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 If a topic or term is not on the outline below it will NOT be on the exam E Intro to Experimentation Ch 6 Lectures 10 9 10 11 Topic Outline for Exam 2 Simple logic of Experimentation The Experimental Ideal create a situation in which two groups are perfectly equal at baseline then introduce 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 Independent Variable vs Dependent Variable Independent variable variable manipulated that potentially causes changes in the measured variable Dependent variable variable we measure is potentially affected by the manipulation Operationalize Manipulate the IV you have to specify how you are going to measure or manipulate the independent variable before you can perform an experiment Random Assignment to Condition helps wash out differences If N 25 observations per group then averages are normally distributed and groups are unlikely to be different from each other just by chance alone Random Assignment ensures that each participant has the same opportunity to be assigned to any given group Experimental vs Control Group Experimental group receives treatment and the control group does not receive any treatment Placebo Group All participants experience only one of the experimental conditions this group believes they are getting the treatment but are not This protects against maturation effects between group designs Randomized Double Blind Placebo control Experiment Gold standard of experiments to combat experimenter effects threat Randomization allows greatest reliability and validity in double blind studies the experimenter does not know what condition the participant is in and in a placebo control experiment one group is given a placebo treatment to account for the placebo effect External Validity the ability of a study s results to apply to the general population in real world circumstances Internal Validity Refers to how confidently one can conclude that the observed effects were produced solely by the independent variable and not extraneous ones Why we might have poor Internal Validity Systematic Error Confounds groups differ on a dimension that makes them unequal at baseline that is unrelated to the IV and that may influence DC scores very problematic and we must figured out how to avoid such confounds aka to mingle so that elements cannot be distinguished or separated Example Having two conditions always run in two separate rooms or by two separated experimenters or at two times of day Example arranged marriage study in US vs India To prevent use logical reasoning practice and get feedback Selection bias our two groups may be predetermined by a characteristic other than our IV Example Personalities of those who sit up front vs in the back of a classroom Example student aggression study To prevent use random assignment Maturation History effects sometimes participants change over time and it has nothing to do with your manipulation A control group is needed for comparison preferably one with the same shared history as those in the experimental group This can also be applied in the short term due to things such as boredom fatigue or practice Example political attitudes study sleeping and SAT s To prevent use control groups and counterbalancing Attrition losing subjects over time in a way that may be systematically related to the IV or DV Example Mischel s marshmallow study To prevent use careful planning and get permission to search public databases for contact information Instrumentation Experimenter Effects If the testing apparatus changes over the course of the experiment it introduces error unrelated to your DV Example racial bias studies juggling study To prevent use scripted protocols and raise awareness of issue Demand Characteristics subjects are often provided with cues to the anticipated results of a study When subjects become wise to anticipated results placebo effect they begin to exhibit performance that they believe is expected of them Example sensory deprivation with or without panic button study To prevent use credible cover stories and emphasize anonymity Random Error aspects of the testing environment that affect both groups equally and that create noise in our data Example a flickering light temperature of the room clutter in the room Null Hypothesis Testing T Tests Ch 8 Lectures 10 16 10 18 The experimental ideal Everything equal at baseline impossible to do The Logic of Null Hypothesis Testing Indirect Proof this is what the null hypothesis test is we have to prove to Dr Null that random chance is such an unlikely explanation for our results that the alternative explanation is better Random Chance vs Effect of IV as explanations for group differences Random Chance is the null hypothesis and effect of IV as explanation for difference is the alternative hypothesis Alpha P values how unlikely does our result have to be to rule out chance as the better explanations Our alpha level determines the cutoff Alpha 05 The p value is the probability of obtaining a test statistic at least as extreme as the one that was actually observed assuming that the null hypothesis us true One rejects the null hypothesis when the p value is less than the alpha significance level The p value tells us the probability that we did get the outcome by chance alone Sampling Distributions give us the statistical probability of getting a difference between sample means M of a certain sample size N from the same population just by chance alone Examples normal distribution T tests ANOVA etc Statistical Significance assessment of whether observations reflect a pattern rather than just chance Type 1 vs Type 2 error and how to minimize the risk of making them Type 1 a false positive rejecting the null hypothesis when it is true to reduce this you
View Full Document
Unlocking...