Commercial and Institutional Buildings Energy Use Survey (CIBEUS)

Detailed information for 2000

The objective of the survey is to produce new statistical information on the energy use of commercial and institutional buildings in Canada.

Data release - September 23, 2002

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

Description

The objective of the survey, conducted on behalf of the Office of Energy Efficiency of Natural Resources Canada (NRCan), is to produce new statistical information on the energy use of commercial and institutional buildings in Canada. Survey results will provide specialists with information on energy consumption and energy efficiency characteristics for these types of buildings across Canada. Results can also be used by the public to identify ways of reducing energy consumption in these buildings. Lastly, it will be useful to assess how well Canada is fulfilling its commitment to reducing greenhouse gas emissions in this sector.

Reference period: Calendar year

Collection period: April to July 2001

Subjects

• Energy
• Energy consumption and disposition

Data sources and methodology

Target population

The CIBEUS target population includes all buildings with an area of at least 1,000 square feet, of which 50% or more is devoted to commercial or institutional activities, located in Census Metropolitan Areas (CMAs) or Census Agglomerations (CAs) with a population of 175,000 or greater. (The threshold is a population of 50,000 or greater in the four Atlantic provinces). Examples of commercial or institutional buildings include elementary and secondary schools, colleges and universities, hospitals, inpatient health care centres, office/professional buildings, warehouses, grocers, enclosed shopping malls, other retail centres, religious-worship buildings, food services and restaurants, hotels and motels, public assembly buildings, etc. This survey does not include the residential or industrial sectors.

Instrument design

NRCan developed the survey questionnaire through a pilot-survey. The questionnaire was slightly revised to ensure compliance with Statistics Canada guidelines.

Sampling

This is a sample survey.

A full description on sampling is provided in the attached document.

• Additional documentation

Data sources

Data collection for this reference period: April 9, 2001 to July 16, 2001

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

The questionnaire is a Computer Assisted Personal Interview (CAPI) survey. Before the personal interview, research is done to obtain the name and telephone number of the person most capable of answering the survey questions.

For questions on energy consumption, respondents can choose two different ways from the three suggested methods for response. The first consists of signing a form authorizing Statistics Canada to gather information directly from the energy provider; the second asks respondents to provide the information requested themselves in a table; the third allows respondents to provide a photocopy of their energy consumption bill.

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

Error detection

Consistency edits are performed on the data for each usable record (every sufficiently complete response for a commercial building). Approximately one hundred edit rules are created. These rules ensure that all the variables have valid responses and are complete and coherent both within the questionnaire and across questionnaires.

If a building record has no responses for any of the essential questions (mainly, year of construction, square footage, activity), the records are not processed any further, and the building is considered a non-respondent.

Imputation

The data imputation approach differs based on whether the data is categoric (variables of the main questionnaire) or continuous (energy consumption). Categoric data take only specific values, while continuous data may take any numeric value.

Categoric data is imputed using a "hot deck" technique in which a donor building is chosen randomly from a group of respondent buildings that have similar characteristics. Generally, these characteristics are the type, age and size of the building.

For buildings where energy consumption is unavailable or where the energy intensity (defined as consumption in gigajoules divided by the area in square feet) for a particular source (e.g. electricity, natural gas) is less than 0.01 or more than 0.8, a respondent donor building with similar characteristics is found and the energy intensity of the donor is imputed.

A small percentage of non-respondent recordings are mass imputed. This technique is used for units in second-stage strata containing only non-respondents for which there are no similar strata in the same EA.

Estimation

Weight adjustment for non-response is based on the principle that respondent buildings can be used to represent all buildings: respondents and non respondents. To proceed with this readjustment, the sample is first subdivided into distinct non-response classes to increase the chances that the respondents and non-respondents have similar characteristics. Non-response classes correspond with second-stage strata for area frame buildings (i.e., building type, age, and size) and with first-stage strata for buildings from lists.

Before making the non-response weight adjustment, all strata in which there are no respondents or at least one non-respondent are identified in order to be paired with strata having at least one respondent (and no non-respondents). Five trials, based on building type, size and age, are held to find one stratum similar to the problem strata.

If after these trials certain problem strata are still not paired, all non-respondents from these strata are mass imputed.

At this time, no national estimates are produced for CIBEUS because the target population is limited to buildings in urban areas with a population of 175,000 or greater (50,000 in the Atlantic provinces). To provide national estimates, rural areas and less populated areas would need to be sampled as well.

Quality evaluation

Since CIBEUS is the first survey in Canada to collect information on energy use in commercial and institutional buildings, little information is available to compare the results of the survey. Some data comparisons are made to the CIBEUS pilot study, conducted on behalf of NRCan by a private consultant, and to the Commercial Buildings Energy Consumption Survey in the United States, administered by the Energy Information Administration.

Disclosure control

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.

Confidentiality analysis includes the detection of possible "direct disclosure", which occurs when the value in a tabulation cell is composed of a few respondents or when the cell is dominated by a few companies.

In CIBEUS, all estimates created with five or fewer occupational records have not been released.

Data accuracy

A full description on data accuracy is provided in the attached document.

• Additional documentation