Small-n

Small-n

1. Analysis of a small number of cases, entailing at least two, yet to permit the application of conventional statistical analysis - Lijphart

2. Intentionally select cases - usually between 2 - 12

3. Why compare few cases?

   • Goals of researcher - focus on cases rather than variables
   • Intensive rather than extensive knowledge
   • Advantages in relation to global statistical analysis
   • Less likely concept stretching
   • Large data set difficult to collect
   • Easier hypothesis testing

4. Too Many Variables too few cases

   • Can choose cases matched on many variables not central to the study
   • Can combine variables on a single measure
   • Develop theory that focuses on a smaller number of explanatory variables

5. Evaluation

   • Intentional case selection to control for potential confounding factors
   • More intensive and less extensive since they encompass more of the nuances specific to each country
   • Case - orientated, more similar and differences among countries rather than the analytical relationship between variables
   • Cannot be used to assess theories that assume probalistic causation
   • Coding of variables crude - dichotomous rather than continuous
     • But coding may be more reliable as more knowledge of cases
   • Lack of precisions about causal effects

6. Strengths

   • Control by selecting either MSSD or MDSD, Good for theory building, intensive, less variable oreintated
     • Avoid conceptual stretching, thick description, area studies, configurative analysis, macro-history
   • SNA provides more opportunity to identify causal process and mechanisms

7. Weaknessess

   • Less secure inferences, selection bias, language training, field reserach

8. MDSD AND MSSD

   • MSSD - perspectives that are similar for one researcher may be different to another, lending little value to the approach
     • Possible over determination
     • Design fails to eliminate rival explanations
     • Different understandings of concepts lead to different measures being used for he same concept
   • Reduce number of variables by focusing on the key explanatory factors, this is achieved by MDSD
     • MDSD inferences relate only to the conformation of the importance of the presence of a certain explanatory factor
       • MDSD can rule out cases more confidently than rule in
         • Solution - Multiple and conjuctional causation
         • Solution - Deepen within case analysis and use of historical anaylsis