Quality Statement
Religious affiliation is the self-identified association of a person with a religion, denomination, or sub-denominational religious group.
A religion is a set of beliefs and practices that usually involves acknowledging a higher power, and guides people’s conduct and morals. Religious affiliation can have multiple responses as people may have affiliation with more than one religion or denomination. A denomination is a subgroup of a religion. For example, Roman Catholic is a Christian denomination.
High quality
Data quality processes section below has more detail on the rating.
Priority level 3
A priority level is assigned to all census concepts: priority 1, 2, or 3 (with 1 being highest and 3 being the lowest priority).
Religious affiliation is a priority 3 concept. Priority 3 concepts are given third priority in terms of quality, time, and resources across all phases of a census.
Priority 3 concepts are those that are:
- data that census would not be solely run for, and information about population groups that could not be captured without being in a census
- data that is important to certain groups
- data that can be used to create sampling frames for other surveys.
The census priority level for religious affiliation remains the same as 2018.
The 2023 Census: Final content report has more information on priority ratings for census concepts.
Census usually resident population count
‘Subject population’ means the people, families, households, or dwellings that the variable applies to.
Religious affiliation is classified into the following categories:
Religious Affiliation 1999 V2.1.0 – level 1 of 3
Code | Category |
---|---|
00 | No Religion |
01 | Buddhism |
02 | Christian |
03 | Hinduism |
04 | Islam |
05 | Judaism |
06 | Māori Religions, Beliefs and Philosophies |
07 | Spiritualism and New Age Religions |
08 | Other Religions, Beliefs and Philosophies |
80 | Object to answering |
99 | Residual Categories |
Religious affiliation uses a 3-level hierarchical classification with level 1 presented in the table above. Follow the link above the table to examine the classification.
Residual categories include ‘Don’t know’, ‘Religion unidentifiable’, ‘Response outside of scope’, and ‘Not stated’.
If more than one religion is reported, each response up to a maximum of four responses is counted. For respondents who provided more than four religions, more detailed responses are prioritised over vague or residual responses. Religious affiliation is a multiple response variable so the number of responses can be greater than the number of respondents.
Subsequent classification levels provide more detailed categories. Detailed religious affiliation information is collected so that responses can be coded to specific religious affiliation categories at level 3 of the classification. Where this is not possible, information is coded to level 1 or to level 2.
Since the 2018 Census, there have been some changes to the lowest level of the classification. Some religions have moved or merged categories. For example:
• Tikanga Māori moved from Anglican to Māori religions, beliefs and philosophies not further defined (nfd).
• Māori Christian moved from Māori religions, beliefs and philosophies nfd to Christian nfd.
• Māori Catholic moved from Māori religions, beliefs and philosophies nfd to Catholicism nfd.
• Iglesia Ni Cristo moved from Anglican to Church of Christ nfd.
Standards and classifications has more information on what classifications are, how they are reviewed, where they are stored, and how to provide feedback on them.
Religious affiliation is collected from the individual form (question 16 paper form).
There has been no change to the question format since the 2018 Census. There were differences in the way a person could respond between the modes of collection (online and paper forms).
On the online form:
- as-you-type functionality helped respondents provide valid, detailed responses
- if there was no match in the as-you-type list, respondents could provide their free-text response
- inconsistent responses were not possible, for example, respondents could not select ‘No religion’ or ‘Object to answering’ and provide a text response.
On the paper form:
- respondents could skip the question or provide an invalid response.
Data from the online forms may therefore be of higher overall quality than data from paper forms. However, processing checks and edits were in place to improve the quality of the paper form data.
Stats NZ Store House has samples for both the individual and dwelling paper forms.
Religious affiliation is a demographic variable, various uses include:
Data-use outside Stats NZ:
- to assess the need for various types of religion-related or religion-sponsored services, including those of churches, mosques, temples, and religious schools
- by churches, mosques, temples, and religious groups to understand the needs of their communities
- by researchers and religious organisations to trace the changes in values and belief systems in New Zealand society, and as an explanatory variable for studies on subjects such as marriage formation and dissolution
- to provide religious demographic data to inform better policy making, as recommended by Recommendation 32 of the Royal Commission of Inquiry into the Attack on Christchurch Mosques on 15 March 2019.
Data-use by Stats NZ:
- as part of measuring cultural diversity along with the ethnicity, birthplace, years since arrival in New Zealand, and languages spoken variables.
Alternative data sources were used for missing census responses and responses that could not be classified or did not provide the type of information asked for.
The table below shows the distribution of data sources for religious affiliation.
Data sources for religious affiliation data, as a percentage of census usually resident population count, 2023 Census | ||
---|---|---|
Source of religious affiliation data | Percent | |
2023 Census response | 84.4 | |
Historical census | 9.2 | |
2018 Census | 6.1 | |
2013 Census | 3.0 | |
Admin data | 0.0 | |
Deterministic derivation | 0.0 | |
Statistical imputation | 6.5 | |
Probabilistic imputation | 3.1 | |
CANCEIS(1) donor’s response sourced from 2023 Census form | 2.9 | |
CANCEIS donor’s response sourced from 2018 Census | 0.3 | |
CANCEIS donor’s response sourced from 2013 Census | 0.2 | |
CANCEIS donor’s response sourced probabilistic imputation from members of UR household | 0.1 | |
No information | 0.0 | |
Total | 100.0 | |
1. CANCEIS = imputation based on CANadian Census Edit and Imputation System Note: Due to rounding, individual figures may not always sum to the stated total(s). |
Where appropriate, responses are used from the 2018 and 2013 Censuses to replace missing or residual responses.
If it was not possible to obtain religious affiliation data from historical census data, probabilistic imputation was used. This is where the religious affiliation of the person closest in age in the same household was used to fill in missing information on religious affiliation for the record. Statistical imputation was used for any records that remained coded to ‘Not stated’ or other residual categories.
Editing, data sources, and imputation in the 2023 Census describes how data quality is improved by editing and how missing and residual responses are filled with alternative data sources (admin data and historical census responses) or statistical imputation. The paper also describes the use of CANCEIS (the CANadian Census Editing and Imputation System) that is used to perform imputation.
Missing and residual responses represent data gaps where respondents either did not provide answers (missing responses) or provided answers that were not valid (residual responses).
Where possible, alternative data sources have been used to fill missing and residual responses in the 2023 and 2018 Censuses.
Percentage of ‘Not stated’ for the census usually resident population count:
- 2023: 0.0 percent
- 2018: 0.0 percent
- 2013: 7.1 percent
For output purposes, the residual category responses are grouped with ‘Not stated’ and are classified as ‘Not elsewhere included’.
Percentage of ‘Not elsewhere included’ for the census usually resident population count:
- 2023: 0.0 percent
- 2018: 0.0 percent
- 2013: 8.2 percent
Overall quality rating: High
Data has been evaluated to assess whether it meets quality standards and is suitable for use.
Three quality metrics contribute to the overall quality rating:
- data sources and coverage
- consistency and coherence
- accuracy of responses.
The lowest rated metric determines the overall quality rating.
Data quality assurance in the 2023 Census provides more information on the quality rating scale.
Data sources and coverage: High quality
The quality of all the data sources that contribute to the output for the variable were assessed. To calculate the 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:
- 0.98–1.00 = very high
- 0.95–<0.98 = high
- 0.90–<0.95 = moderate
- 0.75–<0.90 = poor
- <0.75 = very poor.
The high proportion of data received from 2023 Census forms, alongside the high quality of alternative data sources, resulted in a score of 0.96, leading to the quality rating of high. Refer to the methodology paper for an explanation of how data sources were prioritised.
Data sources and coverage rating calculation for religious affiliation data, census usually resident population count, 2023 Census | |||
---|---|---|---|
Source of religious affiliation data | Rating | Percent | Score contribution |
2023 Census response | 1.00 | 84.36 | 0.84 |
2018 Census | 0.87 | 6.13 | 0.05 |
2013 Census | 0.76 | 3.02 | 0.02 |
Probabilistic imputation | 0.80 | 3.07 | 0.02 |
CANCEIS(1) nearest neighbour imputation | 0.40 | 3.41 | 0.01 |
No information | 0.00 | 0.00 | 0.00 |
Total | 100.00 | 0.96 | |
1. CANCEIS = imputation based on CANadian Census Edit and Imputation System
Note: Due to rounding, individual figures may not always sum to the stated total(s) or score contributions. |
Consistency and coherence: High quality
Religious affiliation data is consistent with expectations across nearly all consistency checks, with some minor variation from expectations or benchmarks which makes sense due to real-world change, incorporation of other sources of data, or a change in how the variable has been collected.
Where there is minor variation from expectations, this is due to relatively high proportions of alternatively sourced data for Māori religions, beliefs and philosophies, and the ability of type and number of religious affiliations to change over time.
Accuracy of responses: Very high quality
Religious affiliation data has no data quality issues that have an observable effect on the data. The quality of coding is very high. Any issues with the variable appear in a very low number of cases (typically less than a hundred).
Improvement in scanning repair for paper forms and increased response rates have reduced the number of responses needing to be sourced from alternative sources.
Religious affiliation data can be used in a comparable manner to the 2018 and 2013 Censuses.
When using this data, users should be aware of the following:
- Māori religions, beliefs and philosophies have the lowest rate of responses from census forms and the highest rate of alternative data sources. It is recommended data users familiarise themselves with the proportion of alternatively sourced data.
- Historic census data was used as an alternative data source for religious affiliation. Although people may have changed their religion(s) since the 2018 or 2013 Censuses, these are still considered higher quality data than CANCEIS imputation, or a residual or missing response.
Comparisons to other data sources
Census is the only comprehensive source of information about religious affiliation data. Comparing 2023 Census data with other data sources should be done with care.
To assess how this concept aligns with the variables from previous censuses, use the links below:
- Religious affiliation – 2018 Information by variable
- Religious affiliation – 2013 Information by variable
Contact our Information centre for further information about using this concept.