15 
V\ 
or conditional distribution of income, therefore includes 
MMft income here, The regression of property owners’ total 
income on their wealth can be studied on the basis of 
Dutch data '■ (fig. 5). The regression is linear, and homo- 
scedastic; the correlation coefficient is 0,5* the re 
gression coofficient is 0.G2Si0.004 (data for 1962/63). 
Tho regression coefficient corresponds to our k, Shot 
<1 can bo explained in the first place by the presumed 
fact that with increasing wealth earned income is less 
and loss important; in the second pi co perhaps by the 
fact that income from shares which dominates for the 
larger wealth does notjk ant a in the undistributed profits. 
Since the Pareto coefficient for wealth was 1.38 in 1962/63* 
we should expect it to be 2.20 for income on the basis of 
the theory. In reality it was 2.03. A better correspondence 
is hardly to be expected, since the wealth distribution at 
that time has been distorted by the stock exchange boom 
(see /l /). 2 ) 
A similar calculation with Swedish data gives very un 
satisfactory results, although the regression line is 
linear and homoscedastic. This may be explained by the 
guosr: that the classification of income (which stops at 
^ D* J 
,.n .a.* 
at * 
1 >See / 1/ 
2) 
Since the holding of shares increases strongly with the 
^0 ^(T ^ , z-'t