PSY3213 Final Exam Notes annenberg cbp headless professor research methods others should be able to achieve same results with same tools Video Notes friend scientific method surveys etc measuring job burnout Video Notes Magician Mind Reading Example o Safe Guards not Utilized Psychologist in same room Not told hypothesis earlier He could have changed the item he displayed Must provide a causal relationship not a Correlational one Survey 93 dissatisfied 75 had affairs but only 4 responded o Beware of faulty collection methods as well as pseudoscientific tests Polygraph those told it was infallible failed regardless of if they were guilty or not Seeing isn t believing question any data any conclusions only as good as the methods used to collect them beware of scientific break throughs and simple answers to complex issues Video 2 IV Type of Crime DV Length of Sentence Between Subjects Designs 2 by 2 Factorial Design 4 conditions Attractive people get lower sentences unless they use their attractiveness to commit the crime Come in read about the crime and assign the sentence given a few guidelines to know what is typical Hypothesis o Ordinary Man Robbery M 5 1 months Swindle M 6 4 months o Attractive Man Robbery M 2 2 months Swindle M 10 5 months Smashing together the robbery and swindle main effect for attractiveness just looking at attractiveness it looks like there is no difference Ordinary 5 8 months Attractive 6 4 months Smashing together type of crimes main effect for crime it shows that swindlers get more time in jail In a line graph a crossing of lines indicated significance which you will also see because of the ANOVA Chapter 12 Factorial Designs Factorial Design Factors IV At least 2 IVs in order to have factorial design More practical and most common are 2 or 3 levels 2 x 2 doubling of our basic 2 level one IV design from Ch 10 11 How many numbers 2 x 2 x 3 3 IVs Value of numbers 2 levels x 2 levels x 3 levels 2 x 2 4 treatment conditions 2 x 3 6 treatment conditions Multiply get number of treatment conditions If you don t use a factorial design and separate into smaller studies you will lose time efficiency and the interaction Make sure the IVs go together Eye color doesn t go with test performance Consider control issues repeated measures gives us greater confidence that there is equality in our groups Keep it simple stupid KISS don t make more complicated than it needs to be More Ss required more experimental conditions more chances things can go wrong Data interpretation becomes nearly impossible with 4 5 6 IVs most people use 2 or 3 Adding levels into factorial design increases groups in multiplicative fashion 2 x 2 x 2 8 conditions 3 x 2 x 2 12 conditions Ex post facto only way to study sex personality race etc IV s involve random assignment between subjects factorial designs or completely randomized Completely within groups or within subjects designs nonrandom assignment in order to assure the equality of participant groups Involve a combination of random and nonrandom assignment with at least one IV using each The use of repeated measures is probably more likely than other types of nonrandom Assigning Participants to Groups Random Assignment designs Mixed assignment type of assignment to groups assignment Main effect Main effects and interactions effect of each IV Interaction looking at result of each IV separately on the DV Example in book of gender of salesclerk and hearing ability of customer look at main Exists when one IV depends on particular level of another IV Example in book Male clerks were much slower in responding than female clerks to deaf customers one variable effects the level of the other variable Crossing lines or lines that converge typically suggest an interaction parallel lines always equals no interaction Example A researcher takes a sample of 40 introverts and 40 extroverts and asks them to solve problems in either a crowded room or an uncrowded room The researcher measures the number of problems solved numbers can range from 0 problems solved to 25 problems solved Crowded Room Uncrowded Room M 12 M 18 Introverts M 12 Extrovert M 18 s Name an IV Is it manipulated or not manipulated by researcher Does IV represent independent or correlated groups How many levels does this IV have SAME for other IV Name the DV Scale of measurement for the DV Does there appear to be a main effect of room Does there appear to be a main effect of personality Does there appear to be an interaction between room and personality Factorial ANOVA With factorial designs th sources of treatment variability increase Instead of having one IV as the sole source of treatment variability factorial designs have multiple IVs and their interactions as sources of treatment variability The actual distribution of the variance among the factors would depend of course on which effect were significant For a two IV factorial design we use the following equations Fa IV A Variability Error Variability F Fb IV B variability error variability Fa x b interaction variability error variability Two Way ANOVA for Independent Samples The two way ANOVAfor independent samples requires that we have 2 IV s clothing style amd customer sex with independent groups The independent sample means that one set of clerks see women dressed casually another different group sees women dressed sloppy etc Source Table In the body of the source table we want to examine only the effects of the two IVs clothing and customer sex and their interaction the remaining source w cell or within is the error term and Is used to test the IV effects different statistical programs will use a variety of different names for the error term the effect of sex shows an F ratio of 3 70 with a probability of 07 this iv shows marginal significance the probability of clothes falls below 01 in the table an f ratio of 6 65 and has p 02 therefore denoting significance two way ANOVA for correlated samples the two way ANOVA for correlated samples requires that we have two IV s with correlates groups for both IV a Most often these correlates groups would be formed by matching or by using repeated emasures In our example of the clothing customer sex experiment repeated measures on both IV s would be appropriate We would merely get one sample of salesclerks and have them wait on customers of both sexes wearing each style of clothing computer results the clothing effect is significant at the 001 level and the sex effect is significant at the 014
View Full Document
Unlocking...