Innovation in the Food Processing Industry Survey

Detailed information for 2018

The objective of this survey is to collect new statistical information on the nature and extent of product, process, marketing and organizational innovations in the Canadian food processing industry and on other emerging issues in the food processing industry.

Data release - December 12, 2019

• Questionnaire(s) and reporting guide(s)
• Description
• Data sources and methodology
• Data accuracy

Description

Statistics Canada conducts the Innovation in the Food Processing Industry survey in collaboration with Agriculture and Agri-food Canada to collect new statistical information in the food processing industry. The data collection focuses on:
- the nature, extent, challenges, and benefits of innovation in the Canadian food processing industry;
- use of government support programs and efforts to raise capital for innovation;
- research and developments activities in the industry;
- inedible food parts and unmarketable food products; and
- private certification systems.

An innovation is the implementation of a new or significantly improved product (good or service), or process, a new marketing method, or a new organizational method in business practices, workplace organization or external relations.

For the purpose of this survey innovations can be new to the business, but do not need to be new to one of its markets. This includes products, processes and methods that the business is the first to develop and those that have been adopted from within its enterprise, other businesses or organizations.

The Food Processing Industry is primarily involved in manufacturing and producing food for human and animal consumption, excluding beverage and tobacco manufacturing.

Results from this survey may be used by businesses and trade associations to study industry performance, government departments and agencies, including Agriculture and Agri-Food Canada, to assist in policy formation and by the academic community for research purposes.

Subjects

• Food, beverage and tobacco
• Innovation
• Manufacturing
• Science and technology

Data sources and methodology

Target population

The target population for the Innovation in the Food Processing Industry Survey is all establishments that are active, with at least one employee classified under the North American Industrial Classification System (NAICS) code 311 'Food Manufacturing' with revenues $1 million or more in the calendar year 2018. NAICS 311 includes:
- NAICS 3111 Animal and Food Manufacturing,
- NAICS 3112 Grain and Oilseed Milling,
- NAICS 3113 Sugar and Confectionary Product Manufacturing,
- NAICS 3114 Fruit and Vegetable Preserving and Specialty Food Manufacturing,
- NAICS 3115 Dairy Product Manufacturing,
- NAICS 311611 Animal (except poultry) Slaughtering.
- NAICS 311614 Rendering and Meat Processing from Carcasses,
- NAICS 311615 Poultry Processing,
- NAICS 3117 Seafood Product Preparation and Packaging,
- NAICS 3118 Bakeries and Tortilla Manufacturing and
- NACIS 3119 Other Food Manufacturing.

There are approximately 2877 in-scope establishments in the target population.

• Additional documentation

Instrument design

The Innovation in the Food Processing Industry Survey (IFPIS) 2018 uses an electronic questionnaire. The questionnaire was developed based on the 2004 IFPIS. Modified or newly added questions were mainly to incorporate emerging concepts and issues both in the innovation and food processing areas.

Statistics Canada's Questionnaire Design Resource Centre field-tested the questionnaire with potential respondents. The Centre for Special Business Projects (CSBP) reviewed and revised the IFPIS 2018 questionnaire together with Agriculture and Agri-Food Canada (AAFC) to incorporate feedback from QDRC and Investment, Science and Technology Division (ISTD) as well as from external stakeholder's comments.

Sampling

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

The survey frame was built using Statistics Canada's Business Register (BR).

The target population was stratified by the NAICS 4-digit and 6 regions (Alberta, Atlantic, BC and Territories, Ontario, Prairies and Québec).

A secure access code was mailed or emailed to all respondents inviting them to respond to the electronic questionnaire.

The final sample size was 2,217 units.

Data sources

Data collection for this reference period: 2019-02-27 to 2019-06-03

Responding to this survey is mandatory.

Data are collected directly from survey respondents.

The data were collected through an electronic questionnaire (EQ), with non-response follow-up and failed edit follow-up for priority questions.

Administrative data (T2, PD7 and Exporter data) were used for data validation and to assist with imputation only.

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

Error detection

To identify, minimize and correct errors, the following quality measures were applied to the data:

- A manual review was performed to ensure that the questionnaire coverage was as anticipated and that a complete response had been provided.

- Data were subjected to computerized edits. These edits are designed to ensure that the accounting relationships are respected and that related variables have been reported on a consistent basis.

- Unusual occurrences were queried to confirm and clarify with the respondents in question.

- If it was not possible to confirm with the respondents, ratios were calculated or Internet sources were used to validate the answer. If the values where considered non-valid, imputation was done.

Imputation

After microdata verification, a variable was created for each of the survey variables to identify those that had either failed the verification rules or had missing values. Two classes of units were created: total non-response cases and partial non-response cases. Total non-response units were treated through weighting, as the weights of responding units in the same homogenous class with respect to the propensity to respond were adjusted to represent the non-response units as well. These adjusted weights were calibrated to the strata population counts. Partial non-response units were completed using imputation.

The missing variables were imputed using the nearest neighbour imputation method. For the nearest neighbour approach, the minimax distance function is used to find the closest donor. The minimax distance function determines the closest donor as being the one with the smallest maximum absolute difference between the value of its matching variables and those of the recipient. For most variables, the matching variable used was the NAICS group. Imputation was performed within groups of units called imputation classes. These imputation classes were formed of similar size units (employment), in the same geography and in the same industry.

A minimum number of units was required within each imputation class. When imputation classes were too small, larger classes were created by combining several classes together.

To ensure internal consistency (coherence between variables of the same record), missing or incoherent variable values were imputed in sequence in which they appeared on the questionnaire. This allowed for an imputed question at one point in the questionnaire may have been used as a matching variable for a question located further along in the questionnaire.

Most imputation of survey variables was performed in an automated way using BANFF, a generalized system designed by Statistics Canada.

Estimation

The response values for sampled units is multiplied by a final calibrated weight in order to provide an estimate for the target population. Sampling error is measured using the standard error (SE) for proportions and the coefficient of variation (CV) for quantitative variables, which represents the proportion of the estimate that comes from the variability associated with it. The Generalized Estimation System G-EST is used to calculate the estimates and their associated variance (calculated using Taylor linearization). The SEs and CVs are presented in the data tables by letter-grade Quality Indicators from A to F, representing very high to very low quality.

Quality evaluation

To ensure data quality, Statistics Canada took into account and applied throughout the survey process all six dimensions of data quality control, namely, the relevance, accuracy, timeliness, accessibility, interpretability and coherence of the data collected, as per its mandate.

Statistics Canada carried out data validation for qualitative questions by ensuring the flows in the questionnaire were respected to confirm the correct population answered each question, to ensure coherence within a question and across questions in a thematic module and to ensure coherence across questions within the questionnaire.

For quantitative questions, Statistics Canada carried out two main validation processes: data coherence and data confrontation. Data coherence involved reviewing different parts of the questionnaire that covered questions which are either directly or indirectly related to ensure that responses were consistent with what was observed in practice. Data confrontation involves comparing the response from the respondent with other sources of information about either that particular respondent or other establishments within that industry.

Disclosure control

Statistics Canada is prohibited by law from releasing any information it collects that 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.

Revisions and seasonal adjustment

This methodology does not apply to this survey program.

Data accuracy

Since all estimates from the Innovation in the Food Processing Industry Survey are based on sample results, they are subject to sampling error. This error is expressed using the coefficient of variation (CV) and the standard error (SE). The CV is used for estimates expressed as a number and the SE is used for estimates expressed as a percentage. The CV and SE are included adjacent to the estimates in the published tables.

Quality code A - Excellent (Coefficient of variation - Up to 5%; Standard error for percentages - Up to 2.5%)
Quality code B - Good (Coefficient of variation - greater than 5% up to 10%; Standard error for percentages - greater than 2.5% up to 5%)
Quality code C - Average (Coefficient of variation - greater than 10% up to 15%; Standard error for percentages - greater than 5% up to 7.5%)
Quality code D - Mediocre (Coefficient of variation - greater than 15% up to 25%; Standard error for percentages - greater than 7.5% up to 10%)
Quality code E - Poor, use with caution (Coefficient of variation - greater than 25% up to 35%; Standard error for percentages - greater than 10% up to 15%
Quality code F - Not reliable, do not use (Coefficient of variation - greater than 35% ; Standard error for percentages - greater than 15%)

The Innovation in Food Processing Industry survey response rate was 74.7%