ABARE survey of businesses in Australia's mining technology services sector, Financial Year 2003/2004
Contents
H. Sample Design
H1 Sample design
What sample design will be used, eg census, stratified simple random sample? (H1)
Note. Should include the sample selection strategy, and, if the sample design is multi-stage or multi-phase (or both), the sample selection strategy used in each stage/phase.
A simple stratified random sample will be used.
If a census, go to H4
Return to top
H2 Sample stratification
What stratification has been used in the sample design? (H2)
Note. Should include: stratification variables; stratification boundaries (noting any strata which are completely enumerated); reasons stratification strategy adopted; and, if multi-stage/phase sampling is being used, report stratification for each stage/phase.
A representative sample will be taken according to size of business (total employment - small, medium, large) and type of industry (seven defined categories).
Return to top
H3 Sample allocation
How has the sample been allocated to strata? (H3)
Note. Should include: allocation formulae (if used), and from where data referenced by formulae obtained; minimum and maximum stratum sample size constraints; reasons why the allocation strategy was adopted; and, if multi-stage or multi-phase sampling is being used, report for each stage/phase.
Company specific data has been sourced from the first ABARE MTS survey completed in 2002 for survey respondents, and publicly available company information for non-respondents. Total company employment is used as an indicator for size of business, and type of industry is used to classify businesses into particular specialisation categories.
Return to top
H4 Sample size
What is the expected total number of businesses you will attempt to contact (ie total sample size initially drawn)? How has this been set? (H4)
Note. Should include: total number of businesses that the agency will attempt to contact including expected non-responding businesses; any constraints which have been imposed (eg RSEs, Confidence Intervals, cost); if multi-stage/phase sampling is being used, should report for each stage/phase; if the survey is a census, then the total sample size should be the same as the total number of units on the frame reported in G4; and, if quota sampling is used, should indicate the number of businesses the agency will attempt to contact.
One in two companies will be sampled according to the size of business (small, medium, large) and type of industry (A, B, C, D, E, F, G) breakdown - 21 different combinations. This will ensure that a stratified random sample of at least 50% of the total population will be surveyed. For (approx.) 500 MTS companies this equates to 250 companies that will receive a survey to be completed.
Return to top
H5 Expected live and in scope units
Of the total number of businesses reported in H4, how many businesses are expected to be live and in scope? (H5)
Note. Should include how these estimates were determined (response should take into consideration frame issues reported in G6) and, if the sample is multi-phase, should include these quantities for each phase. Should exclude: businesses expected to be defunct (ie no longer in business); expected non businesses (eg private individual); businesses contacted that are expected to not fall into the scope of the survey for some other reason (eg a retail business in a manufacturing survey); if quota sampling is used, businesses expected to be contacted but not required (eg where quotas have already been filled).
Greater than or equal to 90% of companies are expected to be live and in scope. This estimate has allowed for a 10% error for companies that were included in the MTS sector but should not have been, companies that may no longer be in business, and companies that may have been merged/acquired.
Return to top
H6 Response rate
Of the number of businesses reported in H5, how many businesses are expected to respond (ie the responding sample size)? (H6)
Note. Should include: how these estimates were determined; target relative standard error (RSE) levels on selected data output items (if any) and reasons for choice; if the sample is multi-phase, should indicate these quantities for each phase; and, if quota sampling is used, should indicate the size of the desired sample (this should be a subset of H5).
It is hoped that all units that have been sampled will respond to the survey in order to obtain representative information on the MTS sector. If the companies that were initially included in the sample do not respond then they will be replaced by other similarly classified companies until a reasonable response rate has been achieved. A target response rate of 50% of the total population has been set.
Return to top
H7 Representativeness of respondents
What evidence is there that the expected respondents will be representative of non-respondents? (H7)
Note. This item addresses the concern that expected survey non-response may bias the survey results. The effect of non-response bias on survey results is lowest when the response rate is high, or when respondents are representative of non-respondents.
Based on information received from the first survey in 2002 and subsequent analysis, there is strong evidence to suggest that respondents are representative of non-respondents.
Return to top
If a census, go to I1
H8 Allowances for non-response
What allowances have been made for expected non-response and frame deficiencies in the sample design? (H8)
Note. Should include allowances made for: refusals, non-contacts, expected defunct units (ie units no longer in business), and expected out of scope units.
A system will be created where companies chosen in the initial sample who are non-respondents or are out of scope will be replaced by other similarly classified companies (by size of business and type of industry - 21 different combinations). This process will only continue until our target response rate has been achieved.
Return to top
H9 Respondent burden across surveys
What consideration has been given to ensuring respondent burden is spread evenly by controlling sample selection across surveys, or (for repeating surveys) over survey cycles? (H9)
It is hoped that respondent burden will be minimised by taking a stratified random sample of companies by size of business and type of industry.
Return to top
-->
