 | This article is rated C-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects: | ||||||||||
| |||||||||||
What about fsQCA? Doesn't that overcome the dichotomy issue expressed in the critique?
Re "But as this variable is essentially a continuous variable, the division will always be arbitrary" The "always" is not correct. It would be better to say "But as this variable is essentially a continuous variable, the division will always need to be accompanied by an explicit theory about what are the important differences in the level of the variable, otherwise it will be seen as an arbirtary choice" — Preceding unsigned comment added by Rckjdavies (talk • contribs) 11:39, 9 May 2013 (UTC) Rckjdavies (talk) 11:50, 9 May 2013 (UTC)
Re "A second, related problem is the fact that the technique does not allow an assessment of the effect of the relative strengths of the independent variables (as they can only have two values)" This is an uninformed assessment. The presence of an attribute (they are not variables!) can have varied significance according to whether it is found to be a necessary condition, a sufficient condition, a necessary and sufficient condition, or an INUS condition (an insufficient but necessary part of a configuration that is unncessary but sufficient). And amongst INUS conditions, some attributes may be more common (i.e. found in more configurations) than others.Rckjdavies (talk) 11:50, 9 May 2013 (UTC)