MIDTERM EXAM 2 STUDY GUIDE 1 What is a research design and what are it s chief goals a A way to go about if X causes Y b Two kinds of research designs 1 Experimental 2 Observational c Chief goals is to help evaluate how well a theory fares as it crosses the 4 hurdles of causality basically answers the question if X causes Y 2 What is an experiment How does it differ from an observational study a An experiment is defined exactly as A research design in which the researcher both controls and randomly assigns values of the independent variable to the participants b An observational study is a research design in which the researcher does not have control over the values of the independent variable which occur naturally independent variable i Necessary however that there is still some variability in the 3 What are the strengths and weaknesses of experiments What are the strengths and weaknesses of observational studies a EXPERIMENTS STRENGTHS i High internal validity automatically crosses the second and 4th hurdle of causality due to the random assigning of different values of x that controls for every x b EXPERIMENTS WEAKNESSES i Not all Independent Variables are controllable and able to be manipulated gender race ii Suffer from low degrees of external validity iii Ethical dilemmas for the researcher 1 Human trials risky iv When interpreting the results of the data sometimes can make mistakes of emphasis 1 Just because an X causes Y doesn t mean that X has the largest effect on that Y c OBSERVATIONAL STUDIES STRENGTHS i High external validity ii More prominent in social science due to the easiness of observability time series and cross sectional iii Comparison of individual units or quantity over time d OBSERVATIONAL STUDIES WEAKNESSES i Doesn t automatically cross the 4 hurdles because X values aren t randomly assigned so there can be confounding variables 1 Don t know if you have controlled for all other possible causes of Y 2 Analysis must be more tentative 4 What are field experiments and how they compare to traditional experiments and observational studies a A field experiment is one that occurs in the natural setting where the subject normally lead their lives i Goes beyond the reach of experimentation 1 Can take place in public policy settings b This is different to experiments and observational studies because they don t have values of X and they have not been controlled field experiments try to influence the value of X c They can COMPARE because in the natural world things become random and then they can be treated as if it was experimentally assigned 5 What is the difference between random assignment and random selection What types of studies use each How does each contribute to internal external validity a Random assignment When the participants for an experiment are assigned randomly to one of the several possible values of X the independent variable i Occurs in experiments 1 Creates internal validity b Random selection A method for selecting individual cases for a study in which every member of the underlying population has an equal probability of being selected i Survey research 1 Goes with external validity and usually observational studies 6 What are the 2 types of observational studies Why would a researcher choose to use each one a Cross Sectional Examines a cross section of a unit focusing on variation between individual spatial units i Same point in time different units b Time Series A comparison over time within a single spatial unit 1 These two kids of observational studies require hard focus on 4 hurdles 7 What are internal and external validity How do they differ What are some common threats to each one a Internal validity When a research design has high levels of confidence in conclusions of causality SEEN IN EXPERIMENTS i Confident that X causes Y b External validity Degree to which we can be confident that the results of our analysis apply not only to individuals but to whole population more broadly i Generalism ii Observational Studies c THREATS INTERNAL VALIDITY i Differences between participants in treatment and control groups other than X d THREATS EXTERNAL i Unrepresented subject population ii Realism in the real world iii Sample of Conveniences 1 Mundane realism The events look the way they would 8 What does it mean to control for Z Why is controlling for Z so important for research a To control for Z means that there are no confounding variables that could make X not cause Y and the 4 hurdles of causality will not be crossed If assigned randomly then there will be no Z variables making the results less confident 9 What is the ecological fallacy What are the examples we used in class Why is it a problem for researchers a The ecological fallacy is a logical fallacy in the interpretation of statistical data where inferences about the nature of individuals are deduced from inference for the group to which those individuals b Gives assumptions for things that can lead to misinterpretations of belong tests 10 What is regression to the mean When is it most likely to occur Why is it a problem for researchers 11 What are the main findings of the reading on the Colbert Bump and how does the reading relate to the lecture material 12 According to lecture and the book What is conceptual clarity and why is it important to research a Conceptual clarity is basically clarifying what exactly the best measure of a certain concept when theorizing i Clarifying to the exact amount ii Example of income surveys job no job parent gives 13 What do reliability and validity mean when talking about properties of measurement note do not confuse the validity of a measurement with internal and external validity How do reliability and validity differ Why is each important for research a Reliability The extent to which applying the same measurement rules to the same case or observation will produce identical results i EX scale same every time 1 2 If it changes within 5 minutes not reliable If it changes within 5 days could just variance b Validity The degree to which a measure accurately represents the concept that it is supposed to measure i Invalid measures measures something other than what it was originally intended c Validity and reliability differ because reliability us a measurement of repetition for accuracy over time and validity is a measurement of d In casual theories a theory must be proven reliable and valid to have how accurate a concept really is confidence in our
View Full Document
Unlocking...