Appendix I: Appendix I
Archived Content
Information identified as archived is provided for reference, research or recordkeeping purposes. It is not subject to the Government of Canada Web Standards and has not been altered or updated since it was archived. Please "contact us" to request a format other than those available.
Concepts and methodology
This report profiles establishments engaged in functional food and natural health product related activities in Canada based on data from the 2011 Functional Foods and Natural Health Products (FFNHP) Survey, conducted in partnership with Agriculture and Agri-Food Canada. The 2011 survey collected information on the activities of establishments for their 2011-12 fiscal year. Previous iterations of the survey were in 2003, 2005 and 2007.
Concepts
Establishment
The establishment is the statistical unit for the FFNHP survey. An establishment is the production entity or smallest grouping of production entities which:
- produces a homogeneous set of goods or services;
- does not cross provincial boundaries; and
- provides data on the value of output together with the cost of principal intermediate inputs used along with the cost and quantity of labour resources used to produce the output.
For example, a plant in the manufacturing industry which provides accounting information regarding the value of shipments (sales), direct costs and labour costs, is considered a single establishment. However, two stores in the retail industry may be considered one establishment if the accounting information described above, is not available separately, but is combined at a higher level.
A production entity is a physical unit where business operations are carried out. It must have a civic address and dedicated labour.
Establishments range from start-ups to multinationals.
Coverage
The target population for the FFNHP survey included all establishments in Canada who developed, produced or provided services related to functional foods or natural health products for the purpose of human consumption during the reference period. Products specifically excluded were pet food, feed, cosmetics and topical creams.
Establishments which strictly retailed or wholesaled functional foods or natural health products were excluded as were establishments of the following types: not-for-profit organizations, associations, alliances, unions, universities, as well as government agencies, departments and commissions.
The survey frame was developed in several stages. Agriculture and Agri-Food Canada compiled a list of business units they identified as engaged in functional food and natural health product-related activities in Canada. Additional units were added to this list from respondents to the 2007 iteration of the survey and from other related external data sources. Businesses in the list were then matched to units on the Statistics Canada Business Register and duplicates were removed. The final survey frame comprised 1,623 establishments engaged in functional food and natural health product-related activities.
The target populations for the 2007 and 2011 iterations of the Functional Foods and Natural Health Product surveys were the same. However, the statistical units and the survey frames were different. In 2011, the survey targeted individual establishments. In 2007, the survey targeted groups of establishments belonging to the same enterprise and located in the same province. The frames for each year were compiled from all available data sources which were different across the two reference periods. As a result, survey estimates for 2007 and 2011 cannot be compared.
Collection
The FFNHP survey used a paper questionnaire to collect data from respondents. This questionnaire was designed by Statistics Canada in co-operation with Agriculture and Agri-Food Canada and in consultation with a group of functional food and natural health product experts. Following the initial design work, the questionnaire was field-tested with potential respondents. Their comments on the design and content were incorporated into the final version.
All establishments were "pre-contacted" by telephone to confirm that they were in-scope for the survey, as well as to determine the name and mailing address for the senior plant manager or research and development manager who would be asked to complete the questionnaire.
Data were collected using a mail out/mail back questionnaire. Questionnaires were mailed to 1,233 establishments following pre-contact. Respondents were asked to return the completed questionnaire within 30 days of receipt. Follow-up for non-response was conducted by telephone and fax. Upon receipt, the collected questionnaires were imaged and data from the questionnaires was captured. The response rate for this survey was 50.6%.
Error detection
Error detection was an integral part of both collection and data processing activities. Automated edits were applied to data records during collection to identify capture and reporting errors. During collection, respondents were contacted by telephone to validate collected data which failed edits.
Prior to imputation, subject matter specialists used a variety of tools to identify and resolve inconsistencies and outliers in the collected data. This review of the micro data focused on records which would have the most significant impact on the final survey estimates either because of the size of their contribution or because of their use in imputation. Problems were resolved using historical and administrative data, data from other surveys, and information from other external sources.
Following imputation, subject matter specialists compared patterns in the current estimates with those observed in data from previous iterations of the survey, where possible. The largest differences in the patterns were investigated by reviewing the source of the change in the micro data and resolving any remaining data issues.
Imputation
Imputation was used to determine plausible values for all variables that were missing or inconsistent in the collected data and which could not be resolved through editing. A number of different approaches were used to impute missing or inconsistent data. The simplest technique involved using a group of deterministic and coherence rules that dictate acceptable relationships among variables and derive missing values residually. Missing variables were also imputed by applying the ratios between variables and historical trends observed in the respondent data, to data records with partial information. Direct replacement of missing variables with data from other sources was another imputation approach used. Lastly, donor imputation was also used. This involved identifying a respondent record (donor) that was similar to the record which required imputation (recipient) based on information which was available for both businesses. The data available for the respondent was then used to derive that for the record requiring imputation.
Imputation groups were based on a number of criteria including establishment type, various measures of size, complexity and province or region. Data from selected survey questions were used to assign an establishment type to each respondent. Seven establishment types were defined as follows: functional foods only; natural health products only; services only; functional foods and natural health products; functional foods and services; natural health products and services; and functional foods, natural health products and services. No imputation was done for records when their establishment type could not be assigned.
Estimation
A complete micro data file was created for all establishments in the survey population for which data were reported or could be imputed. In a census, each establishment in the population would ordinarily represent only itself in the estimates with a weight of 1. However, no imputation was done for records when their establishment type could not be assigned. These records were treated as non-respondents. As a result, weights on all records were adjusted by a factor to account for survey non-response so that the final estimates would be representative of the entire survey population.
Quality evaluation
Survey estimates were compared with estimates from previous iterations of the survey where possible. In addition, subject matter experts from outside Statistics Canada were given an opportunity to review the estimates and provide feedback on quality prior to their release.
Disclosure control
Statistics Canada is prohibited by law from releasing any information it collects which could identify any person, business, or organization, unless consent has been given by the respondent or as permitted by the Statistics Act. Various confidentiality rules are applied to all data which are released or published to prevent the publication or disclosure of any information deemed confidential. If necessary, data are suppressed to prevent direct or residual disclosure of identifiable data.
In order to prevent any data disclosure, confidentiality analysis was done using the Statistics Canada’s G-CONFID system. G-CONFID was used for primary confidentiality as well as for the secondary suppression (residual disclosure). Direct disclosure or primary confidentiality occurs when the value in a tabulation cell is composed or dominated by few enterprises. Residual disclosure occurs when confidential information can be derived indirectly by piecing together information from different sources or data series.
Data accuracy
The data accuracy indicators used for the Functional Foods and Natural Health Products Survey were the standard error and the coefficient of variation. The standard error is a commonly used statistical measure indicating the error of an estimate associated to sampling and to adjustments made because of complete non-response. For this survey, there was no error associated to sampling. The coefficient of variation is the standard error expressed as a percentage of the estimate. The reliability of the data was reported using the symbol convention in Table 1.
- Date modified: