Overview of Exam 2:A. 40 to 45 Multiple Choice Questions. B. Should take roughly 50 minutes to complete, but you have the full 1hr15min (and I’ll stay longer too: time is not an issue). C. Roughly 65% about research design concepts, 35% about statistics & interpreting SPSS output. Stats questions will be very similar to what was asked of you in lab.D. Questions will be based primarily on information in the lecture slides& in-class lecture. For studying purposes, the readings are probably best used as a reference when something from your notes or the slides is unclear.E. If a topic or term is not on the outline below, it will NOT be on the examTopic Outline for Exam 2*Intro to Experimentation: Ch 6 Lectures 10/9 & 10/11 1. Simple logic of Experimentation & The Experimental Ideal & Why it falls short with studying people-Create a situation in which two groups are perfectly equal at baseline.-Then introduce a single treatment, a single treatment, a single change, a single manipulation to one of the groups, and take a measurement.-If the two groups differ on the measurement after the manipulation, we can conclude that the manipulation caused this change.-Biggest challenges with human subjects: groups are never perfectly equal at baseline, and it is difficult to manipulate ONLY one thing at a time.-The ideal situation (experiment) to support a causal claim, you create a situation where you can control everything possible; control both groups; manipulate (will cause change in one).-Start with two groups that are the same, then you do something to one group that you don’t do to the other. If the two groups behave differently afterward, whatever you did to the experimental group must have caused thechange.2. Independent Variable vs. Dependent VariableIV: the variable we manipulate, the one that potentially causes changes in the measured variable: DV: the variable we measure, the one that is potentially affected by the manipulation.-Random Assignment to Condition: This reduces selection bias. If you randomly assign groups to condition, the probability shows that group averages tend to be normally distributed this way (random selection ensures that participants in each group are similar, so that way when testing a difference in a group would be from the manipulation (IV) and not from the participants being different or unequal at baseline).-Probability theory shows that if we recruit N = 25 observations per group, then: Group averages tend to be normally distributed. Groups are unlikely to be significantly different from each other just by chance alone.-In other words, random differences wash out or average out!-We are unlikely replicating type 1 errors, which causes group differences.-If we are worried that the people who actually participate are equal to those who don’t participate, we are worried about external validity Random assignment minimizes threat to internal validity, not external validity.-random assignment allows us to establish cause and effect relationships.-Experimental vs. Control Group-The experimental group receives the treatment. The control group (or placebo group) does not.-Experimental group: receives manipulation that might affect the behavior of the individuals in that group-Control group: group receives either no treatment or a standard treatment with which new treatments are compared.- Placebo Group: in medical research, the comparison group in an experiment that receiveswhat appears to be a treatment, but which actually has no effect, providing a comparison with an intervention that is being evaluated-Randomized, Double-Blind, Placebo-control Experiment:-The Experimenter Effects threat is why the gold standard of experiments is that they all should contain these characteristics: “Randomized, Double-Blind, Placebo-control experiment”.-Double blind: a research design in which neither the investigator nor the participant is aware of the treatment being applied. This means that even the experimenter does not know what condition the participant is in.3. Internal Validity & Why we might have poor internal validity: -If we have the experimental ideal, as stated above in the first bullet, you have high internal validity.-Internal validity: refers to how confidently one can conclude that the observed effect (s) were produced solely by the IV and not extraneous ones. It is concerned with the question: “Was it really the treatment that caused the difference between the subjects in the control and experimental groups?“ -The IV is critical to the level of confidence you have in your conclusions; the greater the internal validity, the more you can have faith that you know what factors cause an individual to act in a certain way.- Why we might have poor internal validity:o There might be random error affecting our DV Scores: -Aspects of the testing environment that affect both groups equally and that create “noise” in our data: Ex: a flickering light, an offensive shirt worn by the experimenter, the temperature of the room, clutter, experimenter mood, ad infinitum…-May cause us to “miss” detecting an effect, but is less of a problem if both groups are equally subjected to it. -Hard to control, and especially difficult to control in Human Sciences. We don't know if there is any random error, so we don’t ever catch it (why replicating experiments is important)o There might be systematic error affecting our DV scores: -Groups differ on a dimension that makes them unequal at baseline, that is unrelated to the IV, AND that may influence DV scores: Ex: having two conditions always run in two separate rooms, or by two separate experimenters, or at two times of day.-VERY PROBLEMATIC! Must critically think how to avoid such confounds(a third variable that causes that change/result; something other than the treatment causing the difference b/w subjects: a variable that is not controlled by an experimenter but that has a systematic effect on abehavior in at least one group in an experiment.)-These errors we do have control over.-If we do have systematic error, there is a problem; if groups are different after, then there is no way of knowing what it is from.-If they are systematically different at baseline; not good & need to fix this.o Selection bias (internal validity threat associated with participants): our two groups may be predetermined by a characteristic other than our IV ((i.e. personalities of those who sit up front vs. sit in back;
View Full Document
Unlocking...