Talk:Confounds and artifacts
 | The contents of the Confounds and artifacts page were merged into Confounding on 1 August 2022 and it now redirects there. For the contribution history and old versions of the merged article please see its history. |
Description of Artifacts
[edit]The description of artifacts seems confusing, for the following reasons:
- The definition ("variables that should have been systematically varied … but that were accidentally held constant") is abstract and would benefit from some concrete examples. It would also be helpful to explain why the term "artifact" is used in this context. It goes immediately from this abstract definition to the conclusion that they are "thus threats to external validity". The reason for drawing this conclusion is not given; there is a conceptual leap here that most readers will not understand.
- It states they are are "threats to external validity", but then describes what the "major threats to internal validity" are.
- The source referenced here, Campbell and Stanley, does not use the term artifacts. This seems to be referring to the content given on p.5, which starts with the following introduction: "Relevant to internal validity, eight different classes of extraneous variables will be presented; these variables, if not controlled in the experimental design, might produce effects confounded with the effect of the experimental stimulus." They then go on to describe history, maturation, testing, etc. In other words, Campbell and Stanley seem to give these as examples of confounding variables, but this Wikipedia article seems to be implying they are examples of artifacts, despite first stating that confounds and artifacts are distinct. This is highly confusing.
I would suggest specific corrections myself, but I'm honestly a bit fuzzy on the artifacts vs. confounds distinction myself. To me, it seems to make more sense to talk about artifacts as a property of the *results* of a study (e.g., "you claim these results are caused by X, but they are simply artifacts of poor experimental design.") But perhaps someone with a deeper understanding can shed some light on this.
--Abe Feinberg (talk) 16:06, 18 January 2021 (UTC)
Merge Discussion
[edit]{{Merge to|Confounding|Artifact (error)}}
Bibeyjj (talk) 18:24, 26 February 2021 (UTC)
- This seems to be a proposal to split the article to two different pages, but is perhaps best tagged as a merge. I suggest a merge to confounding and will add a template to that effect on the article page. Klbrain (talk) 21:56, 26 February 2021 (UTC)
Merger complete. Klbrain (talk) 10:46, 1 August 2022 (UTC)
