PSY 231 1st EditionExam # 2 Study Guide Lectures: 9 - 15Lecture 9 (September 18)Designs With One IV● 2 ways to structure an experiment● Between Groups Design-- compare different groups of participants, treated differently atthe same time● Within Subject Design-- compare the same participants, treating them differently at different times● After-only Design-- you don't know if the IV actually changed. Inadequate.● Before -After Design -- compares the IV before the experiment and again after to see if there was actually a change. (Within Subject) Adequate.Multiple IV Designs● Factorial research designs-- manipulate two or more IV’s simultaneously○ between groups or within subjects● Search for “it depends” effectsStructure● Manipulate two + IV’s○ two or more levels of each IV○ EX.Studying Fatigueyes restedno tiredResults:Main Effects● Main effects-- overall effect of one IV -- ignoring (averaged across) levels of any other IV’s○ EX: studying raises test scoresResults:Interaction Effects● Interaction effect--an it “it depends” answer to the research question○ one IV’s effect depends on the level of another IVLecture 10 ( September 23)Checking External Validity● By experimenting :Replicate○ new types of subjects, test situations, time period● Results that hold true across many experiments are likely to hold true in the real world too● By comparing results to real world patterns○ does “happier” chocolate correlate with : sales? what people say?● Different from face validity● Face Validity -- experiment looks like the everyday situation it is meant to tell us about● External validity is about what we learn, not what it looks likeInternal Validity● Internal Validity-- extent to which the IV, and only the IV, could have affected the DV○ “pure primary variance”○ Experiments may also measure error variance -- score differences caused by something other than the IVTwo Kinds of Error Variance● Unsystematic error variance○ affects all groups the same way○ does not affect our impression of what the IV does● Systematic error variance○ affects different groups differently○ can change our impression of what the IV doesConfound● Confound -- threatens the internal validity, factor that causes systematic error variance● Can make : effective IV look ineffective OR ineffective IV look effective● Results can be externally valid ONLY if the study is internally validLecture 11 ( September 25)Question & Answer Day● Shorthand research design-- 3 X 2○ each slot represents an IV○ the number in the slot shows how many levels of the IV there are○ in this particular example there are two IV’s , one has three levels the other has two. For this experiment there will be a total of six groups● External Validity -- degree to which findings are going to be true outside of the experiment (how your experiment applies to the real world)● Internal Validity -- does the IV and only the IV effect the DVLecture 12 ( September 30)4 Reasons to go “On the Record” With a Hypothesis● A hypothesis suggests a likely answer to your research question○ “ The IV will [ do what?] to the DV?”● Reason 1: be honest, you probably have an opinion● Reason 2: gut check-- why’d you choose this research question?○ an educated guess○ justify your guess with theory and research○ must understand your topic to make a good prediction● Reason 3: to predict, you have to get specific about your experiment design○ effect of IV on DV○ hypotheses refer to variables in operational form■ as they occur in your experiment● Reason 4: good hypotheses make obvious…○ what data will agree with it○ what data will disagree with it○ helps with letting evidence guide your beliefs3 Types of Scientific HypothesesPrediction Scientific Example Null HypothesisPoint (exact) predicts exact value of the DVkids who go to preschool will earn a 3.27 GPA in HSPredicts all other DV valuesOne Tailed (directional)predicts direction of DV changekids who go to preschool will do better in HS than kids who did not go to preschoolpredicts DV will not change, or change in opposite directionTwo Tailed (non-directional)predicts that DV will changekids who go to preschool will perform differently in HS than kids who did not go to preschoolpredicts that DV will not change● Null hypothesis -- covers everything that is not in the hypothesis● These are mutually exclusiveTesting Hypotheses● Compare hypothesis (scientific and null) with dataMeasures of Central Tendency● Take home message about differences between groups○ mean (average)○ median (middle number)○ mode (most common number)Measures of Variance● Take home message about variances● variances -- spread of scores around the mean○ range○ frequency distribution○ standard deviationLecture 13 ( October 2)Error Variance● Error variance -- differences between people that have nothing to do with the IV. Pre-existing differences● Imprecise measurement● Pre-existing individual differences in..○ characteristics you are measuring (DV)○ susceptibility to being changed by the IVTwo Ambiguities Caused by Selecting Subjects from a Varied Population● Group means will almost always differ○ even if IV is not effectiveData Story Possible ExplanationsCentral tendency differs across levels of the IV● Mean differences tells the truth (IV changes behavior?)● Mean differences is accident of population variance (IV does nothing?)Individual scores overlap across levels of the IV● Overlap tells the truth (IV does nothing?)● Overlap is accident of population error variance (IV change behavior?)● Groups will almost always overlap○ even if the IV is effectiveMeasures of Variance Help us to Diagnose Overlap● They measure the amount of similarity between groups○ the less overlap the better○ overlap is too much when if obscures real differences○ if the measure is big, it suggests a lot of overlap, if its small it suggests little overlap● How to avoid hypothesis decision errors? -- Replicate the experiment many times● Inferential Statistics○ advice on whether to believe mean differences○ gives operational definition of “too much overlap”Lecture 14 (October 7)Inferential Statistics● Inferential Statistics-- “advice” on whether to believe the mean difference, operational definition of “too much” variance/overlap● Input-- data from the study (and