I have conducted pre-test surveys of few hundred people through non-probability sampling. Now can I create a sampling frame work with the details of those pre-test survey respondents and than select the random sample for my final survey from this ?
If allowed what would be that sampling technique called? Would it be probability? Also can we use these results to generalise it on health food population in my city (target population) or only limited to sample frame work. Please guide as this would be very useful. Thanks.
The sampling frame obtained from the pre-test is not the actual sampling frame. It is a subset of the actual sampling frame, The method cannot be called probability sampling method, Generalizations based on it cannot be reliable. The real exhaustve sampling frame should be used for the method to be a probability sampling method.
I agree with Ette, but might phrase it slightly differently. What you propose doing is to redefine your population as the non-probability sample, then randomly select from this group. The randomly selected group in the second step is valid, but could only be generalized to the non-probability group, not to the health food population of your city.
Thank Ette and Peter.
But I wonder how do researchers do random sampling in something like niche market like natural products where either the database does not exist or it very miniscule of the actual users (considering that one collates it from various sources). Because, unlike census these details are extremely hard to fetch as all retailers have refused to share info.
I have seen across research papers researchers using probability sampling. In one for example they get panel data of say 20K of eco-shoppers across US and randomly sampling 1200 from it. The paper titled included the country name. Considering the logic u have given how can they claim it represent their country when according to Organic consumer association (US) there approx. 50 million consumers of organic food.
Please clarify and also what best can I do to maximize its impact. Thanks.
I suppose you could conduct a large survey of a random sample of the whole population in your city with one screener-question: are you and eco-shopper? Those who say they are would make up your sample of eco-shoppers and you could ask them additional questions. I believe their answers could be generalized to the whole population of eco-shoppers in your city.
- Badges
- Science method
- Similar topics
- Mathematical Sciences
- Statistics
- Sampling Design