Quarterly Rent Statistics (QRS)

Detailed information for first quarter 2025

This program produces experimental estimates of the asking rent of available rental units listed on major rental platforms in Canada to provide a detailed and up-to-date portrait of rental market prices in Canadian Census Metropolitan Areas (CMAs).

Data release - June 25, 2025

• Description
• Data sources and methodology
• Data accuracy

Description

This program produces experimental estimates of the asking rent of available rental units listed on major rental platforms in Canada to provide a detailed and up-to-date portrait of rental market prices in Canadian CMAs. These statistics cover apartments by number of bedrooms and single rooms available for rent.

Collection period: Ongoing

Subjects

• Families, households and housing
• Housing and dwelling characteristics

Data sources and methodology

Target population

The target population consists of rental units, that is, private dwellings or sets of living quarters in a private dwelling that are for rent. Quarterly rent statistics cover selected census metropolitan areas (CMAs) in the 10 provinces. A unit is considered in scope if it is advertised for rent at any point during the quarter. The target population excludes subsidized rental units, lease transfers, short-term rental units and non-residential units.

Instrument design

This methodology type does not apply.

Sampling

This methodology does not apply.

Data sources

Data are extracted from administrative files.

The asking rent data sources are monthly extractions of active listings from major rental platforms in Canada, including but not limited to the Rentals.ca Network and Zumper.

Error detection

Duplicates within and across platforms are checked and corrected. To remove outliers, the sigma gap method is applied. This method identifies atypical values while preserving legitimate high rents. To account for local variations and different rental unit types, it is applied within each subdomain when there are enough records to capture the underlying distribution. Internal consistency of records for common fields (i.e. rental unit attribute) is verified and adjusted when required.

Imputation

Imputation is not performed on the dataset, and missing values are excluded.

Estimation

The inverse probability weighting method is used to adjust the representation of online listings by accounting for the likelihood of their inclusion in the sample. This likelihood is estimated through a logistic regression model that incorporates factors, such as geography, dwelling characteristics, and local socioeconomic trends, that influence whether a listing appears in the captured online listing data. The model parameters are estimated by maximizing the pseudo-log-likelihood function and require auxiliary information from a reference probability survey that describes the entire target population. Auxiliary data are used as the reference probability distribution source. No weighting is applied to the "room" category, because there is no representative auxiliary data available.

Quality evaluation

To evaluate the quality and representativeness of the estimates, the validation process for the asking rent estimates is approached from multiple perspectives, including comparisons with other sources. These comparisons are undertaken at several geographic levels, with specific attention to CMAs where sufficient data are available from multiple sources. The Seasonal-Trend decomposition using LOESS (STL) is used to evaluate the stability of the trend and potential outlier estimates.

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 type does not apply to this statistical program.

Data accuracy

Even if the data from major rental platforms in Canada are available, the accuracy may be affected by coverage errors, as the QRS program does not cover all online rental platforms, nor does it cover offline advertisements. Response errors and processing errors can also arise from incorrect or incomplete information from the data provider, such as missing addresses, missing unit types or duplicate listings. Measures are put in place to mitigate the effect of these errors.

Sampling errors associated with estimates are measured using coefficients of variation as a function of the standard error and the rent estimate.

Some estimates are suppressed due to insufficient number of observations in the domain or high variability in the values. While asking rent estimates are adjusted for distributional representation of rental unit types, they are not adjusted for changes in quality. This means that variations in the asking rent levels can be influenced by changes in quality attributes of rental units, such as the presence of utilities, upgraded finishes or parking.

Non-sampling error
Non-sampling errors are essentially coverage errors, listing errors and selection bias. Because listings are not selected randomly, the dataset may overrepresent certain types of units and underrepresent others. The mechanism that determines whether a rental unit appears in the observed online listing dataset is unknown.