Annual Greenhouse, Sod and Nursery Survey
The purpose of this survey is to collect information on the production and value of greenhouse products, nursery stocks and sod produced in Canada.
Detailed information for 2014
Data release - April 23, 2015
This survey collects data on greenhouse, sod and nursery farms in Canada. The data are used by federal and provincial agriculture departments and producer associations to perform market trend analysis and to study domestic production with particular interest on imports. This survey also contributes to the agricultural receipts program of Statistics Canada.
- Crops and horticulture
Data sources and methodology
The target population is all farms in the 10 provinces of Canada that operate any greenhouse, sod, or nursery operations, except for institutional farms and community farms. Farms in the survey frame have been extracted from the Statistics Canada Business Register using the 2011 Census of Agriculture.
The questionnaires were developed by subject matter experts through consultation with the provinces and industry experts. The Operations and Integration Division and the Crops Section of the Collection, Planning and Management Division of Statistics Canada conduct in-house testing for flow and consistency.
Subject matter experts may change, add or remove questions. This typically happens because of changes in market trends or because of information in debriefing reports from field staff.
New questions were pre-tested in the field in 2008. This included testing the cognitive process of respondents in answering questions and other tests to obtain feedback for the design of the questionnaire.
This is a sample survey with a cross-sectional design.
For each province, the farms are classified into these 5 types (greenhouse-only, nursery-only, sod-only, greenhouse and nursery but no sod, and mixed) based on the presence or absence of greenhouse, sod and nursery activities. The "mixed" type includes all farms with sod and at least one of greenhouse or nursery. The farms within each type are classified into size groups, based on area and annual sales. The sampling stratum is the (type x size) group within the province.
Small operations that have a total greenhouse acreage smaller than a provincial threshold for total greenhouse, have a sod acreage smaller than a provincial threshold for total sod and have a nursery acreage smaller than a provincial threshold for total nursery are excluded from the sample (Take-None); these thresholds are set so that all farms with an acreage greater than any of the three thresholds represent 95% of greenhouse, sod and nursery acreage in the province together.
In each stratum, a threshold for each of the three commodities was defined using the sigma-gap method, based on the importance of that commodity to the stratum totals. All operations with acreage above one of the thresholds were selected in the sample (Take-All). For the remaining units, the Cumulative Root F Rule was used to divide the strata into 2 groups based on a combined measure of acreage and sales, the large and medium-sized Take-Some. These groups were then collapsed where necessary to ensure that at least 25 units remained in each stratum. A random sample was selected among the operations in each Take-Some stratum.
A sample consisting of 3014 farms was selected by stratified random sampling. We targeted Coefficients of Variation that ranged between 1% and 2% for the different area variables (total greenhouse area, total sod area and total nursery area) in each province. Given factors such as non-response, the final Coefficients of Variation could be much higher, especially for quantities of things that are rare, in the sense that they are grown on only a small proportion of farms.
Data collection for this reference period: 2014-12-12 to 2014-02-08
Responding to this survey is mandatory.
Data are collected directly from survey respondents.
The survey information is collected by telephone interview in Statistics Canada Regional Offices, using a Computer Assisted Telephone Interview (CATI) application. Questionnaires are mailed to the farm a few weeks prior to collection for the farmer's reference during the interview.
View the Questionnaire(s) and reporting guide(s) .
With the introduction of the CATI methodology, it is now possible to implement edit procedures at the time of the interview. Computer programmed edit checks in the CATI system inform interviewers during the interview of possible data errors, which can then be corrected immediately by the interviewer and respondent. The CATI system significantly reduces the need for subsequent telephone follow-up, thereby reducing respondent burden and survey processing time.
Erroneous data and partially completed questionnaires are imputed using historical data information.
The survey data collected are weighted within each stratum in order to produce estimates representative of the population. Non-responding units, for example, no contacts and refusals, are dealt with by adjusting the initial sample weights. A ratio adjustment based on the survey estimates compared to the 2011 Census of Agriculture is applied to the estimates to account for the small non-sampled Take-None units. The jackknife variance estimation method is used.
Daily edits and analysis of the top contributors and historical comparisons are performed before a final estimate is disseminated. Different sources of information are used to validate provincial estimations. No other surveys are available to compare directly with these survey results.
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 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.
The Greenhouse, Sod and Nursery Survey usually obtained a response rate between 80 and 85% of survey respondents.
The overall quality of the estimates depends on the combined effect of sampling and non-sampling errors. Sampling errors arise because estimates are derived from sample data and not the entire population. Non-sampling errors are errors which are not related to sampling and may occur throughout the survey operation for many reasons. For example, non-response is an important source of non-sampling error. Coverage, differences in the interpretation of questions, incorrect information from respondents, mistakes in recording, coding and processing of data are other examples of non-sampling errors.
The estimates published are based on a probability sample of farming operations. The potential error introduced by sampling can be estimated from the sample itself by using a statistical measure called the coefficient of variation (CV). Over repeated surveys, 95 times out of 100, the relative difference between a sample estimate and what would have been obtained from an enumeration of all farming operations would be less than twice the coefficient of variation. The sample estimate plus or minus twice the CV is referred to as the confidence interval. For the Annual Greenhouse, Sod and Nursery Survey, CVs at the Canada level range generally from 2% to 10% for the variables that are more frequently reported (area, investment, expenditures, sales, etc.), which makes them very reliable. Some variables on plant, flower and tree varieties have CVs greater than 25%. The coefficients of variation are available upon request.
- Date modified: