|Page tools: Print Page Print All|
7 The SETIT only collected information from people aged 15–64 years, while in the GSS information was collected from people aged 18 years or over. To enable statistics from the SETIT to be compared to the GSS and previous years, data for the population aged 65 years or over was imputed for 2001. The method used to impute this data is detailed in paragraph 24.
8 In both the SETIT and the GSS, ABS interviewers conducted personal interviews at selected dwellings. Only one person was randomly selected from each participating household to provide information about their household's access to, and their own use of, information technology. The SETIT was conducted between April and August 2001. The GSS was conducted between March and July 2002.
9 In both the SETIT and the GSS, dwellings included for each state and territory were selected at random using a multistage area sample. This sample included only private dwellings from the geographic areas covered by the survey.
10 In the SETIT, the initial sample for the survey consisted of approximately 18,000 dwellings, in each of which there can be more than one household. This number was reduced to approximately 13,200 households due to sample loss (i.e., households which had no residents in scope for the survey and where dwellings proved to be vacant, under construction or derelict). Of the eligible households, 92% responded fully (or adequately) which yielded a total realised sample for the SETIT of approximately 12,100 households.
11 In the GSS, the initial sample for the survey consisted of approximately 19,500 dwellings. This number was reduced to approximately 17,000 households after sample loss. Of the eligible households, 91% responded fully (or adequately) which yielded a total realised sample for the GSS of just over 15,500 households.
WEIGHTING, BENCHMARKING AND ESTIMATION
12 Weighting is the process of adjusting sample survey data to infer results for the total population (whether that be persons or households). To do this, a 'weight' is allocated to each sample unit e.g. a person or a household. The weight is a value which indicates how many population units are represented by the sample unit.
13 The first step in calculating weights for each person or household is to assign an initial weight, which is equal to the inverse of the probability of being selected in the survey. For example, if the probability of a person being selected in the survey was 1 in 600, then the person would have an initial weight of 600 (that is, they represent 600 people).
14 The initial weights were calibrated to align with independent estimates of the population of interest, referred to as 'benchmarks' (for example, age and sex population estimates). Weights calibrated against population benchmarks compensate for over or under-enumeration of particular categories of persons or households in a survey and ensure that the survey estimates conform to the independent estimates of the population rather than to the distribution of persons or households within the sample.
15 It should be noted that the benchmarks used in the SETIT and the GSS relate only to persons and households living in private dwellings. Therefore the estimates do not (and are not intended to) match estimates of the total Australian resident population (which include persons and households living in non-private dwellings, such as hotels and boarding houses) obtained from other sources.
16 Survey estimates of counts of persons or households are obtained by summing the weights of persons or households with the characteristic of interest.
RELIABILITY OF ESTIMATES
17 The estimates provided in this publication are subject to sampling and non-sampling error.
18 Sampling error is the difference between the published estimates, derived from a sample of persons, and the value that would have been produced if all persons in scope of the survey had been included. For more information refer to the Technical Note.
19 Non-sampling error may occur in any collection, whether it is based on a sample or a full count such as a census. Sources of non-sample error include non-response, errors in reporting by respondents or recording of answers by interviewers, and errors in coding and processing data.
20 Non-response occurs when people cannot or will not cooperate, or cannot be contacted. Non-response can affect the reliability of results and can introduce a bias. The magnitude of any bias depends upon the level of non-response and the extent of the difference between the characteristics of those people who responded to the survey and those who did not.
21 To reduce the level and impact of non-response, the following methods were adopted in both the SETIT and the GSS:
22 Of the eligible dwellings selected in the SETIT and the GSS, 8% and 9%, respectively did not respond fully or adequately. As this level of non-response was low, the impact of non-response bias is considered to be negligible and, in any case, would be within the bounds of sampling error for most estimates.
23 Every effort was made to minimise other non-sampling errors by careful design and testing of questionnaires, intensive training and supervision of interviewers, and extensive editing and quality control procedures at all stages of data processing.
IMPUTATION OF DATA FOR PEOPLE AGED 65 OR OVER FOR SETIT
24 It should be noted that the scope of the SETIT was restricted to people aged 15–64 years. Consequently data were not collected from households where all usual residents were aged 65 years or over or from people aged 65 years or over living in households with other people aged 15–64 years. This varies from the scope for GSS and the PSM which included people aged 18 years or over.
25 To enable comparisons with household and person level estimates from 2002 and previous years, the 2001 data include an imputed estimate for households and persons that were considered out of scope of the SETIT due to the exclusion of persons aged 65 years or over.
26 The imputation used data for people aged 65 years or over that was collected in 2000 from the PSM. Two adjustments were made to the 2000 data. The first adjustment accounted for known changes in the numbers of people aged 65 years or over. The second adjustment accounted for expected changes in the proportions of people aged 65 years or over who have access to a computer or to the Internet at home, at a household level, and used a computer or the Internet, at a person level. These expected changes were calculated by assuming that the changes that occurred between 2000 and 2001 would be the same size as the changes between 1999 and 2000. All the adjustments were calculated at the state and metropolitan/ex-metropolitan level.
27 The estimates in the 2001 results should be treated with some caution, because the adjustments may not accurately reflect the true changes that occurred between 2000 and 2001. However, the contribution from the imputed data to the total estimates is relatively small. For example, people aged 65 years or over contributed about 3% to the total estimate of computer use by persons in table 4.1.
REVISION OF PREVIOUS YEARS' ESTIMATES
28 The methodology originally used to create the estimation weights for the PSM differed to that used for the SETIT and the GSS. Both the PSM and the SETIT methodologies benchmarked person level weights from the surveys to population estimates produced by the ABS. However, the SETIT methodology also benchmarked household level weights to household population estimates produced by the ABS. Benchmarking the weights to population estimates reduces the likelihood that differences observed over time in survey estimates for particular groups are due to sampling error rather than actual changes.
29 In order to improve the comparability of the PSM and the SETIT estimates, the PSM data have been rederived using the household and person level weighting methodology applied to the SETIT data. However readers should note that some differences remain between the PSM and SETIT methodologies even after the revision. Consequently readers should exercise caution when interpreting differences in estimates between 2000 and 2001 as these differences may be partly explained by the change in survey vehicle from the PSM to the SETIT.
DISABILITY DATA FROM SETIT
30 Information about disability was collected in the SETIT. This information for 2001 is not included in this publication because, while it is available for people aged 18–64 years, it is not available for the estimate of people aged 65 years or over which was imputed from 2000 data. Inclusion of disability information for 2001 from a subset of the total population would make comparisons with 2002 data misleading.
31 However, for those with a special interest in disability statistics relating to information technology, a special data service can be provided to furnish this information. See contact officer details in paragraph 45.
WORKING FROM HOME
32 Results presented in Chapter 7 relate to wage and salary earners who had an agreement with their employer to work from home. This population shows considerable variability across the years 2000, 2001 and 2002 (438,000, 545,000 and 480,000 respectively) and it is suggested that estimates provided in this section be used with caution. The methodology used to collect this data will be reviewed for future collection of this data.
ESTIMATION OF EXPENDITURE ON INTERNET TRANSACTIONS
33 In 2001, selected persons were asked to specify the value of their Internet orders or purchases of goods and services for private use via the Internet within the following ranges:
$0–$50; $51–$100; $101–$250; $251–$500; $501–$1,000; $1,001–$2,000; $2,001–$5,000; $5,001–$10,000; $10,001+
34 Those persons specifying values in ranges of over $1,000 were required to specify the actual value of their orders/purchases. The total value of orders/purchases was then calculated by using the midpoint of each of the ranges up to $1,000 for each value that was reported as falling within that range, and the actual value reported for those values over $1,000.
35 In 2002, selected persons were asked to specify the value of their Internet orders or purchases of goods and services for private use via the Internet within the following ranges:
$0–$250; $251–$500; $501–$1,000; $1,001–$2,000; $2,001–$5,000; $5,001–$10,000; $10,001+
36 Therefore, the first three ranges used in 2001 were collapsed for the 2002 survey, adding variability to any derived estimate. Of even greater importance was that those persons specifying values in ranges of over $1,000 were not required to specify the actual value of their orders/purchases. This adds an unacceptable level of uncertainty in deriving an accurate estimate of the total value.
37 However, from the 2001 survey results, in each of ranges $1,001–$2,000, $2,001–$5,000, $5,001–$10,000, the average of the specified values was greater than the midpoint of the range. Therefore, in using the midpoint of those ranges for each value that was reported as falling within that range would lead to a conservative estimate in 2002. Also, for the largest range ($10,001+), the average of the specified values was $20,500 in 2001. Given that the average value of orders/purchases via the Internet has increased substantially in 2002, assuming an average value for this range in 2002 of $20,500 would again lead to a conservative estimate. These assumptions were applied to derive the conservative estimate of $4.0 billion for the total value of purchases/orders of goods and services via the Internet.
38 In 2001, the ABS Classification of Qualifications (ABSCQ) (cat. no. 1261.0) was replaced by the Australian Standard Classification of Education (ASCED) (cat. no. 1272.0). The ASCED is a new national standard classification which can be applied to all sectors of the Australian education system including schools, vocational education and training, and higher education. Readers should note that the categories presented in tables for the classification 'Level of highest educational attainment' are not comparable to the categories presented for the classification 'Qualifications' used in previous years' publications.
39 A household is defined as a group of one or more persons in a private dwelling who consider themselves to be separate from other persons in the dwelling, and who make regular provision to take meals separately from those other persons. Lodgers who receive accommodation and meals are not treated as separate households. A household may consist of any number of family and non-family members.
40 For the purposes of the GSS, someone was said to have a disability if he/she reported a limitation, restriction or impairment, which lasted, or was likely to last, for at least six months, and which restricted everyday activities.
41 Metropolitan refers to capital city statistical divisions. These delimit an area which is stable for general statistical purposes. The boundary is defined to contain anticipated development of the city for a period of 20 years. The metropolitan area contains more than just the urban centre, and represents the city in the wider sense.
Highest Educational Attainment
42 Highest educational attainment identifies the highest achievement a person has attained in any area of study.
43 Australian Bureau of Statistics (ABS) publications draw extensively on information provided freely by individuals, businesses, governments and other organisations. Their continued cooperation is very much appreciated. Without it, the wide range of statistics published by the ABS would not be available. Information received by the ABS is treated in strict confidence as required by the Census and Statistics Act 1905.
44 Other ABS publications on the production and use of information technology and telecommunication goods and services in Australia are:
Business Use of Information Technology, Australia, 2001–02 (cat. no. 8129.0)
Government Use of Information Technology, Australia, 1999–2000 (cat. no. 8119.0)
Household Use of Information Technology, Australia, 2000 (cat. no. 8146.0)
Information Technology, Australia 2000–01 (cat. no. 8126.0)
Internet Activity, Australia, September 2002 (cat. no. 8153.0)
Use of Information Technology on Farms, Australia, June 2000 (cat. no. 8150.0)
AVAILABILITY OF UNPUBLISHED STATISTICS
45 As well as statistics included in this publication, the ABS has a range of data on the use of selected information technologies in households. Inquiries about these statistics should be made by telephoning Michael Robertson on Canberra (02) 6252 5189 or email email@example.com.
46 Abbreviations used in the publication:
These documents will be presented in a new window.