RELIABILITY AND ADEQUACY OF FARM-PRICE DATA 
35 
Table 15 shows the prices for potatoes and sweet potatoes in a 
few States. In New York State the large number of reports on the 
price of potatoes by months was sufficient to hold the probable error 
down to a point where four times the relative probable error was 
only 3.2 per cent. The December 1 sample was so much larger than 
the monthly price sample that four times the probable error was only 
2,4 per cent. While the price of sweet potatoes for "New Jersey and 
for Maryland has about the same variability as that of potatoes — 
15 to 20 per cent — the Georgia price sample showed over 30 per 
cent variation. The prices' for sweet potatoes are much less satis- 
factory than the prices for other potatoes, largely because of the 
small number of reports received and the wide dispersion of the 
prices. In many parts of the South sweet potatoes are not raised on 
a commercial scale, and the price is dependent on the local supply 
and demand. 
Table 15. — Farm prices of potatoes: Selected illustrations of size of sample, 
measures of dispersion, and prooaole errors 
Product, unit of measure, State, 
and date 
Number 
of reports 
Average 
price 
(arith- 
metic 
mean) 
Stand- 
ard devi- 
ation of 
reports 
Coef- 
ficient 
of varia- 
bility 
Probable 
error 
of the 
average 
price or 
mean 
Relative 
probable 
error 
Four 
times 
relative 
probable 
error l 
Potatoes: 
Per bushel- 
New York, November, 
Cents 
Cents 
Per cent 
Cents 
Per cent 
Per cent 
1925 
185 
74 
210 
219 
34.7 
35.9 
16.5 
16.4 
1.7 
2.9 
0.8 
1.4 
3 2 
Maine, November, 1925. 
5.6 
Maryland, March, 1926. 
32 
263 
50.7 
19.3 
6.0 
2.3 
9.2 
Per 100 pounds- 
Idaho, November, 1925.. 
32 
240 
43.8 
18.2 
5.2 
2.2 
8.8 
Per bushel- 
Maryland, Dec. 1,1925 2. 
105 
193 
40.8 
21.2 
2.7 
1.4 
5.6 
Per 100 pounds- 
Maryland, Dec. 1, 1925 2. 
34 
364 
71.8 
19.7 
8.3 
2.3 
9.2 
Per bushel- 
New York, Dec. 1, 1925 2. 
569 
219 
43.7 
20.0 
1.2 
.6 
2.4 
Sweet potatoes: 
Per bushel — 
Georgia, November, 
1925 
55 
149 
47.4 
31.9 
4.3 
2.9 
11.6 
New Jersey, November, 
1925. 
12 
11 
238 
217 
36.0 
37.5 
15.1 
17.3 
7.0 
7.6 
3.0 
3.5 
12.0 
Maryland, March, 1926. 
14.0 
Maryland, Dec. 1, 1926 K 
33 
181 
42.5 
23.5 
5.0 
2.8 
11.2 
1 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 prob- 
able error. 
2 The Dec. 1 prices were reported by crop reporters and not by the regular price reporters, who report 
on the 15th of each month. 
APPLES 
Apple prices are about as unsatisfactory as any of the major price 
series which the department collects. The dispersion in the price 
reports received is so wide that ordinarily not enough reports are 
received to give stability to the average price. Table 16 shows that 
it is not at all unusual for an apple-price sample to have a coefficient 
of variability of from 30 to 40 per cent. It is only in the larger apple 
States, where the sample is much larger than the usual State sample, 
that a degree of stability is reached which holds the probable error 
to a point where four times the relative probable error is less than 10 
per cent of the average price. 
