EELIABILITY AND ADEQUACY OF FABM-PRICE DATA 
37 
practice, there are wide price differentials owing to the fact that 
different varieties are being sold within a limited area. Sales within 
an area may include such varieties as Ben Davis, Baldwin, Wealthy, 
and Delicious. 
A price series by varieties would be misleading in years of light 
production or heavy production of those particular varieties. The 
barrel price is not always satisfactory because over a period of years 
the cost of the barrel in which the apples are packed is not the same 
and in some years its cost exceeds the value of the apples packed 
in it. The reported price series for any farm product which is sold 
in containers is affected by variations in the value of the container. 
ANALYSIS OF PRICES OF LIVESTOCK AND LIVESTOCK PRODUCTS 
Hogs from the North Central States are sold on a highly organ- 
ized market. The local market for hogs in these States is fully as 
sensitive to price changes in the primary markets as are the local 
markets for wheat and cotton. Table 17 shows that the coefficient 
of variability of prices of hogs per ±00 pounds in a surplus-produc- 
ing State like Iowa is as low as that of wheat in Kansas or cotton 
in the South. Because of the low variability of the sample, the num- 
ber of reports received on the price of hogs in Iowa is sufficient to 
hold the probable error to a point where four times the relative 
probable error is frequently less than 2 per cent. 
The fact that the local hog markets of Maryland are in close 
touch with the Baltimore market tends to hold the variability at the 
low figure, 6.1 per cent, for March, 1926. In Virginia local-market 
demand is an important factor in hog prices, and as a result the 
coefficient of variability, about 16 per cent, is higher than that in 
either Iowa or Maryland. 
Hog prices in States of surplus production are fully as reliable 
as wheat, cotton, or flax prices and are probably more dependable 
than any other livestock or livestock-product prices. 
Table 17. — Farm prices of hogs: Selected illustrations of size of sample, 
measures of dispersion, and probable errors 
[Per 100 pounds live weight or per head] 
State and date 
Number 
of re- 
ports 
Average 
price 
(arith- 
metic 
mean) 
Standard 
devia- 
tion of 
reports 
Coeffi- 
cient of 
varia- 
bility 
Probable 
error of 
the aver- 
age price 
or mean 
Relative 
probable 
en-or 
Four 
times 
relative 
probable 
error J 
Iowa: 
October, 1924 
45 
92 
61 
91 
85 
278 
28 
90 
24 
Dollars 
10.21 
12.63 
12.28 
11.22 
11.17 
17.06 
9.51 
11.48 
13.25 
Dollars 
0.90 
.95 
.53 
.83 
.50 
4.65 
1.50 
1.84 
.80 
Per cent 
8.8 
7. 5 
4.3 
7.2 
4.5 
27.2 
15.7 
16.0 
6.1 
Dollars 
0.09 
.07 
.05 
.06 
.04 
.19 
.19 
.13 
.11 
Per cent 
0.9 
.6 
.4 
.5 
l'.l 
2.0 
1.2 
.8 
Per cent 
3.6 
March, 1925 
2.4 
April, 1925- 
1.6 
May, 1925.. 
2.0 
June, 1925 
1.2 
Jan. 1, 1926 2 
4.4 
Virginia: 
October, 1924 
8.0 
April, 1925 
Maryland: 
March, 1926. . ... 
4.8 
3.2 
1 The probabilities are ninety-nine out of one hundred that the average of a much larger sample collected 
inthe same way and at the same time would not vary from this average by more than four times the prob- 
able error. 
2 These are Jan. 1 value of hogs per head, as reported by crop reporters, who are farmers. The January, 
1926, report summarizes about half the schedules received;. the other half of the schedules reported hog 
values by subclasses. 
