IVS Data Reliability
Last updated:
April 2008
The International Visitor Survey (IVS) draws on a sample of 5,200 departing international visitors per year to represent the behaviour of all international visitors to NZ. The results from the IVS are subject to measurement errors, including both sampling and non sampling errors. These errors should be considered when analysing the results from the survey.
Sampling Errors
Sampling errors arise from estimating a population characteristic by looking at only a sample of the population rather than the entire population. It refers to the difference between the estimate derived from a sample survey and the “true” value that would result if everyone in the population was surveyed.
The IVS sample includes 5,200 international visitors out of the 2.5 million international visitors to New Zealand each year.
The sampling error:
- Is different for each estimate in the survey
- Generally decreases as the sample size increases
- Depends on the size of the population
- Depends on the variability of the characteristics of interest in the population.
The total expenditure in the year ended December 2008 was $5.9 billion. This estimate has a sampling error of plus or minus 6% (at the 95% confidence level). This means that there is a 95% chance that the true expenditure estimate lies between $5.7 and $6.2 billion.
For the IVS, sampling errors of selected estimate have been modelled as a function of the estimate itself.
IVS Generalised Sampling Errors (at the 95% confidence level)
|
Size of Estimate |
Visitors |
Nights |
Expenditure |
|
5,000 |
> 50% |
> 100% |
> 100% |
|
10,000 |
37.5% |
> 100% |
> 100% |
|
25,000 |
25.1% |
> 100% |
> 100% |
|
50,000 |
18.5% |
> 50% |
> 100% |
|
100,000 |
13.7% |
> 50% |
> 100% |
|
250,000 |
9.1% |
> 50% |
100% |
|
400,000 |
7.4% |
45.9% |
> 100% |
|
600,000 |
6.2% |
39.6% |
> 100% |
|
800,000 |
5.5% |
35.7% |
> 100% |
|
1,000,000 |
5.0% |
32.9% |
> 100% |
|
1,500,000 |
4.2% |
28.4% |
> 100% |
|
2,000,000 |
3.7% |
25.6% |
> 100% |
|
2,500,000 |
|
23.6% |
> 100% |
|
20,000,000 |
|
11.1% |
> 100% |
|
40,000,000 |
|
8.6% |
> 50% |
|
50,000,000 |
|
|
> 50% |
|
80,000,000 |
|
|
46.7% |
|
100,000,000 |
|
|
41.0% |
|
200,000,000 |
|
|
27.4% |
|
400,000,000 |
|
|
18.3% |
|
600,000,000 |
|
|
14.5% |
|
800,000,000 |
|
|
12.3% |
|
1,000,000,000 |
|
|
10.8% |
|
1,500,000,000 |
|
|
8.5% |
|
6,000,000,000 |
|
|
3.8% |
Non Sampling Errors
Aside from the sampling error associated with the process of selecting a sample, a survey is also subject to a wide variety of other errors. These errors are commonly referred to as non sampling errors. Non sampling errors are defined as errors arising during the course of all survey activities other than sampling. Unlike sampling errors they are generally difficult to measure.
Some examples of non sampling errors include:
- Respondent errors
- Poor questionnaire design
- Non response
These types of errors are minimised through the use of best survey practice and monitoring.
ˆ Back to top