PSY450: Experimental Psychology



PSY450: Experimental Psychology

Practice Test #2

1. A researcher presents one of three videogames to 9-year-old participants and then watches them during a peer interaction session immediately following the game. The video games vary in violent content. Broadly speaking, her approach to manipulating her independent variable involves

a. stressing a psychological system.

b. manipulating the context.

c. a physiological investigation.

d. presenting different stimuli.

2. Which of the following is not one of the ways a researcher can manipulate an independent variable?

a. Changing internal, physiological processes of the participant

b. Changing the context in which the stimulus is presented

c. Changing the personality traits of participants

d. Presenting participants with different stimuli

3. How you are feeling right now (a temporary condition that may be influenced by situational factors such as taking this exam) is known as

a. your personality.

b. a state characteristic.

c. a trait characteristic.

d. your self-concept.

4. How many levels or conditions of the independent variable are needed to conduct a true experiment?

a. At least three

b. At least one

c. At least two

d. None

5. When designing a powerful study, we try to _________ the variability among scores ______________ conditions and _____________ the differences among scores _______________ conditions.

a. increase, within; decrease, between

b. decrease, within; increase, between

c. decrease, between; increase, within

d. none of these

6. We want to create conditions in our study that differ substantially, so as to produce large differences in scores. In other words, we want to have

a. a strong manipulation.

b. at least three levels of our independent variable.

c. a control group.

d. external validity.

7. Jonathan measures the speed with which his participants respond to familiar words on a computer screen by having them push a keypad when they encounter a word they know. His dependent variable employs which of these approaches?

a. Reaction time

b. Self-reports

c. Direct observation of the behavior of interest

d. Indirect measures of unseen processes

8. In his research on visual perception and motor coordination, Dr. Jock uses university baseball players as his participants. On average, the worst scoring participant has a very high target hit rate, thus everyone's scores are high. The range of scores is restricted due to

a. a floor effect.

b. habituation.

c. an instrumentation effect.

d. a ceiling effect.

9. Rocky is participating in a signal detection experiment. He is asked to push a button on a keypad when he sees a dot on the screen. He goes through three warm-ups on the task before the actual experiment begins. These warm-ups are called

a. experimental trials.

b. practice trials.

c. reaction trials.

d. multiple trials.

10. Automation of the data collection process is used by researchers because it is likely to

a. increase external validity.

b. increase instrumentation effects.

c. reduce diffusion of treatment.

d. reduce experimenter error and inconsistency.

11. As her experiment with children goes along, Aimee finds that the toys she is using as stimuli are becoming shabby and worn and her videotape is becoming scratched and blurry. These changes lead to subtle changes in the measurement procedure over time, a problem called

a. instrumentation effects.

b. automation effects.

c. experimenter bias.

d. temporal effects.

12. Andrew has collected data on memory in goldfish. Now he is summarizing and describing the important characteristics of his data by computing means, or averages. In other words, he is

a. examining the external validity of his data.

b. computing descriptive statistics.

c. computing inferential statistics.

d. examining the internal validity of his data.

13. On the well-known Rokeach Value Survey, respondents rank 18 different values (such as "world peace" and "financial security") from most important to least important, assigning numbers from 1 to 18. Such scores are called _________ data.

a. ratio

b. interval

c. ordinal

d. nominal

14. If we measure the amount of time it takes a participant to respond to a stimulus, the level of measurement we are using is

a. nominal.

b. ordinal.

c. interval.

d. ratio.

15. You ask everyone in class to report how many hours they watched TV last week and how much junk food they ate (on a 9-point scale from none at all to a great deal). You create a graph of the data, putting hours of TV watched along the x-axis and amount of junk food eaten along the y-axis. Each person is represented by a "dot" on the graph. Such a graph is called a

a. scatterplot.

b. post hoc comparison.

c. line graph.

d. correlation coefficient.

16. The median is the preferred measure of central tendency when

a. the data distribution is not normal and the scale measurement is ordinal, interval, or ratio.

b. the scale of measurement is ratio.

c. the distribution is symmetrical and the scale of measurement is interval or ratio.

d. the scale of measurement is nominal.

17. Harish is comparing Catholics, Muslims, and Protestants according to the frequency with which they report that they attend worship services. What type of graph should he use to present his mean data for each group?

a. Scatterplot

b. Line graph

c. Bar graph

d. Frequency distribution

18. Suppose you collect data on people's fears about flying. If you examine the extent to which your set of scores differ or are spread out, you are studying

a. positive linear relationships.

b. negative linear relationships.

c. validity.

d. variability.

19. Jack, an environmental psychologist, has collected data on students' feelings of being crowded in their dorms. His data are interval scores that are normally distributed. The appropriate category of statistics for him to use would be

a. parametric inferential statistics.

b. nonparametric inferential statistics.

c. post hoc comparison statistics.

d. chi-square statistics.

20. Which of the following is not important to know in order to determine what kind of statistical test you should use to analyze your data?

a. Whether you have a between-subjects design

b. Whether your dependent variable is valid

c. How many conditions your independent variable has

d. What your scale of measurement is

21. Bjorn counted the frequency with which his participants fell into two categories: helped and did not help. He wanted to determine whether men or women helped more. What statistical test should he use?

a. Mann-Whitney test

b. Chi-square test

c. Kruskal-Wallis test

d. Independent samples t-test

22. You want to determine the values of mu that are not significantly different from your sample mean. You compute the highest and lowest values of mu likely to be represented by the sample mean. This range of values is called a(n)

a. unbiased estimated variance.

b. unbiased estimated standard deviation.

c. confidence interval.

d. rho statistic.

23. How do we interpret "a = .05?"

a. There is a 95% probability that our results are due to chance, or sampling error.

b. There is a 95% probability that we will make a Type 1 error.

c. The probability that we reject a true null hypothesis is 95%.

d. The probability that we reject a true null hypothesis is .05.

24. When statisticians report that results are nonsignificant, the results are

a. not important.

b. not due to chance.

c. likely to result from sampling error.

d. different from what we predicted.

25. Imagine that you are feeling very discouraged because you spent a great deal of time on a study and found no significant result. "But wait," your friend says. "You might have made a type II error." What does your friend mean?

a. You have incorrectly rejected the null hypothesis.

b. You made a mistake in calculating population variance.

c. The null hypothesis is true, but sampling error produced unrepresentative data that give the appearance of a relationship.

d. You have concluded there is no evidence for the predicted relationship in the population, when in fact the relationship does exist.

26. Statistical procedures are primarily designed to minimize the probability of

a. Type II errors.

b. Type I errors.

c. rejecting the null hypothesis.

d. sampling error.

27. The greater the N,

a. the more likely an obtained statistic is significant.

b. the more participants are tested.

c. all of these.

d. the more powerful the design.

28. The absence of random assignment in any study

a. allows for potential confounding.

b. increases internal validity.

c. increases external validity.

d. strengthens your ability to make a causal statement.

29. Would a researcher use a true experimental design to examine the effects of spousal abuse on self-esteem? Why or why not?

a. Yes, because experimental realism would be high.

b. No, because external validity would be low.

c. Yes, because a true experiment would allow the researcher to make a causal statement.

d. No, because it would be unethical.

30. Professor Turner found that the correlation between a person's degree of loneliness and the number of hours spent watching television is -.69. He can conclude that

a. as we observe people with higher and higher loneliness, we see a tendency for those people to spend more and more time watching television.

b. the people who watch more television tend to be more lonely.

c. as we observe people with higher and higher levels of loneliness, we see a tendency for those people to spend less and less time watching television.

d. there is not much of a relationship between the two variables because the r is negative.

31. The error in a single prediction is equal to the degree to which a participant's ________________ score deviates from the _________________.

a. predicted; mean

b. predicted; given X

c. actual; mean

d. actual; corresponding predicted score

32. Y' signifies

a. the correlated regression line.

b. a score on the X axis based on values of Y.

c. a predicted Y score.

d. a predicted X score.

33. If we can claim to account for .65 of the variance in Y scores by knowing a relationship, it means that

a. the predicted scores are 65% less variable than predictions made without knowing the relationship.

b. we are, on average, 65% more accurate at predicting Y' scores than we would be if we did not know the relationship.

c. the data are 65% more variable than we thought them to be.

d. the data are 65% less variable than we thought them to be.

34. The Pearson correlation coefficient is not very effective at detecting

a. nonlinear relationships.

b. positive linear relationships.

c. negative linear relationships.

d. instances of no relationship.

35. Arlisea is trying to measure masculinity using a sex-role inventory. She says, "The scale looks like it measures what it's supposed to." Arlisea is suggesting that her scale has

a. split-half reliability.

b. convergent validity.

c. predictive validity.

d. face validity.

36. Which type of questions are used when reliability is not a major concern and when we are interested in exploring new variables that might be relevant?

a. Closed-ended

b. Open-ended

c. Filler

d. Objective

37. Multiple trials on a survey are used to

a. discriminate between participants.

b. increase the face validity of the survey.

c. increase the survey's degree of construct validity.

d. acquire a reliable estimate of a participant's typical behavior.

38. Drew uses two different versions of the same questionnaire. On the pretest, all the participants get Version A, and on the posttest, all the participants get Version B, which differs in question order, question wording, and perspective. Drew is using

a. funnel questions.

b. counterbalancing.

c. alternate forms.

d. a catch trial.

39. An advanced statistical procedure uses the intercorrelations among many variables to discover the common aspects or components they reflect. This technique is called

a. multiple regression.

b. partial correlation.

c. factor analysis.

d. discriminant analysis.

40. An assumption that authors of research articles should make about their readers is that the reader:

a. understands how to interpret the author’s findings about behavior clearly

b. have only a limited knowledge of statistics and research methods

c. are not familiar with terms such as reliability and validity

d. are familiar with the background on a given topic

41. When citing articles with three to six authors,

a. include all author names when citing

b. include all author names only the first time you cite them

c. include only the first author’s name every time you cite the article

d. include only the first author’s name when you write the reference

42. Which part of a research report is typically written last by the author and appears on the second page (all alone) of the report?

a. abstract

b. introduction

c. footnotes

d. author credits

43. In a journal article, the Methods subsection that describes the temporal sequence of events the participants experienced in the research is entitled:

a. Participants

b. Design

c. Procedure

d. Apparatus

44. When writing a report, symbols that are used to represents statistical terms in the results section should be:

a. italicized

b. bolded

c. double underlined

d. bolded and italicized

45. The reference page should include complete references for:

a. all the sources related to your topic

b. only sources the author has cited in the article

c. all the sources the author read when conducting the research

d. all sources cited and all those instrumental in helping in the design

1. Discuss the advantages and disadvantages of using “open ended” questions on a questionnaire. (5 marks)

2. Suppose you find a significant difference in attitudes toward capital punishment between

males and females. Specifically, women are much less likely (M=2.6) to approve of capital punishment than men (M=9.2).

(5 marks)

a. Which type of figure/graph/chart should you use to visually demonstrate these differences.

b. Draw the figure in APA format.

3. Explain, using examples, three ways in which a researcher can create a strong independent variable (3 marks)

4. Suppose you are a researcher studying mortality rates. You count the frequency with which men and women die after a heart attack. (5 marks)

What is your scale of measurement?

What descriptive statistics should you use?

What inferential statistical test should you use to examine central tendency?

PSY450: Experimental Psychology

Practice Test #2

1. d

2. c

3. b

4. c

5. b

6. a

7. a

8. d

9. b

10. d

11. a

12. b

13. c

14. d

15. a

16. a

17. c

18. d

19. a

20. b

21. b

22. c

23. d

24. c

25. d

26. b

27. c

28. a

29. d

30. c

31. d

32. c

33. b

34. a

35. d

36. b

37. d

38. c

39. c

40. d

41. b

42. a

43. c

44. a

45. b

1.

|Advantage |Disadvantage |

|Greater room for interpretation |Lacks direction in answers |

|Can find new information |Tough to “score” |

|Responses in “own words” so closer to what they really mean |Experimenter biases |

2. Bar graph/chart

[pic]

Figure 1. Approval Ratings for Capital Punishment Between Women and Men.

3. 1) select IV conditions that are substantially different from one another

if they are too close they may not be differentiated – i.e. they show same results

e.g. use 0 and 100mg of alcohol rather than 0 and .01mg (the latter is too similar)

2) have participants experience a condition sufficiently for it to influence behavior

if the treatment is too short/small then sometimes they don’t really remember it, don’t get to really feel it, or really experience it

e.g. if you give 0.1mg of alcohol they probably won’t know they’ve had alcohol

if you do a study on music’s influence on mood, the music should last a while to let them experience it – if it lasts 5 seconds then it’s not likely to be of any influence (and you may commit a type II error and say that something is not there when it really is)

3) prevent diffusion of treatment

if participants go out and tell everyone else what happened it can change their

expectations, experiences, and responses

e.g. if you are giving a reaction time test and they go tell their friends, they might take it as a competition and try extra hard, or get so tense they underperform – then your IV has less of an impact on the outcome

4. nominal

chi square

mode

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download