that have the lowest birth rates. For example, Sierra Leone, with the lowest
GNP has the highest birth rate. Based on the comparison of these rankings,
it appears that there is a fairly considerable negative relationship between
the rankings of the countries on the GNP and the birth rate scales.
Compare with the earlier table, the differences Di are much larger numerically, and the squares of these differences are even larger. The sums of the
squares of the differences of the ranks in the final column is
P
D2
i = 291:00.
It is this large value which produces a negative correlation coeffcient here.
The null hypothesis states that there is no correlation between the ranking of
the countries on the GNP and CBR scales. The alternative hypothesis states
that the rankings are negatively related. If the 0.01 level of signi¯cance, and
n ¡ 2 = 10 ¡ 2 = 8 degrees of freedom is used, the t value is -2.897. The
region of rejection of the null hypothesis is all t values to the left of -2.897.
The value of the standardized t statistic is