Talk:Nonprobability sampling

This article is rated Start-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects:

Mathematics Mid‑priority This article is within the scope of WikiProject Mathematics, a collaborative effort to improve the coverage of mathematics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.MathematicsWikipedia:WikiProject MathematicsTemplate:WikiProject Mathematicsmathematics Mid This article has been rated as Mid-priority on the project's priority scale. Statistics High‑importance This article is within the scope of WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.StatisticsWikipedia:WikiProject StatisticsTemplate:WikiProject StatisticsStatistics High This article has been rated as High-importance on the importance scale.

Convenience sample redirects here, while Convenience sampling redirects to Accidental sampling. I don't know which one is correct, but maybe someone can fix this... --Fretdf (talk) 12:43, 5 May 2014 (UTC)Reply

Fixed Seppi333 (Insert 2¢ | Maintained) 12:55, 5 May 2014 (UTC)Reply

Although accidental or careless use of nonprobability sampling is a big problem, there is also fields where it is commonly used, many, as the article says, hold the view that "non-probability approaches are more suitable for in-depth qualitative research". This view is ridiculed by presenting only the view of an opponent. The article should also present the arguments by those who believe in the statement (there are plenty of serious methodologists who do; the controversy is old) and the reasoning about circumstances where nonprobability sampling is justified. --LPfi (talk) 17:21, 14 June 2014 (UTC)Reply

The use of "nonprobability samples" without adjusting a statistical model to account for the issues in the sample is almost surely going to result in inconsistent estimators of model parameters. In English, that basically means that the use of any cookbook statistical methods (i.e., the type of methodology that a nontrivial number of researchers use) with nonprobability samples is going to, at very best, produce invalid results. With inconsistent estimators, it's more likely that any results from data analysis will just be spurious and so won't be reproducible (e.g., if the same researcher uses the same methodology with a different nonprobability sample). Such cases obviously don't stand up to the scientific method. Seppi333 (Insert 2¢ | Maintained) 20:13, 14 June 2014 (UTC)Reply

This article could be helped by a less biased view of the valid uses for non-probability sampling. There are a multitude of legitimate uses of non-probability sampling where probability sampling is either unrealistic or undesirable/irrelevant. Not all research is attempting to draw inferences about the entire population yet this article seems to imply that this is the starting point for all research (making non-probabilistic sampling techniques inevitably unscientific). This is a straw man argument and it is a pity that Wikipedia is presenting such a biased view. — Preceding unsigned comment added by 14.201.213.183 (talk) 18:41, 7 September 2016 (UTC)Reply