Week 7 Research Methods
Week 7 Research Methods Pols 201
Popular in Research Methods in Political Science
Popular in Political Science
This 3 page Class Notes was uploaded by Lauren Jones on Sunday March 6, 2016. The Class Notes belongs to Pols 201 at University of Tennessee - Knoxville taught by Adam Eckerd in Winter 2016. Since its upload, it has received 30 views. For similar materials see Research Methods in Political Science in Political Science at University of Tennessee - Knoxville.
Reviews for Week 7 Research Methods
Report this Material
What is Karma?
Karma is the currency of StudySoup.
Date Created: 03/06/16
Evidence, data, and measurement 3.1 Coining words o Has to be widely applicable Gentrification o Just an example of weird definitions Last Week’s examples o Education leads to wealth Argument made To measure education o At a census tract level Binary o Median One person, household, what is? o Don’t work, don’t have outcome, asked at the individual level o Wealth isn’t the same as income Income is low but wealthy Abstraction o Conceptualization From an idea/thing/ experience o Operationalization From a concept a tangible definition o Measurement From a definition to indicator o WE have to agree about what that word means Abstractor to indicator, we do lose information Indicator o Numbers of years in school Precision and Bias o Maybe theoretically you can measure something perfectly Probably could measure wealth well for population o What things are worth Never get an actual depiction o Summary calculation loses further precision Anyway measured, can be all over the map o Because of bias and lack of precision Reliability o Repeatability o Validity o Neither over or understating the true value of the indicator Bias Selection bias Information bias, observation bias Exclusion bias Recall bias Purposeful vs. accidental exclusion Inability to accurately recall what happens. People are terrible at remembering Indicator= concept+ error Validity o Has to be a valid representation Convergent validity Is it actually a meaure of the thing we are trying to measure Discriminant validity Types of indicators o Observed variables o Perceptual variables Translate indicator back to concept o Indicator can take on meaning itself and become divorced from the concept Three modes of indicators o Instrumental, conceptual, symbolic Look to previous studies at what other people do it o Come up with a new way to measure things instead of symbolic measure Find something that what you are trying to measure Don’t look for just a number o Look at critically, is this measuring the things they are trying to measure Considerations o By whom or how data collected Conceiving a measure of divorce Discuss why this isn’t a good measure If you come up with a measure, and still say that is a bad measure Northeastern University o SAT scores, o AMA, medical doctor Chapter 14 Measurement Principles 14.1 Measurement scales o Ca be binary, presence or absence o Binary Quantifies object as present or absent o Nominal Objects into different categories o Ordinal Categories organized logically in the greater less than way o Interval Temperature, opinion on a 1-10 scale Differ by equal amounts o Ratio Weight, ordered categories 14.2 Testing Hypothesis o Research can’t prove correct, but prove wrong Operational hypothesis Defined measurement characteristics Rejection of null gives difference by hypothesis and the theory If null is supported, difference predicted by hypothesis didn’t occur o Operational hypothesis narrows the measurement possibilities down 14.3 Probability o Null Hypotheses are statistically 95% is the acceptable likelihood .05 level of confidence is confidence expressed in rejecting the null hypothecs Type one errors o False positive results Incorrect rejection of null Type two o False negatives Incorrect acceptance of null 14.4 Randomness o Mathematical principle Random Events Cannot predict each outcome Probability reflects statistical testing, highly calculated gambles Random sampling error could be reasoning