Stats NZ has a new website.

For new releases go to

www.stats.govt.nz

As we transition to our new site, you'll still find some Stats NZ information here on this archive site.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Household Use of Information and Communication Technology: 2012
Embargoed until 10:45am  –  22 April 2013
Data quality

Period-specific information
This section has information that has changed since the last release.

General information
This section has information that does not change between releases.

Period-specific information

Reference period 

The reference period for the 2012 Household Use of ICT Survey was the September quarter 2012. Responses were collected between July and September, and most questions have a recall period of 12 months.

The reference period for the 2006 and 2009 Household Use of ICT Surveys was the December quarter. The change in quarter has minimal effect on most questions, due to the 12 month recall period. However, for estimates referring to online spending, where the recall period was four weeks, there is likely to be some effect. The percentage change in online spending is likely to be an underestimate, as the Retail Trade Survey shows a higher sales volume in the December quarter. 

Sampling error 

Sampling error can be measured, and quantifies the variability that occurs by chance because a sample rather than an entire population is surveyed.

The absolute sampling errors estimates for the overall New Zealand household population are presented in tables 1.01 and 1.02. These errors should be used as a guide for judging the reliability of figures contained in the tables.

Table 1.01

Sampling error estimates for household key variables
2009 and 2012

Variable

All households

Sampling error

2009

2012

2009 

2012

2009 

2012

Number (000)

Absolute number (000)

Relative percent

Internet

1,220

1,332

15

13

1.23

0.98

Landline

...

1,448

...

14

...

0.94

Broadband access

1,023

1,240

21

15

2.04

1.23

Dial-up access

202

70

13

8

6.36

11.00

Note: Sample errors for 2009 have been revised.
Symbol: ... not applicable

Table 1.02

Sampling error estimates for individual key variables
2009 and 2012
Variable

All individuals

Sampling error

2009

2012

2009

2012

2009 

2012 

Number (000)

Absolute number (000)

Relative percent

Recent Internet users

2,677

2,820

24

27

0.89

0.96

Broadband access

...

2,458

...

36

...

1.46

Dial-up access

...

97

...

12

...

11.93

Online purchases

1,430

1,856

39

41

2.71

2.23

Note: Sample errors for 2009 have been revised.
Symbol: ... not applicable

The sampling errors provided above are estimated at the 95 percent confidence level.

How to use the sampling errors

For example, the estimated number of households with Internet in 2012 is 1,332,000. This estimate is subject to a relative sampling error estimate of approximately 13,000. This means that 95 percent of the possible samples of the same size will produce an estimate between 1,319,000 and 1,345,000.

In general, the sampling errors associated with subnational estimates (eg breakdowns by regional council area) are larger than those associated with national estimates.

Response rates 

The 2012 Household Use of ICT Survey targeted a 75 percent response rate. The survey achieved an actual response rate of 76 percent, which represented 13,046 households.

Consistency with other periods or datasets 

Information and communication technology (ICT) is a rapidly changing field. As a result, the Household Use of ICT questionnaire has changed considerably since the last survey cycle. The questionnaire is now more streamlined with a stronger focus on Internet security. The majority of the household questions have been moved into the individual section allowing for use of multiple technologies within a household to be captured. This move was also aimed at gaining the individuals’ perspective of their own circumstances, rather than that of the household. Nevertheless, in order to retain as much comparability as possible with previous years, some individual responses have also been aggregated to the household level. This is done by deriving a variable for a household if at least one individual in the household contributes to that variable. Nevertheless, some outputs will not be comparable with previous years due to question changes and new questions.

General information

Data source

The 2012 Household Use of ICT Survey was a supplement to the Household Labour Force Survey (HLFS) for the September 2012 quarter. The supplement was asked of all households and people eligible to take part in the HLFS. Two questionnaires were used. A Household ICT questionnaire asked about households’ access to the Internet and a landline telephone. An individual ICT questionnaire was then asked of all eligible individuals within the HLFS sample. Proxy responses were not accepted for ICT questionnaires.

Population and sample selection

The target population for the Household Use of ICT Survey is the civilian, usually resident, non-institutionalised population aged 15 years and over living in private dwellings. This means the survey population did not include:

  • long-term residents of homes for older people 
  • hospitals and psychiatric institutions 
  • inmates of penal institutions 
  • members of the permanent armed forces 
  • members of the non-New Zealand armed forces 
  • overseas diplomats 
  • overseas visitors who expect to be resident in New Zealand for less than 12 months.

The HLFS target population includes non-private dwellings whereas the Household Use of ICT Survey does not.

The target population for the household portion of the Household Use of ICT Survey is all households from the scope outlined above with at least one eligible individual.

The HLFS sample contains about 15,000 private households and about 30,000 individuals each quarter. Households are sampled on a statistically representative basis from areas throughout New Zealand, and information is obtained for each member of the household. The sample is stratified by geographic region, urban and rural areas, ethnic density, and socio-economic characteristics

Data capture

The 2012 Household Use of ICT Survey was an electronic questionnaire. One-eighth was conducted via face-to-face interviews, and seven-eighths were collected via telephone (CATI) interviews.

Accuracy of the data

Non-sampling error

Non-sampling error may arise from:

  • errors in the reporting of data by respondents
  • variation in respondents' or interviewers' interpretation of questions
  • errors in capturing or processing of data

An effort has been made to reduce non-sampling error to a minimum by careful design and thorough testing of the questionnaire, efficient operating systems and procedures, and appropriate methodology. Non-sampling errors may still occur and are not quantifiable.

Given the nature of the data collected, there are limitations on the level of accuracy that can be expected from the survey. Even though detailed descriptions of technical terms were given, there may still be differences in respondent and interviewer interpretation.

Unit non-response

Unit (or complete) non-response occurs when units (respondents) in the sample do not complete a questionnaire. The initial selection weight of the remaining units was adjusted to account for the unit non-response.

Item non-response

Item (or partial) non-response is when units (respondents) complete the questionnaire but some questions are not complete (eg refused). Item non-response imputation was carried out for the questions that required derivations of household data – including personal mobile phone use and personal income.

Imputation

Random donor imputation was used to impute answers for unanswered categorical questions and personal income. The donor was a random selection from the same strata, which are defined by characteristics of the respondent.

Suppression of data

Cells with estimates of less than 1000 are suppressed and appear as 'S' in the tables. These estimates are subject to sampling errors too great for most practical purposes.

Interpreting the data

As stated above, a large portion of the household section of the questionnaire was moved to the individual section in the 2012 survey. However, in order to retain comparability at the household level, several individual questions around Internet connection types and devices were aggregated to the household level. While this change in methodology between 2009 and 2012 does not compromise comparability, it is something to note when interpreting the data.

Previously all individuals were asked if they had access to a mobile phone, which was published as individual and aggregated household results. In 2012, a change in routing meant that only those who had used the Internet in the last 12 months were asked if they had a mobile phone. In the published results (see Excel table 21 in the 'Downloads' box) for 2012 this new methodology was applied to the 2009 data for comparability. This change meant that household level comparisons could not be made with 2009 data. Nevertheless, household-level results around mobile phones will be available from the 2013 Census. Census results will be released progressively from December 2013, starting with key population and dwelling information, with the final release approximately 18 months from that date.

Liability

While all care and diligence has been used in processing, analysing, and extracting data and information in this publication, Statistics NZ gives no warranty it is error-free and will not be liable for any loss or damage suffered by the use directly, or indirectly, of the information in this publication.
Timing

Our information releases are delivered electronically by third parties. Delivery may be delayed by circumstances outside our control. Statistics NZ does not accept responsibility for any such delay.

Crown copyright©

Creative Commons logo.
This work is licensed under the Creative Commons Attribution 3.0 New Zealand licence. You are free to copy, distribute, and adapt the work, as long as you attribute the work to Statistics NZ and abide by the other licence terms. Please note you may not use any departmental or governmental emblem, logo, or coat of arms in any way that infringes any provision of the Flags, Emblems, and Names Protection Act 1981. Use the wording 'Statistics New Zealand' in your attribution, not the Statistics NZ logo.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Top
  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+