Presentation on theme: "Research Design Part II: Cross-sectional and Quasi-Experimental Designs Frankfort-Nachmias & Nachmias (Chapter 6 – Cross-Sectional and Quasi-Experimental."— Presentation transcript:
1Research Design Part II: Cross-sectional and Quasi-Experimental Designs Frankfort-Nachmias & Nachmias (Chapter 6 – Cross-Sectional and Quasi-Experimental Designs)Gerring (Chapter 8)Campbell and Stanley, “Experimental and Quasi-Experimental Designs for Research.” (remainder)King, Keohane and Verba (Chapter 5, sections )ApplicationsStack, S. and Gunlach, J. (1992) “The Effect of Country Music on Suicide.” Social Forces 71: 211–18.Lawrence S. Rothenberg; Mitchell S. Sanders, “Severing the Electoral Connection: Shirking in the Contemporary Congress.” American Journal of Political Science, Vol. 44, No. 2. (Apr., 2000), pp (Difference-in-difference)
2Writing a Literature Review Typical format for research articleIntroductionLiterature ReviewTheoryResearch DesignEmpirical Analysis and ResultsConclusion
3Writing a Literature Review Purpose of literature reviewInform reader of prior relevant workPersuade reader that your work is important (justify your research)
4Possible Justifications for Your Research New question, new theoryNew question, existing theoryOld question, new theoryOld question, conflicting theoriesOld question, conflicting findingsOld question, new methodsOld question, new data
5Literature Review Don’ts Don’t (just) provide a chronological listing of article summariesDon’t provide every detail of every study
6Literature Review Do’s Organize your discussion of the literature in a way that reflects and supports the justification for your researchProvide more detail for seminal studies, less detail (or simply a citation) for less cited studiesFor questions that have been studied extensively, it is not necessary to cite every studyEnd your literature review with a summary and critique that justifies your research
7Literature Review Assignment Approx pages, double-spacedDue November 2nd
8How to Identify the Relevant Literature Use electronic databases and keyword searches (Google Scholar, JSTOR)Prioritize:ArticlesArticles published in highly-ranked journalsRecently published articlesSeminal articlesNumber of articles: 10-20?
9Quasi-experimental and Cross-Sectional Designs What are they?Quasi-experimental – study of more than one sample (often over period of time)Cross-sectional – Analysis of a single sample (lacks random assignment, temporal variation, and manipulation); but includes comparison groupsPre-experimental – Cross-sectional, with no comparison group; causal inference impossible
10Quasi-experimental and Cross-Sectional Designs Why?Property-disposition relationshipvs.Stimulus-response relationship
11Pre-Experimental Designs One-Shot Case StudyOne groupNo variation in independent variableX O
12Pre-Experimental Designs Example:Dependent variable: Americans’ support for campaign finance reformIndependent variable: Watergate scandalData: 1976 survey of American adults; examine mean level of support
13Cross-Sectional Designs Static-Group Comparison DesignTwo groups – observed at one timeAllows variation in the independent variableX O1O2
14Elaboration of Static Group Comparison Design Correlational / Cross-Sectional DesignsX1 O1X2 O2X3 O3X4 O4Xi OiProblems with correlational/cross-sectional designs?
15Example: Wine and Health Hypothesis: Drinking wine causes individuals to be healthier (esp. heart)Existing studies: compared the health of wine drinkers to the health of those who do not drink wine:Research designX1 (Wine drinkers) O1 (Health)X2 (Non-drinkers) O2 (Health)
19Quasi-Experimental Designs Contrasted Groups DesignMultiple groups, based on some categorical variableObserved at one point in time (similar to cross-sectional)O1O2O3O4OiProblems with contrasted groups designs?
20Quasi-Experimental Designs One-Group Pretest-Posttest DesignOne groupAllows variation in the independent variableO1 X O2
21Elaborations of the One-Group Pretest-Posttest Design Time Series Designssimple vs. extendedO1…Ok X Ok+1…Omk = # of pretest observationsm = total # observationsOr (“equivalent time samples design”)X1 O1 X2 O2 X3 O3 … Xm Om
32Donahue and LevittHypothesis: The (legal) availability of abortion in a state is negatively related to the crime rate (many years later).O1 O2 O3 X1(early legalization) O4 O5 O6…O7 O8 O9 X2 (legalize 1973) O10 O11 O12…
34Gerring’s Criteria for Research Design Plentitude (N)Boundedness (relevant cases)Comparability (descriptive/causal)IndependenceRepresentativenessVariation (X, Y, X&Y)Analytic Utility (of the sample)ReplicabilityMechanismCausal Comparison
35KKV – Overcoming Common Problems Omitted Variable BiasInclusion of Irrelevant VariablesEndogeneityAssigning Values of the IV’sControlling the Research Situation
37Stack & GundlachHypothesis: There is a positive relationship between exposure to country music and suicide ratesResearch design:X1 (no country music) O1 (suicide rate)X2 (1 station) O2 (suicide rate)X3 (2 stations) O3 (suicide rate)X4 (3 stations) O4 (suicide rate)Xi ( etc.) Oi (suicide rate)
38Stack & GundlachFindings: 51% of the variation in urban white suicide rates can be explained by variation in airtime devoted to country musicInternal Validity?
47Regression Discontinuity Designs Example: What is the effect of an award on later achievement? (from CS)
48Regression Discontinuity Designs Example: What is the effect of an award on later achievement? (from CS)Inferential challenge: Award recipients are likely to do well anyway, even without the award, because criteria for receiving award also predict future success
49A regression discontinuity design is appropriate for any research design in which the assignment of the treatment is determined by a continuous variable that is also related to the outcome of interest.
51Head StartHead Start is a federal program that provides comprehensive education, health, nutrition, and parent involvement services to low-income children and their families.Head Start began in 1965Local nonprofits/education agencies must apply to federal government to be a Head Start provider
52Head StartResearch Question: What is the effect of Head Start on health/well-being of former participants?What problems might we encounter if we were to conduct the following study:X O (where X = Head Start participation)O
53Ludwig and Miller, 2007OEO and application assistance to poor counties in 1965“Treatment” group – 300 poorest counties that received head start application assistance“Control” group – 228 poor counties that did not