Supply and disposition of hogs in Canada using PigTRACE estimates

This experimental release uses administrative data collected by the Canadian Pork Council (CPC) to estimate interprovincial hog imports and exports, defined as the movement of pigs to a different province for non-slaughter purposes. This approach is in line with Statistics Canada's AgZero Initiative, which aims to produce high-quality estimates using models, administrative data and other non-traditional survey-based approaches.

The data published in Table 32-10-0227-01, "Experimental hog estimates using PigTRACE data, supply, disposition, and ending inventories of hogs, semi-annual," are released as experimental statistics. The purpose of this release is to assess the feasibility of replacing current estimates of interprovincial imports and exports with estimates derived from the PigTRACE program. Interprovincial movements of hogs are currently published in Table 32-10-0200-01, "Hog statistics, supply and disposition of hogs, semi-annual." These data are estimated via the Biannual Livestock Survey, in consultation with provincial specialists. The values published in Table 32-10-0200-01 remain the official statistics on Canadian hog supply and disposition.

Since July 1, 2014, reporting to PigTRACE is mandatory by law for all people and organizations participating in the movement of pigs. It is, however, recognized that if premises do not report their movements to the CPC, there may be undercoverage in the PigTRACE estimates.

Random tabular adjustment

The random tabular adjustment (RTA) technique, which aims to increase the amount of data made available to users while protecting the confidentiality of respondents, was applied to the estimates derived from PigTRACE hog movement reports.

Statistics Canada typically uses suppression techniques to protect sensitive statistical information. These techniques involve suppressing data points that can directly or indirectly reveal information about a respondent. This can often lead to the suppression of a large number of data points and significantly reduce the amount of available data.

Using RTA, Statistics Canada can identify sensitive estimates and randomly adjust their value rather than suppress them. The size of the adjustment is calculated to protect respondent confidentiality. After adjusting the value, the agency assigns a quality measure (A, B, C, D or E) to the estimate to indicate the degree of confidence that users can have in its accuracy.

For more information on RTA, please refer to the article "Random Tabular Adjustment is here!," now available as part of the StatCan Blog.