1 This publication presents estimates from the 2003 Survey of Motor Vehicle Use (SMVU). The data were collected in four quarterly sample surveys conducted by the Australian Bureau of Statistics (ABS) over the period 1 November 2002 to 31 October 2003.
2 The scope of the survey is all vehicles that were registered with a motor vehicle authority for road use at some stage during the 12 months ended 31 October 2003. Not included are caravans, trailers, tractors, plant and equipment, vehicles belonging to the defence services and vehicles with diplomatic or consular plates. Where they were registered as such, vintage and veteran cars were also excluded from the survey. Unregistered vehicles are out of scope.
3 The population was identified on 31 March 2002 using information obtained from the state and territory motor vehicle registration authorities. There were 12.8 million vehicles on the population frame at this time.
4 For the 2003 SMVU, a sample of approximately 16,400 vehicles was selected to report on vehicle use over a three-month period within the reference year 1 November 2002 to 31 October 2003. Of these, 26% were passenger vehicles and motor cycles, 55% were freight vehicles, 14% were buses and 5% were non-freight carrying vehicles. The sample size was chosen to give a suitable level of precision for estimates of total distance travelled and tonne-kilometres for each state/territory of registration by type of vehicle category.
5 The survey methodology is described as pre-advice, where owners of vehicles selected in the survey received early advice about their inclusion to encourage record keeping and minimise reliance on recall. These owners were asked to complete two mail questionnaires tailored to their vehicle type. The first, at the beginning of each quarterly survey period, asked for selected vehicle characteristics and the vehicle's odometer reading. Owners were also advised that they would receive a follow up questionnaire at the end of the quarter seeking details about the use of the vehicle over the quarter and a second odometer reading. Examples of the main items requested in the second questionnaire were included with the first questionnaire.
6 When questionnaires were returned to the ABS they were checked for completeness and accuracy and, where possible, follow-up contact was made with owners to resolve reporting problems. Where contact with providers could not be made, missing items on incomplete questionnaires were filled by imputing average data from like vehicles for which data were obtained.
7 Where the selected vehicle owner had not owned the vehicle for the whole quarterly survey period, the details provided for the period of ownership were adjusted to give a three-month equivalent, except where the vehicle was deregistered, in which case only the use up to the date of deregistration was included.
8 In addition, adjustments were made in the estimation process to account for the use of new motor vehicles registered after the survey population was identified, as well as the re-registration of other vehicles during this time. For the 2003 SMVU the population frame was created on 31 March 2002. More information about these adjustments is provided in Technical Note: Data Quality.
9 Estimates from information reported in each quarterly collection period were produced and these were then aggregated into annual estimates relating to the use of vehicles during the period 1 November 2002 to 31 October 2003. The size of the sample is insufficient to produce reliable quarterly results.
RELIABILITY OF ESTIMATES
10 When interpreting the results of a survey it is important to take into account factors that may affect the reliability of estimates. Such factors can be classified as either sampling error or non-sampling error. Information on sampling and non-sampling error is provided in Technical Note: Data Quality.
COMPARISON WITH MOTOR VEHICLE CENSUS DATA
11 Survey estimates of the numbers of vehicles, by vehicle type, are not fully comparable with ABS Motor Vehicle Census data (see Motor Vehicle Census Australia, (cat. no. 9309.0)). The main differences are:
- survey estimates of the numbers of vehicles relate to the average number of vehicles registered for road use during the period 1 November 2002 to 31 October 2003, not to the number of vehicles registered at a specific date, as is the case for the Motor Vehicle Census
- the characteristics of the type of vehicle identified from the survey information may differ from those recorded by the motor registries.
CONCEPT OF AVERAGES
12 Most tables in this publication include statistics presented as averages. Tables 1, 3 and 4 are summary tables and present average kilometres travelled per vehicle for all registered vehicles including those that travelled zero kilometres. The other tables present more detailed information on actual vehicle use where the denominator used in calculating the average is limited to the estimated number of vehicles that contribute to the particular cell. In some cases a vehicle may contribute to more than one cell in a table (e.g. a bus used for route service and charter purposes) but will only be counted once in the denominator for the total.
13 As the denominators used to calculate each average are different it should be noted that the averages along a table row cannot be used to derive the total column entry for that row.
14 This publication includes estimates of vehicle use for 1999, 2000, 2001, 2002 and 2003. Data from the 1998 to 2002 SMVUs have been post-stratified due to problems which were identified with sample selections for these surveys. For the 2003 survey these problems were rectified and therefore post-stratification was not necessary. The post-stratified results for the 1998 to 2002 SMVUs may be different to those obtained had initial sample selections been correct. For this reason, direct comparisons between 2003 and earlier data should be made with caution. See Technical Note 2: Methodological Review in Survey of Motor Vehicle Use, Australia, 12 months ended 31 October 2002 (cat. no. 9208.0) for information on the post-stratification process.
15 It should be noted that the survey methodology was designed to produce reliable level estimates of key data items at the state by vehicle type level. The survey was not designed to produce reliable estimates of annual movements. Changes in data over time may be subject to high RSEs and hence the changes may not be statistically significant. While the analysis in this publication does make comparisons over time the limitations as outlined above should be taken into account and care should be taken in drawing inferences from these comparisons.
RELATED PUBLICATIONS AND PRODUCTS
16 Users may also wish to refer to the following publications and products which contain information relating to motor vehicles in Australia:
Motor Vehicle Census, Australia cat. no. 9309.0 - issued annually
Sales of New Motor Vehicles, Australia, (Electronic Publication) cat. no. 9314.0.55.001 - issued monthly
Directory of Transport Statistics, 1998 cat. no. 1132.0 - released in January 1999
Transport Theme page on ABS Internet
ABS DATA AVAILABLE ON REQUEST
17 As well as the statistics included in this publication, the ABS has other relevant data available on request. Inquiries should be made to the National Information and Referral Service on 1300 135 070.