Data quality, concepts and methodology: Methodology and data quality

View the most recent version.

Introduction

Throughout the publication, data in some instances have been updated based on more recent information from differing data sources. The contents of this publication represent the most recent information available at the time of printing on selected fruits and vegetables produced in Canada. All data are prepared in consultation with representatives of Federal and Provincial Departments of Agriculture and the Institut de la statistique du Québec. Current year data are preliminary and will be revised in subsequent publications and on CANSIM.

Current year area figures are preliminary while historical data are estimated based on more complete market information. Data are generally concerned with total production and take into account wastage. With the availability of market and wastage information the estimates more closely reflect commercial production.

Data shown in this publication are on a crop year basis. In the case of mushrooms and greenhouse tomatoes and cucumbers, however, the data are on a calendar year basis. All value data are those obtained at the "farm gate" and are concerned with returns to growers. Estimates are provided in both imperial and metric units.

Production and value data are provided for the thirteen most commercially significant fruits grown in Canada. The production figures for fruit crops refer to marketed production rather than harvested production. Only vegetable crops grown commercially are included: no data are available for fruits and vegetables grown for home consumption.

Spring Fruit and Vegetable survey

Survey methodology

A major source of information in this publication is the 2009 Spring Survey of Fruit and Vegetables conducted by Statistics Canada. This is a sample survey for which the data are collected by telephone. The survey estimates the intended area to be planted for the principal fruit and vegetable crops. For fruit, bearing area is estimated as a subset of the cultivated area and is a sum of the fresh market and processing areas.

The data collected from this survey is used to provide aggregate information of estimates of the area for the fresh and for the processing markets of fruit and vegetable crops in Canada. The results are publicly released and are used by producer associations and governments to assess the economic health of the industry.

Survey frame

The survey frame has been designed to include all operations growing fruit or vegetables based on the latest Census of Agriculture. Observations on the Spring 2009 survey frame have been extracted from two last Spring survey occasions and the 2006 Census of Agriculture, to which have been added some operations coming from external sources.

Institutional farms, farms on Indian reservations, Hutterite colonies as well as operations from Yukon, the North West Territories and Nunavut were excluded from the survey. Operations producing only mushrooms, potatoes or greenhouse vegetables were excluded as well because these operations are already covered by other surveys collecting the desired information. Also excluded were the small operations with less than 1 acre of fruit and 1 acre of vegetables. Ultimately, around 14,000 operations were on the Spring 2009 survey frame.

Sample selection

For each province, three strata were defined based on the type of operation i.e. fruit only operation, vegetable only operation or fruit and vegetable operation. In each stratum, a threshold based on the total fruit acreage and on the total vegetable acreage was defined. A random sample was selected among the operations below the threshold. A census of all operations above the threshold was taken as well. Thresholds went from 2 to 10 acres depending on the province. For each stratum, the minimum sample size was 10 and the maximum design weight was 2.

Overall, the sample size was determined in order to achieve a target CV of 0.01 (1%) for total fruit area and total vegetable area at the provincial level. The final sample size for this survey was 10,254 operations.

Data collection

The Spring Fruit and Vegetable survey collects information by telephone. The regional offices of Statistics Canada conducted the survey in April 2009 using computer-assisted telephone interviews (CATI).

Response rates

Information was received from 93.8% of the sample sent to collection. Non-responding units (i.e. no-contacts and refusals) are dealt with by adjusting the initial sample weights. The assumption that the non-responding units are randomly distributed among the sample is used to justify adjusting the initial sample weights.

Edit and imputation

It is possible to implement edit procedures at the time of the interview with the introduction of the CATI system. 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. For the 2009 Spring Survey of Fruit and Vegetables, imputation was used to adjust for incomplete survey responses to the question of fruit and vegetable area. The imputation used a trend analysis of the completed questionnaires to generate averages to be used to impute the missing values.

Sampling and non-sampling errors

The statistics from the 2009 Spring Survey of Fruit and Vegetables are based on a stratified random sample of agricultural operations and, as such, are subject to sampling and non-sampling errors.

Sampling errors arise when estimates are derived from sample data and not the entire population. These errors depend on factors such as sample size, sampling design and the method of estimation. An important feature of stratified random sampling is that sampling errors can be measured from the sample itself.

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.

Estimation

Similar to the Fall Survey of Fruit and Vegetables, the spring survey data collected are weighted within each stratum in order to produce estimates representative of the population. 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.

Data quality

The estimates from the 2009 Spring Fruit and Vegetable survey are based on a probability sample of farming operations. The potential error introduced by the reduction of sample size due to non-response 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 should have been obtained from an enumeration of all farming operations with respect to the sample estimates would be less than twice the coefficient of variation. For the 2008 survey, CV’s at the Canada level range from 1.1% to 24.9%. We obtained CV’s around 10.2% at the province level. Less commonly reported variables are associated with higher, but still acceptable CV’s, usually lower than 20%. Coefficient of variation values for the published data is available upon request and is not included in this publication due to space limitations.

Revision policy

Data for the previous year are presented as final while data for the current year are considered preliminary. Data are presented initially in the June issue of Fruit and Vegetable Production (Catalogue 22-003-X) and are revised further in the February issue of the publication.

Mushroom Growers’ survey

Survey frame

The Annual Mushroom Growers’ survey is a Census of all mushroom growers in Canada. The population of mushroom growers is derived from the 2006 Census of Agriculture and supplemented by administrative data from various sources, including mushroom co-operatives.

Concepts and definitions

The survey questionnaire asks growers to identify the species of mushroom grown, the type of operation and growing medium, growing area, production and value of sales, value of investment including land, buildings and equipment and number of employees and payroll. Data are collected for both common (Agaricus) and specialty mushrooms.

Data collection

A survey questionnaire is mailed out to each grower in Canada in February of each year and the responses are mailed back directly to Statistics Canada in Ottawa. Follow-up is done by telephone. Data are edited for accuracy and completeness on return. Data inconsistencies are verified by telephone.

Estimation

Tabular data are compiled only from those growers who respond. There is no weighting for non-response. Data are imputed only for those growers who do not respond and whose continuing existence can be verified. The data imputed are obtained from the previous year's questionnaire.

For the 2008 survey, the British Columbia Ministry of Agriculture and Lands provided production data for its clients who make up most of the growers in the province. These figures are compiled with data obtained from the questionnaires returned by independent producers to make up the provincial production figures. Value data was calculated using minimum price per pound also provided by the ministry. Investment and payroll data are obtained and compiled from the returned questionnaires.

Data confidentiality

Data confidentiality is ensured under the Statistics Act, which prohibits the divulging of individual or aggregated data where individuals or businesses might be identified.

Revision policy

Data for the previous years are presented as final while data for the current year are considered preliminary.

Data quality

In British Columbia, production and value data are obtained from the Ministry of Agriculture and Lands and other sources. The value of investment and labour figures are retained and compiled with that of the independent producers. The production and value data obtained from the survey represent 57.2% of the known growers in Canada.