Natural Health Products Survey
Detailed information for Winter 2004
This survey collected new statistical information to measure the size and scope of the natural health product activities in Canada. National estimates of products manufactured, imported and sold in Canada were produced by product class, based on active ingredients used.
Data release - March 29, 2004
The purpose of the survey was to collect new statistical information to measure the size and scope of the natural health product activities in Canada. National estimates of products manufactured, imported and sold in Canada were produced by product class, based on active ingredients used.
Results from this survey will be used by Health Canada to forecast the operational and planning requirements for the timely review and assessment of natural health product license applications. These product license applications are expected as a result if the new Natural Health Product Regulations which came into effect on January 1, 2004.
- Environmental factors
- Lifestyle and social conditions
Data sources and methodology
The population units covered by this survey are firms involved in the manufacturing and/or importing of Natural Health Products (for sale in Canada) in North American Industrial Classification (NAICS) Codes:
325410 Pharmaceutical and Medicine Manufacturing; 325620 Toilet Preparation Manufacturing; 414520 Toiletries, Cosmetics and sundries Wholesaler-Distributors and 413190 Other Specialty-Line Food Wholesaler-Distributors.
This survey population also includes companies identified in the Natural Health Products Canada, Industry Guide 2003/2004 published by Contact Canada, with the exception of associations, departments, or organizations that were clearly uninvolved in the actual manufacturing or importing of Natural Health Products.
The Natural Health Products survey was developed by the Small Business and Special Surveys Division of Statistics Canada with input and guidance from the Natural Health Products Directorate of Health Canada. The survey questionnaire was reviewed by the Statistics Canada Questionnaire Design and Resource Centre. Questionnaire testing was conducted in Toronto and Montreal and in both official languages.
This is a sample survey with a cross-sectional design.
The survey frame was built using a combination of Statistics Canada's Business Register (BR) and the Natural Health Products Canada, Industry Guide 2003/2004 published by Contact Canada.
After researching the North American Industrial Classification System NAICS codes of companies known to be involved in manufacturing and importing natural health products, the following NAICS were determined to most likely contain the greatest proportions of companies involved in natural health products: 325410 Pharmaceutical and Medicine Manufacturing; 325620 Toilet Preparation Manufacturing; 414520 Toiletries, Cosmetics and sundries Wholesaler-Distributors and 413190 Other Specialty-Line Food Wholesaler-Distributors. All of the companies in these NAICS were contacted (in a process called pre-contact) to determine if they participated in the manufacturing or importing of natural health products. All of the companies that indicated participation in these activities during pre-contact were included in the survey frame. After comparing the companies from the NAICS list to the Contact Canada list, and removing duplicates, almost all companies from the Contact Canada industry guide were surveyed. (The exceptions were associations, departments, or organizations that were clearly uninvolved in the actual manufacturing or importing of Natural Health Products).
The final sample size was 931 units.
Data collection for this reference period: 2004-01-01 to 2004-02-15
Responding to this survey is voluntary.
Data are collected directly from survey respondents.
Data was collected using a paper mail-out, mail-back questionnaire. Pre-contact was made by telephone prior to the mail-out. Follow-up was also conducted by telephone.
View the Questionnaire(s) and reporting guide(s) .
Questionnaires were manually edited and outliers detected as they were received during collection. A series of edit rules were developed and invalid or inconsistent entries were corrected using these rules. Follow-up was conducted for missing entries that could not be manually edited.
Imputation was done using BANFF, a generalized system developed at Statistics Canada. It is the same application as GEIS on the mainframe except that it is used on PC with SAS.
The imputation method used was donor imputation. Most of the donors were randomly selected among a pool of donors. This is referred to as hot deck imputation. However, when possible, we selected a donor using a matching field, i.e. a variable correlated to the variable to be imputed. Thus, a distance between the donor and the recipient is calculated based on the matching field. The donor with the smallest distance is therefore selected within the imputation group. This is called nearest neighbour imputation.
Imputation groups were based on the NAICS codes.
The estimation was done using GES (Generalized Estimation System). A weight was derived for each unit based on the sampling fraction in each stratum (NAICS). Non-response adjustments were also done at the stratum level. The weight of completes, partials, OOS and OOB was increased to compensate for non-response.
Means and totals were computed using the Horvitz-Thompson estimator. The variance estimation method was a simple stratified variance estimator.
The Natural Health Products Survey was the first survey of it's kind conducted in Canada. Currently there is no published data comparable to the data collected by the Natural Health Products Survey.
Statistics Canada is prohibited by law from releasing any data which would divulge information obtained under the Statistics Act that relates to any identifiable person, business or organization without the prior knowledge or the consent in writing of that person, business or organization. Various confidentiality rules are applied to all data that 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.
Aggregated tabular data was released for this survey. Sensitive cells, with a C.V. greater than 30% or and Standard Error greater than 15%, were suppressed.
Revisions and seasonal adjustment
This methodology type does not apply to this survey.
The data accuracy indicators used for the Natural Health Products Survey were 'Standard Error' and the 'Coefficient of Variation'. The standard of error is a commonly used statistical measure indicating the sampling error of an estimate. The standard error and the coefficient of variation (standard error expressed as a percentage of the estimate) was using in the following tables to provide an indication of the level of data quality of the estimate. Please note that the coefficient of variation (CV) was not calculated for percentage tables.
Alphabetic symbols representing the size and range of the standard error and coefficient of variation (CV) were used in the statistical tables to provide and indication of the extent of the sampling error of the estimates. The letter 'A' indicates that the estimate has a very low standard of error or CV; the letter 'B' indicates that the standard error or CV is somewhat larger; and so forth. Some data with a higher standard error or CV (in the 'C' category) are precise enough for some purposes, however one should proceed with caution. The letter 'D' indicates that the estimate had a standard error or more than 15% or a C.V. of greater than 30%. Estimates subject to sampling error of this magnitude were not published.
The response rate for this survey was 54%.