Exam 3 - 1 ID# Exam 3 PS 217, Spring 2009 (You must use your official student ID) As always, the Skidmore Honor Code is in effect. You’ll attest to your adherence to the code at the end of the exam. Read each question carefully and answer it completely, showing all your work (so that you can receive partial credit). Have a peaceful and relaxing summer. 1. An industrial-organizational psychologist was interested in whether individuals working in different sectors of a company differed in their attitudes toward the company. A simple 9-point response scale was used, in which 1 indicated a strongly negative attitude toward the company and 9 indicated a strongly positive attitude toward the company. The results from the survey are seen below. Analyze these data as completely as possible for the psychologist and tell the psychologist what management should be told about the results. [15 pts] Engineering Marketing Accounting Production 9 6 2 5 8 4 1 3 8 5 3 4 8 7 2 5 Sum Sum 33 22 8 17 80 Sum of squared scores (e.g., ΣX2) 273 126 18 75 492Exam 3 - 2 2. Rehnman and Herlitz (2007) examined male and female subjects who viewed faces of both children and adults of either Swedish or Bangladeshi origin. They were later tested on their ability to recognize the faces from among a set of new/distractor faces (all presented in color from a frontal view, but free of facial hair and glasses). The DV in this case is d' (remember signal detection, where d' is a measure of sensitivity, with higher d' meaning more sensitivity, or greater recognition ability). Complete the source table below (slightly modified from SPSS output), then interpret the results as completely as you can. [15 pts] Dependent Variable:d' Source Type III Sum of Squares df Mean Square F Sig. Partial Eta Squared Observed Powerb Model 2.534 .000 .735 1.000 Subject 1.395 .000 .604 1.000 Model * Subject .582 .000 .389 1.000 Error .915 Corrected Total 5.426Exam 3 - 3 3. Drs. Yerkes and Dodson were interested in establishing the relationship between arousal and performance. They created a means of determining levels of arousal that fall between 1 (very low arousal) and 10 (very high arousal). They also use a measure of performance that falls between 1 (very low performance) and 10 (very high performance). The data that they collect from 12 subjects are seen below. Analyze the data as completely as you can to tell the good Drs. whether or not their data would allow them to predict levels of performance if they know levels of arousal. For instance, if they knew that a person's arousal level was 5, what would be the best prediction of performance level? What proportion of variance do these two measures share? [10 pts] Subject Arousal Performance 1 8 5 2 2 3 3 6 8 4 3 5 5 9 3 6 7 6 7 5 8 8 3 4 9 6 7 10 4 6 11 8 4 12 5 7 Sum 66 66 Sum of squared scores (e.g., ΣX2) 418 398 Mean 5.5 5.5Exam 3 - 4 4. Suppose that you are interested in the relationship between the time spent studying and the time it takes a person to complete an exam. You collect these data from 11 students and find that the coefficient of determination is .81. Are you justified in computing the regression equation for prediction? Assuming that you are, and given the information from the students seen below, compute the regression equation to predict the time to complete an exam (Y) from the number of hours spent studying (X). (You should assume a positive relationship.) [10 pts] Hours Studying Time to Complete Exam (Mins) Mean 5 50 Variance .2 7.2 5. How are the repeated measures and the two factors analyses of variance similar? How do they differ? The error term for the repeated measures ANOVA is most similar to which term in a two-factor ANOVA? (This question requires no computation.) [5 pts]Exam 3 - 5 6. Although psychologists do not completely understand the phenomenon of dreaming, it does appear that people need to dream. One experiment demonstrating this fact shows that people who are deprived of dreaming one night will tend to have extra dreams the following night, as if they were trying to make up for the lost dreams. In a typical version of this experiment, the psychologist first records the number of dreams (by monitoring rapid eye movements [REM]) during a normal night's sleep. The next night, each subject is prevented from dreaming by being awakened as soon as she or he begins a dream. During the third night, the psychologist once again records the number of dreams. Hypothetical data from this experiment are as follows: First Night Night After Deprivation S1 4 7 S2 5 5 S3 4 8 S4 6 7 S5 4 10 S6 5 7 S7 4 7 S8 4 6 Sum 36 57 Sum of squared scores (e.g., ΣX2) 166 421 Interpret these data as completely as you can. [15 pts]Exam 3 - 6 7. Below are some summary data from a single-factor independent groups experiment. On the basis of this information, you can compute an ANOVA. (Trust me, you can!) There’s a slightly more time-consuming way to get the source table from these data. A somewhat shorter procedure requires that you use information that you should know about the basis for the MSBetween and the MSWithin. Analyze the data as completely as possible (i.e., don’t simply complete the source table). [15 pts.] IV = Type of learning strategy (Repetition, Imagery, Make-a-Story, No Instructions) DV = Number of words recalled out of 30 Repetition Imagery Make-a-Story No Instructions Mean 2.6 7.2 7.2 5.7 Variance 1.6 2.4 2.4 .9 n 10 10 10 10 Source SS df MS F Between Within TotalExam 3 - 7 8a. As part of an analysis of the relationship between smoking and absenteeism, a researcher collected data from 8 randomly selected smokers and 8 randomly selected non-smokers. The number of packs a day that each person smoked was recorded (i.e., 0 for the non-smokers) as was the number of days absent from work in a year. Given the computer output seen below, what would you say about the relationship and the researcher's data? What proportion of the variability in absenteeism is explained by smoking? If a person smoked 1.5 packs a day, what would be your best guess about the number of days that they would be absent? What if the person smoked 7 packs a day? (10 pts)Exam 3 - 8 8b. One could also address the question slightly differently, by asking if there was a significant difference in the number of days absent from work as a result of smoking. You can’t extract the