Monthly Survey of Large Retailers (LMR)

Status:
Active
Frequency:
Monthly
Record number:
5027

The Monthly Survey of Large Retailers (LMR) provides a breakdown of national retail sales on the basis of commodities for a panel of about 80 large retail enterprises. Sales data for more than 100 commodities are available on a monthly basis.

Detailed information for May 2014

Data release - July 17, 2014

Description

The Monthly Survey of Large Retailers (LMR) provides a breakdown of national retail sales on the basis of commodities for a panel of about 80 large retail enterprises. Unadjusted sales data for more than 100 commodities are available on a monthly basis.

The survey covers Canada's largest food, clothing, home furnishings, electronics, sporting goods, and general merchandise retailers (department stores are included). Together these retailers represent about 35% of total annual retail sales after excluding recreational and motor vehicle dealers.

This monthly commodity survey was developed for the retail community in response to their expressed need for timely, ongoing commodity information for decision-making purposes. It replaced Statistics Canada's monthly Department Store Sales and Stocks Survey (record number 2408) which provided commodity information about the sales of department stores. (The name of survey #2408 was changed to "Monthly Retail Trade Survey (Department Store Organizations)" as of the January 2003 reference period.) In order to maintain and improve the usefulness of Statistics Canada's monthly retail commodity program for retailers and to provide them with estimates for determining market share, coverage was expanded to include additional very large key retailers. The revised survey (the Monthly Survey of Large Retailers) was introduced in January 1997.

Estimates from the LMR are summed over the quarter and integrated with the larger Quarterly Retail Commodity Survey (QRCS - record number 2008) that is designed to provide commodity estimates for all of Retail Trade. The LMR and the QRCS use the same questionnaire.

Reference period:
month
Collection period:
The month following the reference month

Subjects

  • Retail and wholesale
  • Retail sales by type of product

Data sources and methodology

Target population

The LMR surveys a panel of about 80 large retail enterprises representing Canada's largest food, clothing, home furnishings, electronics, sporting goods, and general merchandise retailers.

Instrument design

The questionnaires were developed and tested in the field in pre-tests and focus groups in both official languages. The resulting data have been determined to provide accurate measures of the concepts being surveyed.

Sampling

At the outset of the survey, a panel of approximately 80 large retail enterprises was chosen due to their significant contribution to the retail food, clothing, home furnishings, electronics, sporting goods, and general merchandise sectors. This panel has been followed since the beginning of the survey.

The list of retailers included in the Monthly Survey of Large Retailers is available to the public.

Data sources

Responding to this survey is mandatory.

Data are collected directly from survey respondents.

Data collection, data capture, preliminary edit and follow-up are performed by Head Office staff. Respondents are given a choice of collection methods: mail or telephone. Approximately 80% are by mail and 20% are by telephone. They also have the choice to report commodity data in dollars or as a percentage of total sales and receipts. Telephone follow-up is conducted to resolve edit problems with mail-back questionnaires and to collect data from respondents who have not returned the questionnaire.

About 95% of respondents report on a monthly basis. However, respondents can report quarterly or annually if it has been determined that a respondent's commodity distribution is stable over the course of a year.

Commodity Indexes were developed to assist interviewers and respondents in choosing the most appropriate commodity codes to classify the type of retail sales being reported. There are two Indexes -- one is organised by commodity code and the other one is an alphabetical listing by commodity.

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

Error detection

During data collection, on-line edits are performed to check for consistency between the current period's data and the last period's data. If the commodities reported for the current period are inconsistent with the previous period, the data is verified with the respondent. There are edits to ensure that the captured information is numerically valid and that all data fields are completed. Edits are also in place to ensure that the reporting period dates are valid.

Edit reports are produced each month. Edits are in place to check if the sum of the individual commodities adds to the total sales reported, and to notify of large fluctuations in sales from period to period. There are also checks in place to make sure that the total value of all commodities reported on the LMR by a company are in line with the total sales collected on the Monthly Retail Trade Survey (MRTS - #2406) by that same company.

Subject matter experts investigate these edit failures and correct the obvious errors or contact the respondent for clarification.

Imputation

Commodity values are imputed for questionnaires for which data are not received, and for questionnaires with missing or inconsistent fields that are identified during the editing process.

Questionnaires for which data has not yet been received, manual imputation based on historical data (using the same month of the previous year, or the previous month) is used whenever possible. For others requiring imputation, or when historical data is not available, an automated ratio imputation system using a donor pool is used. This method uses a ratio of the commodity value versus the total sales calculated from the donor pool, and applies it to the questionnaire in question to determine the imputed commodity value.

The first step in the ratio imputation process involves defining imputation groups. An imputation group consists of a set of homogeneous companies. A value imputed to a commodity will be derived from the values of respondents belonging to the same imputation group. In other words, efforts are made to use companies with similar profiles in the imputation process. Respondents that are considered to be outliers (either due to extremely large fluctuations in their commodity distributions when compared to their previous data, or due to unusual commodity sales for the type of store) are excluded from the group. Once the donor pool has been decided and a ratio has been determined, the commodity is imputed using the ratio to the company's total sales.

Since imputation does not ensure that the parts will add up to the totals, it is followed by a prorating step to ensure that all parts add up to the corresponding totals.

Quality evaluation

Prior to the data release, combined survey results are analyzed for comparability; in general, this includes a detailed review of individual responses, general economic conditions, and historical trends.

The data is examined at a macro level to ensure that the long-term trends make sense when compared to publicly available information in media reports, company press releases, etc. Large fluctuation in year-over-year sales and inventories are analysed to determine if they are in error or if they accurately reflect retail activity. Subject matter officers follow up with the company to confirm the data and to document reasons for large fluctuations in sales or inventories.

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.

Revisions and seasonal adjustment

Revisions in the raw data are required to correct known non-sampling errors. These revisions mainly stem from respondent data received after the release date.

Raw data are revised, on a monthly basis, for the month immediately prior to the current reference month being published. For example, when data for December are being published for the first time, there will also be revisions, if necessary, to the raw data for November. In addition, revisions are made once a year, with the release of the February data for the first time, for all months in the previous year. The purpose is to correct any significant problems that have been found that apply for an extended period. The actual period of revision depends on the nature of the problem identified, but generally does not exceed one year.

Data accuracy

The methodology of this survey has been designed to control errors and to reduce the potential effects of these. The panel for the Monthly Survey of Large Retailers was selected based on their sales size and contribution to the food; clothing; furniture, appliance and electronics; general merchandise; and sporting goods industries of retail trade; thus, due to the survey design, sampling errors are not an issue. However, the results of the survey remain subject to non-sampling errors. For example, these types of errors can occur when a respondent provides incorrect information, or does not answer certain questions; when a company in the panel is omitted or covered more than once; or when errors such as coding or capture errors occur in the data processing. While the impact of non-sampling errors is difficult to evaluate, certain measures such as response and imputation rates can be used as indicators of the potential level of non-sampling error.

Non-sampling errors are difficult to ascertain. However, actions have been taken to reduce non-sampling errors to a minimum. One area that can be measured is the level of non-response. The response rate is the percentage of the sample for which a response was expected, and was received. The response rate for the LMR is usually in the 94% to 96% range. A second indicator of non-sampling error is the imputation rate. The imputation rate is the proportion of the estimated sales which comes from imputed data. The imputation rate varies from commodity to commodity, but in general less than 15% of LMR companies use any imputed data.

Documentation