POS 3713Midterm Exam II Study Guide 1 What is a research design and what are its chief goals Formally Research Design specifies the procedures we will use to answer a research question what data will we use Time space etc Informally ensures that data we examine provides an answer to the research question Chief Goals allow for valid inferences as to causal effects of x on y to assess whether that x IV moves or changes y DV we must compare two or more units Answer the how else question in comparing dependent variable values between two units individuals etc how else might those units differ from one another 2 What is an experiment How does it differ from an observational study In an experiment the researcher randomly assigns subjects to one of two groups the experimental group take drug and the control group placebo An experiment is a research design in which the researcher both controls and randomly assigns values of the independent variable to the participants The experiment must have random assignment of the treatment or control groups Observational study is a research design in which the researcher does not have control over values of the independent variable which occur naturally and there is no random assignment to the treatment groups 3 What are the strengths and weaknesses of experiments Observational studies Not all Independent variables are controllable ethical considerations prevent some experiments low external validity With experiments sometimes you cannot randomly assign the values of the IV Experiments also suffer from low external validity o Three ways that External Validity suffers in experiments Normally researchers do not draw a random sample from a population Instead they use a sample of convenience which is the group of people the researcher coerces into participating This makes it difficult to know whether the results of that analysis are in any way typical of what we would find in a different sample o The second threat to External Validity in experiments is the external validity of the stimulus itself Since an experiment creates an entirely artificial environment we might be concerned that the results of that experiment in a more real world o The third threat to External Validity in experiments is that they carry special context could be different ethical dilemmas for the researcher In an observational study the comparison between groups with different values of the independent variable may very well be polluted by other factors interfering with our ability to make conclusive statements about whether X causes Y cannot cross the 4 What are field experiments and how do they compare to traditional experiments and fourth hurdle observational studies In a Field experiment the researcher tries to influence the value of X in a true experiment the researcher assigns values of X the researcher may not have complete experimental control may not be able to use random assignment and the behavior that is of interest is observed in a natural setting Field experiments are in a natural setting which allow for high external validity as well as longer observation periods Disadvantages do not have complete experimental control may not be able to use random assignment therefore treatment and control groups are not balanced z s 5 What is the difference between random assignment and random selection What types of studies use each How does each contribute to internal or external validity Random Assignment Values of the Independent Variable assigned randomly Random Selection members of the study are selected randomly from the population If a researcher didn t use random assignment then there could be differences between participants in the treatment and control groups other than X which would be a threat to internal validity one 6 What are the two types of observational studies Why would a researcher choose to use each Cross Sectional Study examines a cross section of social reality focusing on variation between individual spatial units like citizens elected officials voting districts or countries and explaining the variation in the dependent variable across them Time Series Study the variation within one spatial unit over time is examined 7 What are internal and external validity How do they differ What are some common threats to each one Internal Validity belief that X causes Y or confidence that the effect of X on Y is real Threats to Internal Validity Any differences between participants in treatment and control groups other than X External Validity Confidence that the relationship between X and Y generalizes beyond the sample we want our study and conclusion to apply to the real world Threats to External Validity any differences between participants and non participants the setting under study and real world 8 What does it mean to control for Z Why is controlling for Z so important for research Controlling for Z Research design that eliminates alternate explanations for an observed relationship between X and Y If you do not control for Z the other effects of other causes of Y we are likely to misunderstand the relationship between X and Y So long as a reasonable cause can be made that some uncontrolled for Z might be related to both X and Y we cannot conclude with full confidence that X indeed causes Y Random assignment controls for Z in an experiment 9 What is the ecological fallacy What are the examples we used in class Why is it a problem for researchers relationship exists Ecological fallacy Using relationship groups to infer among individuals when no true Examples Are African Americans joining the KKK Finding Strong positive association between x of population in county that is Black and Y membership in KKK 10 What is regression to the mean When is it most likely to occur Why is it a problem for researchers luck Regression to the mean an extreme value of a variable is likely to be followed by a less extreme value that is one closer to the mean It is likely to occur in lucky situations if the extreme value was due to luck then next time should be less extreme with average 11 What are the main findings of the reading on the Colbert Bump and how does the reading relate to the lecture material Democrats only go on Colbert when they are in trouble and after Democrats go on the Colbert show donations increase Republicans go on the show when they are doing well and Republicans either see no change or a decrease in donations after they appear on the Colbert show 12 According to
View Full Document
Unlocking...