Editing Case study (section)

==Limitations==
''[[Designing Social Inquiry]]'' (also called "KKV"), an influential 1994 book written by [[Gary King (political scientist)|Gary King]], [[Robert Keohane]], and [[Sidney Verba]], primarily applies lessons from regression-oriented analysis to qualitative research, arguing that the same logics of causal inference can be used in both types of research.<ref name=":3" /><ref name=":1">{{Cite journal|last1=Humphreys|first1=Macartan|last2=Jacobs|first2=Alan M.|date=2015|title=Mixing Methods: A Bayesian Approach|journal=American Political Science Review|volume=109|issue=4|pages=654|doi=10.1017/s0003055415000453|s2cid=1846974|issn=0003-0554}}</ref><ref name=":02"/> The authors' recommendation is to increase the number of observations (a recommendation that [[Barbara Geddes]] also makes in ''Paradigms and Sand Castles''),<ref name=":0">{{Cite book|last=Geddes|first=Barbara|title=Paradigms and Sand Castles: Theory Building and Research Design in Comparative Politics|publisher=University of Michigan Press|year=2003|isbn=978-0-472-09835-4|pages=129–139|doi=10.3998/mpub.11910|jstor=10.3998/mpub.11910}}</ref> because few observations make it harder to estimate multiple causal effects, as well as increase the risk that there is [[Observational error|measurement error]], and that an event in a single case was caused by random error or unobservable factors.<ref name=":3" /> KKV sees [[Process tracing|process-tracing]] and qualitative research as being "unable to yield strong causal inference" because qualitative scholars would struggle with determining which of many intervening variables truly links the independent variable with a dependent variable. The primary problem is that qualitative research lacks a sufficient number of observations to properly estimate the effects of an independent variable. They write that the number of observations could be increased through various means, but that would simultaneously lead to another problem: that the number of variables would increase and thus reduce [[Degrees of freedom (statistics)|degrees of freedom]].<ref name=":02"/> Christopher H. Achen and Duncan Snidal similarly argue that case studies are not useful for theory construction and theory testing.<ref>{{Cite journal|last1=Achen|first1=Christopher H.|last2=Snidal|first2=Duncan|date=1989|title=Rational Deterrence Theory and Comparative Case Studies|url=https://www.jstor.org/stable/2010405|journal=World Politics|volume=41|issue=2|pages=143–169|doi=10.2307/2010405|jstor=2010405|s2cid=153591618 |issn=0043-8871|url-access=subscription}}</ref>

The purported "degrees of freedom" problem that KKV identify is widely considered flawed; while quantitative scholars try to aggregate variables to reduce the number of variables and thus increase the degrees of freedom, qualitative scholars intentionally want their variables to have many different attributes and complexity.<ref>{{Cite web|last=Bennett|first=Andrew|editor1-first=Janet M|editor1-last=Box-Steffensmeier|editor2-first=Henry E|editor2-last=Brady|editor3-first=David|editor3-last=Collier|date=2008-08-21|title=Process Tracing: a Bayesian Perspective|url=https://www.oxfordhandbooks.com/view/10.1093/oxfordhb/9780199286546.001.0001/oxfordhb-9780199286546-e-30|access-date=2021-02-19|website=The Oxford Handbook of Political Methodology|language=en|doi=10.1093/oxfordhb/9780199286546.001.0001|isbn=9780199286546}}</ref><ref name=":7" /> For example, James Mahoney writes, "the Bayesian nature of process of tracing explains why it is inappropriate to view qualitative research as suffering from a small-N problem and certain standard causal identification problems."<ref>{{Cite journal|last=Mahoney|first=James|date=2016-09-02|title=Mechanisms, Bayesianism, and process tracing|url=https://doi.org/10.1080/13563467.2016.1201803|journal=New Political Economy|volume=21|issue=5|pages=493–499|doi=10.1080/13563467.2016.1201803|s2cid=156167903|issn=1356-3467|url-access=subscription}}</ref> By using [[Bayesian probability]], it may be possible to makes strong causal inferences from a small sliver of data.<ref name=":22">{{Cite web|last=Bennett|first=Andrew|editor1-first=Janet M|editor1-last=Box-Steffensmeier|editor2-first=Henry E|editor2-last=Brady|editor3-first=David|editor3-last=Collier|date=2008|title=Process Tracing: a Bayesian Perspective|url=https://www.oxfordhandbooks.com/view/10.1093/oxfordhb/9780199286546.001.0001/oxfordhb-9780199286546-e-30|url-status=live|website=The Oxford Handbook of Political Methodology|language=en|doi=10.1093/oxfordhb/9780199286546.001.0001|isbn=9780199286546|archive-url=https://web.archive.org/web/20140804121534/http://www.oxfordhandbooks.com:80/view/10.1093/oxfordhb/9780199286546.001.0001/oxfordhb-9780199286546-e-30 |archive-date=2014-08-04 }}</ref><ref>{{Cite book |last1=Fairfield |first1=Tasha |url=https://books.google.com/books?id=kHB3EAAAQBAJ |title=Social Inquiry and Bayesian Inference |last2=Charman |first2=Andrew E. |date=2022 |publisher=Cambridge University Press |isbn=978-1-108-42164-5 |language=en}}</ref>

KKV also identify inductive reasoning in qualitative research as a problem, arguing that scholars should not revise hypotheses during or after data has been collected because it allows for ad hoc theoretical adjustments to fit the collected data.<ref>{{Cite book|last1=King|first1=Gary|url=https://books.google.com/books?id=A7VFF-JR3b8C|title=Designing Social Inquiry: Scientific Inference in Qualitative Research|last2=Keohane|first2=Robert O.|last3=Verba|first3=Sidney|date=1994|publisher=Princeton University Press|isbn=978-1-4008-2121-1|pages=20–22|language=en}}</ref> However, scholars have pushed back on this claim, noting that inductive reasoning is a legitimate practice (both in qualitative and quantitative research).<ref>{{Cite journal|last=Yom|first=Sean|date=2015|title=From Methodology to Practice: Inductive Iteration in Comparative Research|url=https://doi.org/10.1177/0010414014554685|journal=Comparative Political Studies|language=en|volume=48|issue=5|pages=616–644|doi=10.1177/0010414014554685|s2cid=143936902|issn=0010-4140|url-access=subscription}}</ref>

A commonly described limit of case studies is that they do not lend themselves to generalizability.<ref name=":3" /> Due to the small number of cases, it may be harder to ensure that the chosen cases are representative of the larger population.<ref name=":19" />

As small-N research should not rely on random sampling, scholars must be careful in avoiding selection bias when picking suitable cases.<ref name=":6" /> A common criticism of qualitative scholarship is that cases are chosen because they are consistent with the scholar's preconceived notions, resulting in biased research.<ref name=":6" /> Alexander George and Andrew Bennett also note that a common problem in case study research is that of reconciling conflicting interpretations of the same data.<ref name=":7" /> Another limit of case study research is that it can be hard to estimate the magnitude of causal effects.<ref>{{Cite book|last=Gerring|first=John|url=https://books.google.com/books?id=xECY0nnkTvMC|title=Case Study Research: Principles and Practices|date=2007|publisher=Cambridge University Press|isbn=978-0-521-85928-8|pages=44, 53–55|language=en}}</ref>