Māori descent - electoral (information about this variable and its quality)

Priority level

Priority level 1

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

Māori descent electoral is a priority 1 variable. Priority 1 variables are core census variables that have the highest priority in terms of quality, time, and resources across all phases of a census.

The priority level for Māori descent in 2013 was priority 2 (previously known as a ‘defining variable’).

Quality Management Strategy and the Information by variable for Māori descent electoral (2013) have more information on the priority rating. Note, this refers to both the census output variable and the electoral variable.

Overall quality rating for 2018 Census

High 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 this variable and have rated it as high quality. Initial Report of the 2018 Census External Data Quality Panel has more information.

Subject population

Census usually resident population count

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

How this data is classified

Māori descent electoral is a flat classification with the following categories:

1 Māori descent

2 No Māori descent

This is a separate classification from the Māori descent output variable.

No provision is made for residual categories (for example ‘not stated’) as the Māori descent electoral variable requires a ‘yes’ or ‘no’ response to the Māori descent question.

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

Question format

Māori descent electoral data is collected on the individual form (question 11 on the paper form).

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

There were also differences in the way a person could respond between the modes of collection (the online and paper forms).

On the online form:

• as it is now a priority one variable, Māori descent was a mandatory variable requiring a single response for the respondent to submit the form
• built-in routing functionality directed all individuals who were usually resident in New Zealand at the time of the census to this question.

On the paper form:

• as it is now a priority one variable, Māori descent was on the front page of the individual form
• non-response to this question and multiple responses were possible.

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 quality of the paper forms.

How this data is used

Māori descent electoral data is used in conjunction with Māori Electoral Option data (MEO) to calculate the Māori electoral population and determine the number of Māori electorates.

Population Insights use Māori descent electoral data to derive the Estimated Resident Population of Māori descent.

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.

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

Where appropriate, we used responses from the 2013 Census to replace responses which did not provide the information required for electoral purposes. When this was not possible, we used administrative data from the Department of Internal Affairs (DIA) Births Register.

It’s important to note the following caveats relating to the use of admin data for the Māori descent electoral variable:

• the Births Register could only be used to source Māori descent for individuals born after 01 September 1995, when Māori descent was added
• children of Māori descent born overseas are not included in the DIA Births Register.

Addition of admin records to the NZ Census dataset: an overview of statistical methods has more information on the timeliness of administrative data.

If it was not possible to obtain Māori descent information from the 2013 Census or the DIA Births Register, we used within household donor imputation, finding the person closest of age in the usual residence and copying their Māori descent, if the response was a ‘yes’ or ‘no’ value. If this wasn’t possible, we used 2018 Census valid iwi responses. The use of iwi contributed to less than 1 percent of data for the Māori descent electoral population and is included within the ‘Response from 2018 Census’ percentage in the data sources table.

For any records that remained coded to 'not stated' or other residual categories, we used nearest neighbour statistical imputation, which is included along with probabilistic imputation in the ‘Statistical imputation’ percentage above.

The use of these additional data sources meant that the ‘No information’ percentage is zero, as we were able to derive Māori descent electoral data for every person in the subject population.

Deriving the 2018 Māori descent electoral population provides more information on the process used in 2018.

Data sources, editing and imputation for the 2018 Census dataset (Stats NZ, in press) will provide detailed information on 2018 data processing, with a summarising comparison of the methodology for Māori descent (both electoral and census output).

Missing and residual responses

As with previous censuses, the Māori descent electoral variable does not have a ‘not stated’ or any other remaining residual category.

Data quality processes

Overall quality rating: High 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: 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.

The high proportion of data from received forms and the 2013 Census, alongside the high quality admin data contributed to the score of 0.97, determining the high quality rating.

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: High quality

Māori descent electoral data is consistent with expectations across nearly all consistency checks with some minor variation from expectations or benchmarks that makes sense due to real-world change, incorporation of other sources of data or a change in how the variable has been collected.

However, a break in the time series is apparent due to the methodological changes increasing the number of responses in the Māori descent electoral population:

• 2013 Census data, admin data and statistical imputation were used to derive Māori descent electoral for missing responses and individuals added to the census usually resident population through admin enumeration. In the 2013 Census, Māori descent electoral was imputed for substitute records that were added to the subject population.
• due to its change to a priority one variable, it was no longer possible to submit the form online without answering the Māori descent question. This added people to the Māori descent electoral population who may not have responded to the question previously.

The result of the changes in the methodology are visible when examining data across different population groups, for example:

• males of Māori descent between 20–30 years of age were more likely to be counted in 2018
• although the number is small, there has been a noticeable proportionate increase for respondents who are not of Māori descent but have Māori ethnicity. This could be partly due to there being more admin data sources available for ethnicity than for Māori descent.

Deriving the 2018 Māori descent electoral population provides further information on the changes to the methodology since the 2013 Census, as well as a comparison of counts for the Māori descent population with expectations and the time series.

Data quality: High quality

Māori descent electoral data only has minor data quality issues. The quality of coding and responses within classification categories is high. Any issues with the variable appear in a low number of cases (typically in the low hundreds).

The data quality checks for Māori descent electoral included edits for consistency within the dataset, and cross-tabulations to the SA2 level of geography.

Recommendations for use and further information

The overall quality of the data is high and is fit for electoral purpose.

However, in addition to the points discussed above, you should be aware that:

• the census data may not correspond with the Māori Electoral Roll, which is dependent on whether individuals wish to enrol as Māori voters and is restricted to those aged 18 years or older.

Contact our Information Centre for further queries relating to this variable.