Number of rooms and number of bedrooms (information about this variable and its quality)

The Number of rooms variable has changed from poor quality to moderate quality.

The consistency and coherence quality rating for number of rooms has been changed from poor to moderate quality. This has resulted in an overall quality rating increase from poor to moderate quality for the number of rooms variable. The Data quality processes section (consistency and coherence subsection) has more information.

Priority level

Priority level 3

We assign a priority level to all census variables: Priority 1, 2, or 3 (with 1 being highest and 3 being the lowest priority).

Number of bedrooms and number of rooms are priority three variables. Priority three variables do not fit in directly with the main purpose of a census but are still important to certain groups. These variables are given third priority in terms of quality, time, and resources across all phases of a census.

The census priority level for number of bedrooms and number of rooms, remains the same as 2013.

Quality Management Strategy and the Information by variable for Number of rooms and number of bedrooms (2013) have more information on the priority rating.

Overall quality rating for 2018 Census

Number of bedrooms – high quality

Number of rooms – moderate quality

Data quality processes section below has more detail on the rating for this variable.

The External Data Quality Panel has provided an independent assessment of the quality of these variables and have rated number of bedrooms as high quality and number of rooms as poor quality. 2018 Census External Data Quality Panel: Assessment of Variables has more information.

Subject population

Occupied private dwellings

‘Subject population’ means the people, families, households, or dwellings to whom the variable applies.

How this data is classified

Census number of bedrooms V1.0.0

Number of bedrooms is a flat classification with the following categories:

001 One bedroom

002 Two bedrooms

003 Three bedrooms

004 Four bedrooms

005 Five bedrooms

006 Six bedrooms

007 Seven bedrooms

008 Eight bedrooms

009 Nine bedrooms

010 Ten bedrooms

011 Eleven bedrooms

012 Twelve bedrooms

013 Thirteen bedrooms

014 Fourteen or more bedrooms

999 Not elsewhere included

‘Not elsewhere included’ contains the residual categories of ‘response unidentifiable’ alongside ‘not stated’.

Census number of rooms V1.0.0

Number of rooms is a flat classification with the following categories:

001 One room

002 Two rooms

003 Three rooms

004 Four rooms

005 Five rooms

006 Six rooms

007 Seven rooms

008 Eight rooms

009 Nine rooms

010 Ten rooms

011 Eleven rooms

012 Twelve rooms

013 Thirteen rooms

014 Fourteen rooms

015 Fifteen rooms

016 Sixteen rooms

017 Seventeen rooms

018 Eighteen rooms

019 Nineteen rooms

020 Twenty or more rooms

999 Not elsewhere included

‘Not elsewhere included’ contains the residual categories of ‘response unidentifiable’ alongside ‘not stated’.

The classifications of number of bedrooms and number of rooms in the 2018 Census are consistent with the classifications used in the 2013 and 2006 Censuses. Number of bedrooms is most often grouped for output with a top category of five or more. Most occupied private dwellings have fewer than five bedrooms.

Number of rooms is most often grouped for output with a top category of eight or more. Most occupied private dwellings have fewer than eight rooms.

The Standards and Classifications page provides background information on classifications and standards.

Question format

Number of rooms and number of bedrooms data is collected on the dwelling form (question 10 on the paper form).

Stats NZ Store House has samples for both the individual and dwelling paper forms.

The question has changed since 2013. In the 2013 Census there were two questions – one for number of bedrooms and one asking for the total number of rooms. In 2018 a single question was used that asked for a count of each individual room type (bedrooms, lounges, dining rooms, kitchens, studies, and conservatories). The individual room type counts were then used to produce the number of bedrooms and number of rooms data.

There were differences between the question format in the online and paper versions of this question.

The note text (always visible to the respondent) was different:

• online – ‘Count open-plan rooms like this: kitchen-lounge-dining is three separate rooms’.

Online also contained the following note ‘Include any caravan used as a bedroom in the count of bedrooms’.

• paper – ‘Count any open-plan rooms as separate rooms. For example, a kitchen-dining room is two separate rooms’

There were also differences in the way a person could respond.

On the online dwelling form:

• non-numeric answers, negative numbers, or responses greater than 99 were not possible.

On the paper dwelling form:

• a respondent could give a non-numeric answer, a negative number, or a number greater than 99, even though the space provided only allowed for a one- or two-digit answer. These responses were resolved by edits.

How this data is used

Outside Stats NZ

• Gives some indication of the size of a dwelling.
• Gives information on changing housing occupancy patterns over time and between various socio-economic groups.
• Estimate future demand for housing.
• Helps create the New Zealand Deprivation Index, in conjunction with other census variables (Otago University and the Ministry of Health).
• Derive household crowding measures.

Within Stats NZ

• Number of rooms and dwelling type are used to derive the rental component of the Consumers Price Index.
• Number of rooms is also used for data modelling in the Regional Household Expenditure Database. The model estimates expenditure for area units.
• Number of bedrooms has been used to calculate household crowding and output in the Housing in Auckland and greater Christchurch reports.

2018 data sources

We used alternative data sources for missing census responses and responses that could not be classified or did not provide the type of information asked for. Where possible, we used responses from the 2013 Census, administrative data from the Integrated Data Infrastructure (IDI), or imputation.

The tables below shows the breakdown of the various data sources used for this variable.

2018 Number of bedrooms – occupied private dwellings
Source	Percent
Response from 2018 Census	91.1 percent
2013 Census data	3.4 percent
Administrative data	2.6 percent
Statistical imputation	2.8 percent
No information	0.1 percent
Total	100 percent
Due to rounding, individual figures may not always sum to the stated total(s)

2018 Number of rooms – occupied private dwellings
Source	Percent
Response from 2018 Census	91.1 percent
2013 Census data	5.2 percent
Administrative data	0.0 percent
Statistical imputation	3.7 percent
No information	0.1 percent
Total	100 percent
Due to rounding, individual figures may not always sum to the stated total(s)

The ‘no information’ percentage is where we were not able to source number of bedrooms or number of rooms data for a dwelling in the subject population.

Administrative data sources

Data from the following administrative sources was used for number of bedrooms:

• Housing New Zealand Corporation
• Tenancy Bonds, Ministry of Business, Innovation and Employment.

Please note that when examining number of bedrooms or number of rooms data for specific population groups within the subject population, the percentage that is from 2013 Census data, administrative data, and statistical imputation may differ from that for the overall subject population.

Missing and residual responses

No information’ in the data sources tables is the percentage of the subject population coded to ‘not stated’. In previous censuses, non-response was the percentage of the subject population coded to ‘not stated.’

In 2018, the percentages of ‘not stated’ for number of bedrooms and number of rooms are lower than previous censuses due to the use of the additional data sources described above.

Number of bedrooms - percentage of ‘not stated’ for occupied private dwellings:

• 2018: 0.1 percent
• 2013: 5.1 percent
• 2006: 4.4 percent.

Number of rooms - percentage of ‘not stated’ for occupied private dwellings:

• 2018: 0.1 percent
• 2013: 5.8 percent
• 2006: 5.1 percent.

Responses that could not be classified or did not provide the type of information asked for (response unidentifiable) remain in the data, where we have been unable to find information from another source. In the 2018 data sources table, this residual category is included in the ‘Response from 2018 Census’ percentage.

For output purposes, as with the 2013 and 2006 Censuses, the residual category response is grouped together with ‘not stated’ and classified as ‘Not elsewhere included’.

Number of bedrooms - percentage of ‘not elsewhere included’ for occupied private dwellings:

• 2018: 0.1 percent
• 2013: 5.1 percent
• 2006: 4.5 percent.

Number of rooms - percentage of ‘not elsewhere included’ for occupied private dwellings:

• 2018: 0.1 percent
• 2013: 5.8 percent
• 2006: 5.1 percent.

2013 Census data user guide provides more information about non-response in the 2013 Census.

Data quality processes

Overall quality rating:

Number of bedrooms – high quality

Number of rooms – moderate quality

Data was evaluated to assess whether it meets quality standards and is suitable for use.

Three quality metrics contributed to the overall quality rating:

• data sources and coverage
• consistency and coherence
• data quality.

The lowest rated metric determines the overall quality rating.

Data quality assurance for 2018 Census provides more information on the quality rating scale.

Data sources and coverage:

Number of bedrooms – very high quality

Number of rooms – high quality

We have assessed the quality of all the data sources that contribute to the output for the variable. To calculate a data sources and coverage quality score for a variable, each data source is rated and multiplied by the proportion it contributes to the total output.

The rating for a valid census response is defined as 1.00. Ratings for other sources are the best estimates available of their quality relative to a census response. Each source that contributes to the output for that variable is then multiplied by the proportion it contributes to the total output. The total score then determines the metric rating according to the following range:

• 98–100 = very high
• 95–<98 = high
• 90–<95 = moderate
• 75–<90 = poor
• <75 = very poor.

Number of bedrooms

2013 Census data and admin data was mostly comparable to 2018 Census responses while data sourced through statistical imputation was moderately comparable to census responses.

The high proportion of data from received forms in comparison to the low proportion sourced from admin sources and statistical imputation contributed to the score of 0.98, determining the very high quality rating.

Quality rating calculation table for the sources of number of bedrooms data – 2018 occupied private dwellings
Source	Rating	Percent of total	Score contribution
2018 Census form	1.000	91.06	0.91
2013 Census	0.790	3.43	0.03
Admin data	0.850	2.64	0.02
Imputation
Donor’s 2018 Census form	0.600	2.44	0.01
Donor’s response sourced from 2013 Census	0.474	0.21	0.00
Donor’s response sourced from admin data	0.510	0.16	0.00
No Information	0.00	0.05	0.00
Total		100.00	0.98
Due to rounding, individual figures may not always sum to the stated total(s) or score contributions.

Number of rooms

2013 Census data was mostly comparable to 2018 Census responses while data sourced through statistical imputation was moderately comparable to census forms.

The high proportion of data from received forms in comparison to the low proportion sourced from 2013 Census data and statistical imputation contributed to the score of 0.97, determining the high quality rating.

Quality rating calculation table for the sources of 2018 number of rooms data.

Quality rating calculation table for the sources of number of rooms data – 2018 occupied private dwellings
Source	Rating	Percent of total	Score contribution
2018 Census form	1.000	91.07	0.91
2013 Census	0.790	5.17	0.04
Imputation
Donor’s 2018 Census form	0.600	2.95	0.02
Donor’s response sourced from 2013 Census	0.474	0.75	0.00
No Information	0.00	0.05	0.00
Total		100.00	0.97
Due to rounding, individual figures may not always sum to the stated total(s) or score contributions.

Data sources, editing, and imputation in the 2018 Census has more information on the Canadian census edit and imputation system (CANCEIS) that was used to derive donor responses.

Consistency and coherence:

Number of bedrooms – high quality

Number of rooms – moderate quality

Number of bedrooms in the 2018 Census is highly comparable with the 2013 and 2006 Census data, while number of rooms is moderately comparable with previous census data.

Number of bedrooms data is consistent with expectations and timeseries across nearly all consistency checks, with some minor variation from expectations or benchmarks.

• There are minor variations from the time series for the higher bedroom count categories. This is believed to be due to improvements in data quality.

Number of rooms data is mostly consistent with expectations across consistency checks. There is an overall difference in the data compared with expectations and benchmarks that can be explained through a combination of real-world change, incorporation of other sources of data, or a change in how the variable has been collected.

• The number of rooms variable shows a systematic upward shift in the number of rooms per dwelling compared with the 2013 Census.

• The increases in room counts may be partly due to the change in question structure (ie the change to asking for a count for each individual room type, instead of an overall room count per dwelling). Some respondents may have under-counted their total rooms previously.

Data quality:

Number of bedrooms – high quality

Number of rooms – moderate quality

The data quality checks for number of rooms and number of bedrooms included edits for consistency within the dataset and cross-tabulations to the national level. Regional variation was expected to be limited.

Number of bedrooms data has only minor data quality issues. The quality of coding and responses within classification categories is high. Any impact of other data sources used is minor. Any issues with the variable appear in a low number of cases (typically in the low hundreds).

Number of rooms data has various data quality issues involving several categories of the data, in particular seventeen rooms, eighteen rooms, and twenty or more rooms. These issues are mainly a result of respondent error and scanning mis-recognition and, for example:

• on the paper forms – instead of numerical responses, some respondents put lines, crosses, and dashes in the response boxes. These responses were interpreted by the processing scanner as large numbers.
• on the online forms – respondents did not always press ‘tab’ to enter the next field before entering their next room count response, resulting in two responses appearing in the boxes for one type of room and a very high count for example a response of 21 bedrooms when the intended response was two bedrooms and one lounge.

These issues have incorrectly increased the number of dwellings in the higher room count categories and decreased those in the lower categories.

Recommendations for use and further information

Number of bedrooms data is high quality and comparable with 2006 and 2013 data.

When using this data you should be aware that:

• data has been assessed as consistent at the national level. Some variation is possible at geographies below this level due to the introduction of administrative data
• non-response is lower for 2018 due to the use of other data sources and statistical imputation.

Number of rooms is moderate quality and comparable with 2006 and 2013 data.

When using this data you should be aware that:

• data has been assessed as consistent at the national level
• non-response is lower for 2018 due to the use of other data sources and statistical imputation.

Contact our Information Centre for further information about using this variable.