Truly random probabilistic sampling was impractical as Aboriginal and Torres Strait Islander people account for only 3 % of the total Australian population.14 We used
a quota sampling design, based on meaningful clusters: the communities served by ACCHSs (and a community in the Torres Strait).
The Talking About The Smokes (TATS) project surveyed 2522 Aboriginal and Torres Strait Islander people using
a quota sampling design in the communities served by 34 Aboriginal community - controlled health services (ACCHSs) and one community in the Torres Strait, and has been described elsewhere.8, 9 Briefly, the 35 sites were selected based on the geographic distribution of the Aboriginal and Torres Strait Islander population by state or territory and remoteness.
Not exact matches
We are most confident in the methodological strengths of the longitudinal
design and future longitudinal analyses.7 More caution is needed in interpreting our prevalence estimates, but in spite of the methodological uncertainties of using a non-probabilistic
sample, we believe this, like many other
quota samples, is likely to give estimates similar to a probabilistic
sample (which may be subject to different biases, as we have shown with the NATSISS).23
Stata 13 (StataCorp) survey [SVY] commands were used to adjust for the
sampling design, using 35 site clusters, and the age — sex
quotas as strata.11
Design, setting and participants: The Talking About The Smokes project surveyed 2522 Aboriginal and Torres Strait Islander people from communities served by 34 Aboriginal community - controlled health services and one community in the Torres Strait, using
quota sampling, from April 2012 to October 2013.