ERM 681 MIDTERM EXAM I Fall 2017 Part I (MCQs 21), II (Long Qs 8), III (Very Long Qs 2), HW3 : Q 1 to 5

Complete this section and submit as a hard copy by the due date. Make sure to BOLD your answers to each part of a question. Highlight only critical statistic.

For next 4 items, sketch each graph so that they depict the described relationship between the Experimental and the Control groups and gender (M vs. F). A labeled axis and key is provided on the answer sheet for each question.

22. Mean male > Mean female; Mean exp > Mean control and no treatment by gender interaction.

23. Mean male = Mean female; Mean exp < Mean control and a treatment by gender interaction.

24. Mean male = Mean female; Mean exp = Mean control and a treatment by gender interaction.

25. Mean male < Mean female; Mean exp > Mean control and no treatment by gender interaction.

22. 23.

24. 25.

26. Three methods of dieting are compared for effectiveness in terms of pounds lost. Because it is believed that a person’s gender may influence the relative effectiveness of the three methods, a two-way AOVA balanced design with equal cell sizes is employed and the summary table is provided. (12pts)

a) Describe the design by filling in the blanks in the following sentence. The design is a ____________ by _____________ balanced ANOVA with ___________ per cell. (1pt)

b) Assume that instead of the previous design you chose to examine the effect of the three methods of dieting ignoring the influence of gender. Reconstruct the data in the previous table into a one-way ANOVA table. (3pts)

c) Which of the two types of design, the one-way or two-way is the more powerful test of the treatment in this case? Explain (3pts)

d) Compare the effect size of diet in the one-way design to that in the two-way design and comment on your results? (5pts)

27. A hypothetical study was conducted to determine whether weight differs by incidence of coronary heart disease (CHD) and cigarette use. 100 people were randomly selected and assigned to each of the four conditions: no-CHD nonsmokers, no-CHD smokers, CHD nonsmokers and CHD smoker. The following line graph represents the results of the study. (12pts)

a) Does the line graph suggest a main effect due to cigarette use? If so, describe the nature of the effect. (2pts)

b) Does the line graph suggest a main effect due to the incidence of CHD? If so, describe the nature of the effect. (2pts)

c) Does the line graph suggest an interaction effect? If so, describe the nature of the effect. (2pt)

d) The factorial ANOVA design in this situation is said to be orthogonal (or balanced) because (1pt)

i. The lines are parallel

ii. The cell sizes are all equal

iii. There are two factors represented in a two-way design

iv. None of the above

e) Based on the results depicted in the line graph, complete the two-way ANOVA table by filling in the values where appropriate. (5pts)

Section III

Please make an answer sheet for each question in Part II. Make sure that your answer to each question is broken clearly into each lettered sub-question. As long as responses are clearly organized you do not need to retype questions. Put all of your final answers in the order and format specified by the question. Then, if SPSS output is requested, attach your SPSS output (only the relevant portions) on which you have highlighted your answers. Finally, attach all your computational work highlighting the problem number and your answers. Provide only final copies of any calculations done by hand (I don’t want multiple versions of scratch work). These responses should be turned in with the Part I answer sheet.

28. A study by Staub, 1970, was concerned with the effects of instructions to young children and their subsequent attempts to help another child (apparently) in distress. Twenty-four first-grade students were randomly assigned to one of three groups. The first group was labeled as indirect responsibility (IR), where students were informed that another child was alone in an adjoining room and had been warned not to climb up on a chair. The second group was labeled direct responsibility one (DR1), where students were told the same story as in the IR condition, but also that they were left in charge and to take care of anything that happened. The students were given a simple task, and the researcher left the room. The students then heard a loud crash in the adjoining room followed by a minute of sobbing and crying. Students in the third group, direct responsibility two (DR2), had the same instructions as the DR1 condition but the sounds of distress also included calls for help. Ratings from 1 (no help) to 5 (went to the adjoining room) were given to each student by an observer sitting behind a one-way mirror. The results are given below. Perform a one-way ANOVA in SPSS with α = .05 and answer the following questions: (25 pts)

IR DR1 DR2

3 5 4

4 4 4

2 5 3

1 4 3

1 5 4

2 5 2

1 4 5

1 3 3

a) State the null hypothesis in words. (2pts)

b) Perform the analysis in SPSS. Make sure to highlight or bold relevant portions of the output. (2pts)

Make sure to include:

ONLY relevant descriptive statistics, ANOVA table, any appropriate plot, any relevant statistical test(s), Effect Size and Power

c) Calculate the effect size using ω2. (2pts)

d) Assume you were planning to compare the Indirect Responsibility group with the Direct Responsibility groups. Without using SPSS (4pts)

i. Write out the linear contrast to perform this comparison

ii. Compute the contrast.

iii. Test whether the contrast is significant or not.

e) Use SPSS to perform the same contrast as in (e) and interpret your results. Include the appropriate table for this test. (3pts)

f) Run the Tukey’s HSD, S-N-K and R-E-G-W Q post hoc tests. What can you conclude about the effects of the three types of instructions? (3pts)

g) Based upon the ANOVA (and post hoc) results and assuming that the researcher is more concerned with avoiding Type I error than Type II error which of the three post hoc test should the researcher base his conclusions. Explain. (4pts)

h) Write an APA-style summary of your findings for the study based on the analyses you have completed. (5pts)

29. There have been a number of studies on the effects of "jetlag". Jetlag seems to be worse when one travels eastward. Hayes (1993) examined how many days it takes a person to adjust after taking a long flight. She had several groups of subjects: one group flew east across time zones (California to New York), a second group flew west (New York City to Los Angeles), and a third group took a long flight within the same time zone (New York to Miami). The researcher was also interested in whether men are affected more than women. The dependent variable is the number of days needed to adjust. The data may be analyzed in SPSS (provide output) but record your answers here. The following is the data that were collected: (25 points)

Eastbound Westbound Same

Males 4 3 5 2 3 2 3 3 2 4 1 1 2 1 1

Females 3 2 4 2 4 2 1 4 3 2 1 1 1 2 2

a) Complete the following table of cell, marginal means and the grand mean. (2pts)

b) State the alternate hypothesis in words for each test. (4pts)

Row:

Interaction:

c) Complete the following ANOVA table (using SPSS) and indicate with asterisks which tests are significant at α=.05: (2pts)

d) Plot the cell means for males and females as the direction of flight changes (w/o SPSS) (2pt)

e) Briefly comment on the chart in part (d). (3pts)

f) Conduct any follow-up test(s) to refine the findings of the ANOVA results and report any results that are statistically significant. (4pts)

g) Write a brief summary report of the substantive findings supported by the appropriate statistical evidence. (5pts)

h) Point out three potential weaknesses in the analyses that you have conducted that can invalidate the findings you have reported. (3pts)

1

M

Exp

F

Control