6. Dwelling Classification Survey

6.1 Introduction

As described in Section 5.7, census data are adjusted for occupied non-respondent dwellings. The number of people living in these dwellings is estimated by the Dwelling Classification Survey (DCS). These estimates are used in census processing to specify how many people should be imputed during whole household imputation (WHI). The second objective of the DCS is to measure three types of dwelling classification error.

One of the potential sources of error in a census is the misclassification of dwellings. When a census questionnaire is not returned from a household, the enumerator has to determine if the dwelling is occupied or not. Two types of classification error can occur. First, an occupied dwelling can be incorrectly classified as unoccupied. Census population undercoverage is the result of this classification error because the people living in the dwelling will not be on the census database. Second, an unoccupied dwelling can be incorrectly classified as occupied. When this error occurs, no questionnaire will be received for this dwelling and it will be subject to non-response follow-up (NRFU) as described in Section 4.5. If the NRFU fails to correct the dwelling's classification to unoccupied, the dwelling will continue to be considered as a non-respondent dwelling and therefore subject to imputation. This would add persons to the census database when, in fact, no one is living at that dwelling. That is, this classification error results in population overcoverage. Estimates from the DCS are used to adjust census data for both of these coverage errors.

The third component of dwelling classification error measured by the DCS is the error incurred when marginal dwellings or dwellings under construction are classified in error as dwellings. Since the dwelling would be classified as unoccupied, no population overcoverage results as only occupied dwellings can be classified as non-respondent dwellings and therefore be subject to imputation. However, there is dwelling overcoverage. Census data are not adjusted for these dwellings so census estimates of the housing stock include some degree of overcoverage.

Top of Page

6.2 Methodology

6.2.1 Stratification and sample selection

The DCS target population consisted of all dwellings classified as either unoccupied or non-response dwellings, excluding dwellings in collective collection units (CU), canvasser CUs and Indian reserves CUs. These areas were excluded because of cost and operational considerations.

The sample size for the DCS was set at 1,729 CUs. The sampling frame consisted of all self-enumeration CUs. Consequently, Nunavut has no in-scope CUs and hence the DCS is not conducted in Nunavut. The sample design was as follows. First, all in-scope CUs in the Yukon (50 CUs) and in the Northwest Territories (19 CUs) formed one stratum. All of these CUs were selected for the DCS sample with certainty. All of the CUs in Prince Edward Island formed a second stratum from which a simple random sample of 44 CUs was selected.

The remaining CUs were grouped into urban and rural strata. A CU was considered urban if it initially had been part of a census metropolitan area (CMA) or a census agglomeration (CA) that had 40,000 or more occupied dwellings. Further, all of the CUs within a crew leader district (CLD) were considered urban if more than 50% of the CUs in the CLD were urban. All of the remaining CUs formed the rural strata. Urban CUs were stratified by CMA and CA. A simple random sample of at least five CUs was selected within each stratum. From past census data, it was determined that five CUs was an appropriate workload for an interviewer. There were 1,092 urban CUs in the sample. In order to control field costs, the rural sample was chosen to be geographically close. This was done via a two-stage stratified random sampling design. In the first stage, CLDs were selected within each province. In the second stage, five CUs were selected from each of the selected CLDs. There were 637 rural CUs in the sample.

Sub-sampling of dwellings within a sampled CU was invoked when the number of unoccupied and non-response dwellings exceeded a maximum dwelling parameter, which was 100 in mail-out and list/leave CUs and 200 in seasonal CUs. Sub-sampling of in-scope dwellings occurred in 84 CUs. Otherwise, all unoccupied dwellings and non-response dwellings in the sampled CUs formed the DCS sample of dwellings. A total of 37,493 unoccupied and 7,557 non-response dwellings were sampled in 2011. Table 6.2.1 shows the distribution of the sample by province and territory.

6.2.2 Field interviews

Sampled dwellings in the sampled CUs that were classified as unoccupied on Census Day or classified as occupied but for which no census form had been returned, were to be checked again in late June or early July 2011 to determine the true occupancy status of the dwellings on Census Day. A DCS questionnaire was used for this purpose.

The timing of this operation was left to the discretion of each regional office (RO). In order to determine occupancy status and collect other information, enumerators were instructed to contact current occupants, neighbours, landlords, or any other person with some knowledge about the dwelling. Up to three contact attempts were made for each dwelling. If the dwelling was found to have been occupied on Census Day, the number of occupants on Census Day was also obtained.

Top of Page

6.2.3 Processing, coding and editing

All completed questionnaires were sent to Ottawa for processing.

Some preliminary edits and general grooming were then performed before the questionnaires were sent for data capture (key entry). Once data capture was completed, the questionnaires were subjected to an extensive set of consistency edits. The questionnaires failing edits were examined manually in order to resolve the inconsistencies.

At this point in processing, the unoccupied dwellings and the non-response dwellings in the sample were separated and the classification of these dwellings was confirmed against final census listing. The questionnaires completed for each sampled CU were matched to the final census listing of unoccupied dwellings. If a match could not be found, the sampled dwelling was discarded and no further processing was required. Dwellings listed as unoccupied on the census list for which no DCS questionnaire was received were considered as total non-response and went on to the next step of processing. Similarly, the final census listing of all dwellings for which a census questionnaire was not received was used to establish which of the DCS dwellings for which a DCS questionnaire was not received would be considered as total non-response.

Total non-response was addressed by a weighting adjustment while item imputation was used for item non-response. The procedure was the same for the unoccupied dwellings and non-response dwellings. When there was no information for a dwelling, the design weights of the respondents were adjusted to account for the design weight of the non-respondents. The adjustment was done separately by geographic post-stratum, i.e., for each of the Montréal, Toronto and Vancouver CMAs, for the remaining urban areas in each province and territory, and for the rural areas for each province and territory. Item non-response for occupancy status, number of usual residents, and dwelling type was addressed by imputation. Occupancy status was imputed first and then used in the imputation of the other variables. Design weights were then adjusted so that the sum of the adjusted weights for each geographic post-stratum equaled the number of unoccupied/non-response dwellings.

6.2.4 Census whole household imputation

Once the DCS estimates were produced, census data were adjusted for non-respondent dwellings and for occupied dwellings classified in error as unoccupied. This was done in the whole household imputation (WHI) step of census processing as follows for the non-respondent dwellings; unoccupied dwellings were handled in a similar but simpler fashion. First, all the non-respondent dwellings within a DCS geographic post-stratum were identified. Second, any non-respondent dwelling for which field collection had obtained the number of usual residents was deemed to be occupied and assigned the recorded household size. Finally, an additional number of non-respondent dwellings was randomly selected and imputed as occupied. The selection was done so that the final number of non-respondent dwellings converted to occupied dwellings in the post-strata equaled the DCS estimate of occupied dwellings in the non-respondent dwelling universe. This process resulted in all private dwellings on the census database being classified as either occupied or unoccupied.

A procedure, constrained on the DCS estimates by post-stratum and household dwelling size was used to impute the household dwelling size and other variables for the selected non-respondent dwelling. Household size was determined by randomly selecting a dwelling from all dwellings that had completed a census questionnaire in the same CU. The complete record from this donor household was then assigned to the non-respondent dwelling. If no donor was found, then only a household size was assigned.

More information on WHI can be found in Dick (2013).

Top of Page

6.3 Estimates

Census data are adjusted for non-respondent dwellings and for occupied dwellings that are classified in error as unoccupied using DCS estimates. The estimates are given in Sections 6.3.1.1 and 6.3.2. Census data are not adjusted for marginal dwellings or dwellings under construction that are classified in error as dwellings. Section 6.3.1.2 presents estimates of the number of marginal dwellings and dwellings under construction that are classified in error as dwellings and therefore erroneously included in the housing stock.

6.3.1 Unoccupied dwellings

6.3.1.1 Occupied dwellings misclassified as unoccupied

Table 6.3.1.1.1 gives the estimated number of dwellings classified as unoccupied that should have been classified as occupied, and the corresponding error rate for unoccupied dwellings by urban and rural,^Footnote1 and by province and territory. For comparison, Table 6.3.1.1.2 gives the same estimates for the 2006 Census. Table 6.3.1.1.3 gives the estimated number of persons living in occupied dwellings misclassified as unoccupied. Table 6.3.1.1.4 shows the number of households and persons added to the initial 2011 Census counts to adjust for these misclassifications.

Table 6.3.1.1.1 shows that 13.8% of all dwellings classified as unoccupied were actually occupied. This is a decrease from 17.4% found in 2006. The misclassification of dwellings was more prevalent in urban areas (19.3%) than in rural areas (6.5%). Both areas show decreases from 2006. Decreases in the misclassification rates occurred for all provinces except New Brunswick where it increased.

Among the provinces and territories, British Columbia had the highest misclassification rate, 15.9%, followed by Alberta, 15.2%, Quebec, 14.9%, Ontario, 14.8% and the Yukon, 13.1%. The rates for the other provinces and territories ranged from 11.2% for New Brunswick to 5.7% for Newfoundland and Labrador and Prince Edward Island.

Because of error in the initial classification of dwellings, approximately 151,152 households were not enumerated in the 2011 Census. This is the number of households added to the census during WHI. Table 6.3.1.1.4 shows the number of households and persons added to adjust for occupied dwellings misclassified as unoccupied.

Top of Page

6.3.1.2 Housing stock overcoverage

Table 6.3.1.2 shows the estimated number of unoccupied dwellings not in the housing stock and the corresponding error rate for unoccupied dwellings for various geographic areas. No adjustments were made to the census database to account for dwellings not in the housing stock that were erroneously classified as unoccupied.

The enumeration of unoccupied dwellings that fall outside the housing universe results in overcoverage of dwellings. Dwellings are considered to be outside the housing universe if they are used for commercial purposes, if they are not habitable year round, or if they are double counted in the census. This last situation can happen when the dwelling appears to have two addresses associated with it, or when two questionnaires are mistakenly returned for a dwelling which no longer contains a separate apartment within it.

The Dwelling Classification Survey estimates of the number of unoccupied dwellings misclassified as dwellings are not used to adjust the census database because of the degree of subjectivity associated with classifying a dwelling as suitable for year-round occupancy. A dwelling must have a source of heat or power and provide complete shelter from the elements to be considered as suitable. It is sometimes difficult to tell whether or not a dwelling is habitable for example, when the dwelling is a cottage; when the dwelling is under construction and almost complete; or when the dwelling has deteriorated.

Dwellings outside the housing stock account for 8.4% of all dwellings classified as unoccupied. Among the provinces and territories, the incidence of dwellings outside the housing stock having been classified as unoccupied ranges from 3.1% in Prince Edward Island to 24.8% in the Yukon. The problem is more prevalent in urban areas (10.3%) than rural areas (5.8%).

Dwellings actually outside the housing stock represent 0.6% of all private dwellings in the 2011 Census. This is a decrease from the 2006 error rate of 2.5%. Among the provinces and territories, the error ranges from a rounded low of 0.0% in the Northwest Territories to a high of 1.1% in British Columbia.

6.3.2 Non-response dwellings

6.3.2.1 Persons added in non-response dwellings

Table 6.3.2.1.1 gives the estimated number and rate of occupied non-response dwellings in the census by urban (> 50,000) and rural and by province and territory. Table 6.3.2.1.2 gives the number of persons estimated by the DCS to be living in these non-response dwellings while Table 6.3.2.1.3 gives the same information for the 2006 DCS.

Table 6.3.2.1.1 shows that 69.2% of all dwellings classified as non-response were actually occupied. The census did a slightly better job of classifying non-response dwellings in urban areas (71.7%) than it did in rural areas (59.8%). At the province and territory level in 2011, the Northwest Territories had the highest rate of correctly classified non-response dwellings at 87.4%, while Prince Edward Island had the lowest rate at 56.1%.

Table 6.3.2.1.2 shows the number of non-response dwellings in the 2011 Census, and gives the number of persons added in those dwellings through the DCS. Table 6.3.2.1.3 shows the same data from the 2006 DCS. In 2011, a total of 443,098 persons were added to the census in 220,181 dwellings. The comparable 2006 numbers are 571,521 persons in 259,894 dwellings.

Top of Page

6.3.2.2 Dwellings not in the housing stock misclassified as non-response

Table 6.3.2.2 shows the 2011 Census dwelling classification error from dwellings erroneously classified as non-response because they should not have been included in the housing stock. Section 6.3.1.2 provides the definition of dwellings outside of the housing universe and comments on the difficulty in determining whether a dwelling should be included in the housing stock. At the national level, dwellings outside the housing stock account for 4.5% of all non-response dwellings. The error rate is similar in rural areas (4.3%) and urban areas (4.6%). For provinces and territories, the incidence of dwellings outside the housing stock having been classified as non-response ranges from 2.1% in Saskatchewan to 5.7% in British Columbia. At the national level, non-response dwellings outside the housing stock account for 0.1% of all private dwellings. This error is 0% in the Northwest Territories, rounded to 0% in Saskatchewan and rounded to 0.1% in all other provinces and territories.