PEI VAZQUEZ 2.docx

Political Empirical Inquiry Exam 1 Cont. Chapter 4 Measurement Systematic observation and representation by scores or numerals of the variables we wish to investigate. Conceptualization Defining terms precisely Must be done before operationalization of concepts Ex) conceptualize ?political tolerance? Conceptual Order Need to conceptualize (define) an item Then, operationalize (create a measure for) it Operationalism Deciding in specific terms how you will measure something This operationalization should indicate what should be observed empirically to measure your concepts Should indicate specifically what data should be collected to test your hypothesis The precise meaning of that concept in a study becomes clear Reliability Consistency of measurements; higher consistency = higher reliability, lower consistency = lower reliabilty Ways of Testing Reliability Test ? Retest Method Apply the same ?test? to the same observations after a period of time and compare the results Split-Half Method Compare the results of two equivalent measures made at the same time. Only use when you have a multi-item measure Alternative Form Method Repeating different but equivalent measures at two or more points in time; combination of test-retest and split-half methods Research Worker/Inter-Coder Reliability Creating a code and training people how to decode given articles Validity Content Validity Example: Liberalism Accuracy of measurement with concept that?s supposed to be measured Types of Validity Face Asserted Validity by the researcher that the measurement is related closely to the concept being measured; subjective Content Ensures that full domain of a concept is measured; subjective Are all aspects of a concept covered in measurement ? Problems arise when not all areas are covered Construct Shows that the measure of one concept is related to the measure of another concept; empirical Attitudes about the Iraq War Political Party Example of Construct Validity Questions regarding the War in Iraq Questions measuring Party I.D. Inter-item Association Test of the extent to which scores of several items/measurements of one concept are the same Displayed in a correlation matrix Example of Correlation Matrix Problems With Reliability or Validity Can be reliable and invalid (yielding consistent results, but not measuring the concept it is meant to measure) Must be reliable if it is valid Pick validity over reliability, but reliability is easier to test Levels of Measurements Nominal Categories/attributes are different in name only; none of the attributes are better or worse than the other Example: Ethnicity Caucasian African-American Hispanic Asian Ordinal One attribute is more/less than another Example: Education Some High School High School Grad Some College College Degree Interval One-unit difference in scores is the same throughout the range of the measure; 0 is arbitrarily assigned (doesn?t represent absence) Thermometer 0C is not the absence of heat 60C is not double the heat of 30C Ratio Use full mathematical functions of numbers; most precise Can be used to order attributes 0 = absence of something Multi-Item Measures Enhance the accuracy of a measure and increases the level of measurement of a phenomenon Index Accumulated score of several different measurements Assign a range of possible scores for a number of items Determine the score for each item for each observation Then combine the scores for each observation across the board The resulting summary is the representative measurement of the phenomenon. Based on the Judgment of the researcher Scale Measures Intensity Types of Scales Likert Scale Calculated from scores obtained on individual items. Each item generally asks a respondent to indicate a degree of agreement or disagreement with an item Only some of the items are selected for inclusion in the calculation of the final score. Rensis LikertThose items that allow a researcher to distinguish most readily those scoring high on an attribute from those scoring low will be retained, and a new scale score will be calculated based only on those items. Gutman Scale Presents respondents with a range of attitude choices that are increasingly difficult to agree with Items composing the scale range from those easy to agree with to those difficult to agree with Louis GuttmanRespondents who agree with the ?more difficult? attitude items will also likely agree with ?less difficult? ones. Chapter 6 Literature Review Reasons to Conduct a Literature Review See what has/hasn?t been investigated Develop general explanations for observed variation in behavior/phenomena Identify potential relationships between concepts & to identify researchable hypotheses To learn how others have identified & measured key concepts To develop alternative research designs To discover how a research project is related to the work of others Key Things to Look for During a Literary Review What is the research question posed? (Question) What is the theoretical basis of the study? (Basis) What are the concepts/hypothesis used in study? (Hypothesis) What are the methods & data used by the authors? (Methods) What are the findings? (Findings) What contribution does it make? (Contribution) Can you see any flaws with the methodology used? (Flaws) Journals in Political Science American Journal of Political Science American Political Science Review British Journal of Political Science Comparative Politics Journal of Politics Political Communication Social Science Quarterly American Politics Research Search for Previous Literature Library Journal Search Jstor www.jstor.org Google Scholar http://scholar.google.com Lexis Nexis Search newspapers, laws, legal documents Allows you to restrict the search to the sources that will be most useful in finding accounts of political events from news organizations Writing a Review Limit to most relevant previous work Focus on concepts instead of individual books, articles, or authors. Boxcar Method Summary of each piece of literature (similar to annotated bibliography) NOT GOOD FOR LITERARY REVIEW FIN Welfare Military Spend. Abortion SS AA Income Tax Vouch. Rights Welfare x Military Spending .56 x Abortion .71 .60 X S.S. .80 .51 .83 X A.A. .63 .38 .59 .69 X Income Tax .48 .67 .75 .39 .51 X Vouchers .28 .08 .19 .03 .30 -.07 X Rights of the Accused -.01 .14 -.12 .10 .23 .18 .45 x