BUREAU OF STATISTICS. 785 



REVISION OF ESTIMATES. 



The reports issued by the Bureau of Statistics from month to 

 month do not purport to be other than estimates; they are not the 

 results of actual enumerations as are the figures reported decennially 

 by the Bureau of the Census. Every (}uantitative estimate of this 

 bureau, whether relating to acreage and production of crops or 

 numbers of live stock, is nothing more than a consensus of judgment 

 of many thousands of correspondents and a limited number of 

 agents. 



The annual estimates regarding acreage of crops and number of 

 live stock are based on corresponding estimates for each preceding 

 year, there being no other bases to which can be applied the percent- 

 ages of increase or decrease indicated by reports received fi-om cor- 

 respondents and agents, except once in 10 years, when census figures 

 become available. 



When the figures of the last census became available, showing the 

 number of each class of live stock on farms in 1910 and the areas of 

 crops in 1909, they were adopted as bases for subsequent estimates, 

 which were arrived at by applying the percentages of increase or 

 decrease for the year following the census to the census figures. 



It is, of course, out of the question that an agricultural census be 

 taken every year; the expense would be prohibitive. The only way 

 in which the constant and increasing demand for current information 

 can be met is through carefully made estimates. It is not claimed 

 that the estimates of the Bureau of Statistics are exactly accurate; 

 no estimate can be. They are given as the best available data, rep- 

 resenting the fullest information obtainable at the time they are 

 made. 



It is apparent that estimates made monthly, from year to year, 

 following each other during a period of 10 years, without means of 

 verification or correction, are likely to be more or less out of line 

 with conditions at the end of the 10-year period as disclosed by actual 

 census enumerations. Cumulative errors, impossible of discovery, 

 are likely to occur and can not be corrected until census reports are 

 available. 



If the requirement that an agricultural census be taken hereafter 

 every five years is carried into effect, the estimates of this bureau 

 can be checked up and adjusted to the facts as disclosed by the 

 quinquennial enumerations, and new bases for estimates be provided 

 every five years, resulting in corresponding reduction in the extent 

 of cumulative errors or other divergencies. 



The e^stimates of the bureau are made promptly, for current use; 

 the results of actual enumerations by census methods can not be 

 made Imown until a year or more has elapsed after the agricultural 

 data have been gathered. Constant effort is made to render the 

 estimates as closely approximate to the facts as is possible; and, 

 when census figures are available, they are used for the purpose of 

 revision and adjustment to increase their accuracy; but when not 

 available, dependence must, of necessity, be placed on the ccmsensns 

 of judgment of the bureau's correspondents and agents. 



The results of the agricultural census which related to 1909 were 

 not pulilished in time to permit a revision of estimates until the close 

 of 1911, when revisions, for all crops for which census figures wero 



70481°— AGB 1912 50 



