RELIABILITY AND ADEQUACY OF FAEM-PBJCE DATA 
33 
such minor crops as buckwheat and cowpeas is that they indicate the 
price trend over a period of a year or more. Since cowpeas are sold 
primarily for seed purposes and are grown in Southern States, it is 
not surprising to find a coefficient of variability of about 25 per cent 
as there are comparatively few reports and 12.4 per cent as four 
times the relative probable error. The farm prices of other seed 
crops such as soy beans, clover, timothy, and alfalfa seed are usually 
highly variable and the average prices relatively unstable because of 
the limited number of reports received on such minor crops. 
HAY 
Hay prices have large coefficients of variability in all sections of 
the country, whether the price is that of loose hay or baled hay, or 
whether it applies to timothy, clover, alfalfa, or prairie hay. Table 
14 shows that the variability in prices is seldom less than 15 per cent, 
and that not often is it more than 25 per cent. With the size sample 
usually obtained in most States of fair size, the probable error is 
such that four times the relative probable error is from about 5 to 10 
per cent. For some of the less important varieties of hay in a given 
State, the sample is so small that the probable error is much larger. 
Hay prices fluctuate considerably from month to month, but are 
valuable as indicating the trend of prices over a period of several 
months. The price of baled hay has been asked as a check question 
in order that the prices of loose hay might be reported as those of 
loose hay and not as those of baled hay, in some cases. The variabil- 
ity of baled-hay prices is apparently less than that of loose-hay 
prices. 
Table 14. — Farm prices of hay: Selected illustrations of size of sample, 
measures of dispersion, and probable error 
[Per ton] 
State, commodity, and date 
Number 
of reports 
Average 
price 
(arith- 
metic 
mean) 
Standard 
deviation 
of reports 
Coeffi- 
cient of 
variabil- 
ity 
Probable 
error of 
the aver- 
age price 
or mean 
Relative 
probable 
error 
Four 
times 
relative 
probable 
error 1 
New York: 
Loose — 
November, 1925 „ 
December, 1925 . 
72 
115 
91 
75 
56 
59 
43 
45 
28 
40 
26 
27 
7 
21 
93 
Dollars 
13.56 
13.95 
16.44 
15.68 
14.95 
13.24 
12.86 
18.18 
16.25 
19.35 
17.81 
16.30 
20.14 
18.43 
18.94 
Dollars 
2.97 
3.34 
2.35 
3.45 
3.81 
2.80 
2.23 
3.37 
3.80 
3.38 
3.39 
3.39 
3.44 
3.50 
3.78 
Per cent 
21.9 
23.9 
14.3 
22.0 
25.5 
21.1 
17.3 
18.5 
23.4 
17.5 
19.0 
20.8 
17.1 
19.0 
20.0 
Dollars 
0.235 
.210 
.166 
.269 
.342 
.245 
.229 
.339 
.484 
.362 
.449 
.440 
.875 
.515 
.266 
Per cent 
1.8 
1.5 
1.0 
1.7 
2.3 
1.9 
1.8 
1.9 
2.9 
1.9 
2.5 
2.7 
4.4 
2.8 
1.4 
Per cent 
7.2 
6.0 
Baled, December, 1925 
Timothy- 
December, 1925 
November, 1925 
Clover — 
December, 1925 
4.0 
6.8 
9.2 
7.6 
November, 1925 
Alfalfa, December, 1925 
Pennsylvania: 
Loose, December, 1925 
Baled, December, 1925 
Timothy, December, 1925__ 
Clover, December, 1925 
Alfalfa, December, 1925 
Maryland: 
Loose — 
March, 1926 - 
7.2 
7.6 
11.6 
7.6 
10.0 
10.8 
17.6 
11.2 
December, 1925 
5.6 
i The probabilities are ninety-nine out of one hundred that the average of a much larger sample collected 
in the same way and at the same time would not vary from this average by more than four times the 
probable error. 
26813°— 27 5 
