Friday, August 25, 2017

Case Study Research

Trying something new, here...

What I'm reading, today:

Bent Flyvbjerg, "Five Misunderstandings About Case-Study Research," Qualitative Inquiry, vol. 12, no. 2, April 2006, pp. 219-245.

https://arxiv.org/pdf/1304.1186.pdf

Why am I reading this? 

I'm editing my paper for the Annual APSA meeting coming up, and having a hard time interpreting my results, and making grand claims about what we've found, despite all the hard work that went into what we have so far. Its been frustrating, but is mostly due to the fact that I have a hard time finding purely descriptive analysis, based on a single case study, interesting. This paper I am reading is reminding me that case studies are valuable... next I need to read something about the value of purely descriptive research. (PS that paper looks at around 900k tweets from the general election, and compares positive and negative sentiment in tweets that mention Clinton to tweets that mention Sanders and Trump, as well as a comparison of policy language in those tweets, and popular hashtags. Findings are mixed, but overall, the social media environment was worse for Clinton; however negative Trump sentiment was really high). 

What did I learn? 

Five misunderstandings about case studies and their revisions:

1. General, context independent knowledge is more valuable than context dependent knowledge. 

1a. Predictive theories and universals cannot be found in the study of human affairs. Concrete, context-dependent knowledge is therefore more valuable than the vain search for predictive theories and universals.

2. Generalizability is not possible. 

-‘[M]ore discoveries have arisen from intense observation than from statistics applied to large groups.’ (Bevenridge 1951). 
-That knowledge cannot be formally generalized does not mean that in cannot enter into the collective process of knowledge accumulation--it may help cut out a path toward future innovation. 

2a. One can often generalize on the basis of a single case, and the case study may be central to scientific development via generalization as supplement or alternative to other methods. But formal generalization is overvalued as a source of scientific development, whereas ‘the force of example’ is underestimated.

3. Cannon test hypotheses or build theory with case studies. 

"When the objective is to achieve the greatest possible amount of information on a given problem or phenomenon, a representative case or a random sample may not be the most appropriate strategy. This is because the typical or average case is often not the richest in information. Atypical or extreme cases often reveal more information because they activate more actors and more basic mechanisms in the situation studied. In addition, from both an understanding-oriented and an action-oriented perspective, it is often more important to clarify the deeper causes behind a given problem and its consequences than to describe the symptoms of the problem and how frequently they occur. Random samples emphasizing representativeness will seldom be able to produce this kind of insight; it is more appropriate to select some few cases chosen for their validity" (13). 

3a. The case study is useful for both generating and testing of hypotheses but is not limited to these research activities alone.

4. Case studies are more prone to subjectivity bias

4a. The case study contains no greater bias toward verification of the researcher’s preconceived notions than other methods of inquiry. On the contrary, experience indicates that the case study contains a greater bias toward falsification of preconceived notions than toward verification.

5. Summarizing case studies into theories is difficult. 
-Not if you allow for the open endedness of the question "‘What is this case a case of?’

5a. It is correct that summarizing case studies is often difficult, especially as concerns case process. It is less correct as regards case outcomes. The problems in summarizing case studies, however, are due more often to the properties of the reality studied than to the case study as a research method. Often it is not desirable to summarize and generalize case studies. Good studies should be read as narratives in their entirety.




Thursday, January 26, 2017

The Inauguration and Fivethirtyeight.com

For the inauguration I was able to be a part of the fivethirtyeight.com liveblog! I am working on a story for them right now, although we were definitely slowed down by the inauguration and what as been a nonstop news cycle since Trump took office. The story is actually on executive orders, so its pretty relevant. hopefully it gets posted.

But below are the posts I was able to contribute to the liveblog. I know it seems stupid to save my contributions when the link is here for all eternity. But for those who know me well, they know I have been a Nate Silver superfan for years, and think that 538 does excellent reporting and journalism.  So to be associated with them, if only for 1 event, means/meant a lot, and was a major thrill for me! So here are some of the semi-smart things I contributed to the liveblog :)