Fruits and Vegetables Survey (FV)

Detailed information for 2015





Record number:


This survey collects data to provide estimates of the total cultivated area, harvested area, total production, marketed production and farm gate value of selected fruits and vegetables grown in Canada.

Data release - February 3, 2016


This survey collects data to provide estimates of the total cultivated area, harvested area, total production, marketed production and farm gate value of selected fruits and vegetables grown in Canada. The data are used by Agriculture and Agri-Food Canada, other federal departments, provincial organizations and related industries for production and price analysis, and for development of agricultural policies and programs.

Reference period: One year

Collection period: Mid November to early December


  • Agriculture and food (formerly Agriculture)
  • Crops and horticulture
  • Food and nutrition

Data sources and methodology

Target population

The target population is all farms in the ten provinces of Canada that grow fruit and/or vegetables for sale. The Yukon, the Northwest Territories and Nunavut are excluded from the survey.

The survey frame excludes farms producing only mushrooms, farms producing only greenhouse vegetables, and farms producing only potatoes, as well as institutional farms, community pastures or farms that are on Indian reserves.

Instrument design

The questionnaire was developed by subject matter specialists through consultation with the provinces and industry experts. New questions are not pre-tested in the field. However, testing is conducted in-house for flow and consistency. Questions will be changed, added or removed as the need arises. Required changes are usually identified through such means as subject matter specialist research, changes in market trends and field staff debriefing reports.


This is a sample survey with a cross-sectional design.

For each province, small operations that have a total fruit acreage smaller than a provincial threshold for total fruit or have a vegetable acreage smaller than a threshold for total vegetables are excluded from the sample (Take-None); these thresholds are set so that all farms with greater acreage than either threshold together represent 95% of fruit and vegetable acreage in the province. Three strata were then defined based on the type of operation i.e. fruit only operation, vegetable only operation or fruit and vegetable operation. In each province, a threshold for commodities using the sigma-gap method was defined, based on the importance of that commodity to the provincial or national totals. All operations with acreage above the threshold 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 acreage, 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, and a random sample was selected among the operations in each Take-Some stratum. For each stratum, a minimum sample size was set to ensure a maximum design weight of two.

Overall, the sample size was determined in order to achieve a target CV of around 0.01 (1%) for total fruit area and total vegetable area at the provincial level. The final sample size was 7,024 operations. During collection, survey response reached is 81.99%.

Data sources

Data collection for this reference period: 2015-11-12 to 2015-12-06

Responding to this survey is mandatory.

Data are collected directly from survey respondents.

The data are collected by telephone interview in Statistics Canada regional offices, using a Computer Assisted Telephone Interview (CATI) application.

View the Questionnaire(s) and reporting guide(s) .

Error detection

There are edits built into the data capture application to compare the entered yield and price data against provincial averages, as well as to check for possible inconsistencies. Whenever an edit fails, the interviewers are prompted to correct the information (with the help of the respondents when necessary). For most edit failures the interviewers have the ability to override the edit failure if they cannot resolve the apparent discrepancy.

Once the data are received back at head office an extensive series of processing steps are undertaken to thoroughly verify each record received. All data failing these edits are subject to manual inspection and possible corrective action.


Partially completed questionnaires are imputed using a combination of automated and manual approaches. The automated imputation is done by Statistics Canada's AG2000 software using ratio imputation: a trend analysis of the fully completed questionnaires generates averages, which are used to impute missing values. The manual imputation uses various methods such as historical imputation and imputation using provincial averages for yield and price.


The survey data collected are weighted within each stratum in order to produce estimates representative of the population. The weights of respondents are adjusted to account for non-response. Analyses of the top contributors and historical comparisons as well as consultations with the Provincial Departments of Agriculture are performed before a final estimate is published. The jackknife variance estimation method is used.

Quality evaluation

Disseminated data are subject to a certain degree of error such as incorrect information from respondents or mistakes introduced during processing. Reasonable efforts are made to ensure such errors are kept within acceptable limits through careful questionnaire design, editing of data for inconsistencies and subsequent follow-up and quality control of manual processing operations. Extensive consultation with provincial agricultural experts combined with data from various marketing boards assists in the verification of the level estimates obtained through the survey.

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 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.

A series of sensitivity rules known as the Duffett rules are used to identify cells which are considered sensitive. Sensitive cells are suppressed, and complementary suppression of non-sensitive cells is also done to avoid disclosure of the sensitive cells.

Data accuracy

The statistics from the Fall Survey of Fruits and Vegetables are based on a random sample of agricultural operations and, as such, are subject to sampling and non-sampling errors. The overall quality of the estimates depends on the combined effect of these two types of errors.

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. Population 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.

By the end of the collection period, around 85% of the questionnaires have been fully completed. The refusal rate to the survey is approximately 2.5%. The remainder of the sample unaccounted for can be explained by non-contact and non-response. Initial sample weights are adjusted by a process called "raising factor adjustment" in cases of total or partial non-response.

Sampling errors arise because estimates are derived from sample data and not from the entire population. These errors depend on factors such as sample size, sampling design and the method of estimation. Sampling error can be measured by the standard error (or standard deviation) of the estimate. The coefficient of variation (CV) is the estimated standard error percentage of the survey estimate. Estimates with smaller CVs are more reliable than estimates with larger CVs. Coefficients of variation values for the published data are available upon request and are not included in this publication due to space limitations.

Date modified: