Health - Health measures for children by DHB, ethnicity and sex 2011–2014

Ministry of Health


Prevalence: The percentage of the population who have the condition or outcome of interest, at one point in time.

95% confidence interval: Indicates the uncertainty in a prevalence estimate due to collecting data from only a sample of the population. For example, a confidence interval of 18.0-32.0 means we are 95% confident that the true population prevalence lies between 18.0 and 32.0.

P-value: When we observe a difference between two groups, the difference could be a real difference or it could be due to chance. The p-value is the probability of obtaining the observed difference (or a bigger difference) by chance. For example, if 16.2% of adults surveyed in 2013/14 and 14.9% of adults surveyed in 2006/07 had been diagnosed with arthritis, then a p-value of 0.01 shows that there is a 1% chance of observing a difference of at least 1.3 percentage points, even if there was no change in the population prevalence of arthritis between 2006/07 and 2013/14.

Statistically significant: In this report, we often compare the prevalence estimates for two groups. Following usual practice, we have said that a difference between the groups is statistically significant if the p-value is less than 0.05 (that is, a 5% significance level). A statistically significant difference is likely to represent a real difference in the underlying populations, rather than representing random variation due to the sampling process.

Age-standardisation: A statistical procedure that facilitates comparisons between two or more population subgroups that may have different age structures. Age-standardisation adjusts the subgroup prevalences as if each subgroup had the same (standard population) age structure.

Adjusted rate ratio: Rate ratios are used to compare the results for different population groups. A rate ratio tells us how many times larger or smaller the rate is for the group of interest (e.g., Māori) compared with the reference group (e.g., non-Māori). Adjusted rate ratios above 1 show that the indicator is more likely in the group of interest than in the comparison group; adjusted rate ratios below 1 show the indicator is less likely.

Limitations of the data

These tables provide results for data collected from 13,742 children from July 2011 to June 2014 for all 20 DHBs.
The survey results rely on self-reported information, except for obesity (which uses measured height and weight).

Even with pooling three years of data, the sample sizes for some of the smaller DHBs are relatively small. For example, the results for the Wairarapa DHB are based on survey responses from around 670 adults and 200 children. This can mean that there is more uncertainty in the results for smaller DHBs, as shown by the 95% confidence intervals for the prevalence estimates. For example, the prevalence of obesity for adults in the Wairarapa DHB is estimated to be 32.1%, with a 95% confidence interval of 27.2% to 37.5%. Small sample sizes can also mean that there needs to be a large difference between the DHB prevalence and the national prevalence to be confident that there is a true difference. Similarly, the sample size for Māori is very small in some DHBs, making differences between Māori and non-Māori hard to detect.

Data provided by

Ministry of Health

Dataset name

New Zealand Health Survey: 2011-14 results for children for all 20 DHBs


How to find the data

At URL provided, select 'Data tables: 2011-14 results for children (aged 0 to 14 years) for all 20 DHBs' from the right-hand column. To view all raw data, right click on any tab at the bottom of the Excel screen and select 'Unhide'.

Import & extraction details

File as imported: New Zealand Health Survey: 2011-14 results for children for all 20 DHBs

From the dataset New Zealand Health Survey: 2011-14 results for children for all 20 DHBs, this data was extracted:

  • Sheet: Data DHB M NM
  • Range: F2:J5038
  • Provided: 25,185 data points

Dataset originally released on:

May 07, 2015