely, if ever, possible
for the economist to state more than “such and such a cause tends to produce such and such an
effect.” Events can only be stated to be more or less probable. He is dealing mainly, therefore,
with correlation and not with simple causation.
• Just as the biologists cannot predict a man’s height or color of eyes or temper or combativeness
by knowing those qualities in his ancestors, so economists cannot predict that a definite call
rate in Wall Street will go with a given percentage of reserves to deposits in New York banks or
that a given supply of wheat will result in a definite price per bushel. But, on the other hand,
just as it has been observed that there is a relation existing between a man’s stature and the
stature of his ancestors, so it has been observed that a relation does exist between bank reserves
and call rates and between supply of wheat and its price per bushel.
• The commonly used method of measuring the amount of correlation between any two series of
economic statistics is to represent the two series graphically upon the same sheet of cross-
section paper and then compare the fluctuations of one series with those of the other. The
quantity theory of prices has been tested in this way by Dr. E. W. Kemmerer. Dr. Kemmerer
builds up the following price equation:
• In the case of the correlation of bank reserves and money in circulation, inclusive of bank reserves,
Dr. Kemmerer concludes, “There can be no question but that when due allowance is made for
fluctuations in business confidence, the evidence of Chart I strongly supports the contention
that there exists a close relationship between the amount of money in circulation and the amount
of the country’s bank reserves.”
• The graphic method of comparing fluctuations is well enough as a preliminary, but does it
enable anyone to tell anything of the extent of the correlation between the series of figures being considered?
Is Dr. Kemmerer warranted in deducing his conclusions from observation of the charts ? It
seems to the writer that one opposing the quantity theory might draw opposite conclusions
with as much (or as little) reason. The charts do not answer the questions proposed. The painstaking
collection of statistics to test correlation is useless if there be no more reliable method to measure
correlation. A numerical measure of the correlation must be found if we wish to determine the
extent to which the fluctuations of one series synchronize with the fluctuations of another series.

144 LOVELY PROFESSIONAL UNIVERSITY