3122 Final Exam

It is almost always best to use: A. 5 or 7 point rating scales B. Simple rating scales of 1-3 for children C. 10 or more point rating scales since they provide more range of responses D. Rating scales that do not provide a neutral or no opinion response

A. 5 or 7 point rating scales

When a measure relates consistently to other measures of the same concept it shows ____ validity. A. Convergent B. Divergent C. Face D. Internal

A. Convergent

The Pearson product-moment correlation coefficient (r) is unable to detect A. Curvilinear relationships B. Positive linear relationships C. Negative linear relationships D. Instances of no relationship

A. Curvilinear relationships

Any event that occurs between the first and second measurement period but is not part of the manipulation is referred to as a ______________ effect. A. History B. Maturation C. Testing D. Regression toward the mean

A. History

A multiple baseline design is often used when... A. It is impossible or unethical to effect a reversal of treatment B. A random assignment to groups was done incorrectly C. The researcher wants to correlate many behaviors with the one of interest D. The chances are high there will be a high mortality rate among the participants

A. It is impossible or unethical to effect a reversal of treatment

In a perfect positive relationship between two variables A. Knowing an individual's score on one variable will allow us to predict exactly what his or her score will be on the other variable B. The correlation coefficient would range between -1.0 to +1.0 C. All of the scores on one variable will be the same as the scores on the other variable D. All of these

A. Knowing an individual's score on one variable will allow us to predict exactly what his or her score will be on the other variable

Which one of the following scales of measurement lacks numeric properties? A. Nominal B. Ordinal C. Interval D. Ratio

A. Nominal

The use of existing natural groups of participants often results in A. Nonequivalent groups B. Equivalent groups C. Many independent variables D. Equal numbers of males and females

A. Nonequivalent groups

Inferential statistics allow us to arrive at conclusions about the ____ on the basis of ___ data. A. Population, sample B. Sample, population C. IV, DV D. DV, IV

A. Population; sample

What is the difference between true experimental designs and quasi-experimental designs? A. True experimental designs use random assignment while quasi-experimental designs do not B. True experimental designs use control groups while quasi-experimental designs do not C. Quasi-experimental designs use random assignment while experimental designs do not D. Quasi-experimental designs use a control group while experimental designs do not

A. True experimental designs use random assignment while quasi-experimental designs do not

In a multiple baseline design, in order to conclude that a treatment is effective, a behavior change must be observed A. With multiple participants B. Under multiple circumstances C. When a treatment is removed and reintroduced multiple times D. All of the above

A. With multiple participants

Which of the following best represents use of an interval scale? A. Identifying the order of finish for runners in a marathon B. Assessing students' ratings of their professors performance on a five point scale from "poor" to "excellent" C. Measuring the number of boxes of cookies sold by scouts on the west versus the east side of town D. Naming the different brands of cars seen in the school's parking lot

B. Assessing students' ratings of their professors performance on a five point scale from "poor" to "excellent"

When a researcher ____ the probability of making a Type I error, she _____ the probability of making a Type II error. A. Increases; Increases B. Decreases; Increases C. Decreases; Decreases D. Decreases; Does not affect

B. Decreases; Increases

Choosing a sample size should be dictated by ___________. A. The researcher B. Desired probability of correctly rejecting the null hypothesis C. The number of participants that are available D. The type of statistic that is being used.

B. Desired probability of correctly rejecting the null

A correlation coefficient indicates the ____ and ____ of the relationship between two variables. A. Nature; shape B. Direction; strength C. Scatter; strength D. Direction; Distribution

B. Direction; strength

Dr. Walters finds that students who work less than 10 hours a week have significantly higher test scores than students who work more than 10 hours a week. In order to determine the magnitude of the effect of work hours on test scores, she should calculate a(n) A. Critical value B. Effect size C. Null calculation D. Degree of freedom

B. Effect size

The ____ refers to the strength of association between variables A. Statistical index B. Effect size C. Standard deviation D. Linear degree

B. Effect size

You are constructing a test of knowledge of research methods. In doing so, you use your textbook for this class to devise true-false questions on various aspects of research methods. Without conducting any research, you can be most certain of which validity of this test? A. Construct B. Face C. Criterion D. Divergent

B. Face

____ and ____ validity focus on assessing whether the items in a measure actually represent the construct being measured. A. Convergent; predictive B. Face; Content C. Content; Convergent D. Concurrent; Convergent

B. Face; Content

What is the difference between an interval and a ratio scale? A ratio scale _____ while an interval scale does not. A. Uses equal intervals B. Has an absolute zero C. Indicates order D. Gives numerical information

B. Has an absolute zero

When there is no effect of the IV on the DV, the effect size statistic will A. Be equal to the degrees of freedom B. Have a value of 0 C. Have a value of -1.0 to +1.0 D. Vary depending on your alpha level

B. Have a value of 0

Jay calculates the 95% confidence interval for the difference between means. He finds the interval ranges from 1.85 to 4.08. What might Jay conclude from this finding? A. 95% of the means have values of 1.85 and 4.08 B. He is 95% certain that the interval 1.85 to 4.08 contains the difference between means. C. The results will not be significant 95% of the time. D. 95% of the population will be confident in his results.

B. He is 95% certain that the interval 1.85 to 4.08 contains the difference between means.

One way to increase the reliability of a measure is it A. Calculate a correlation coefficient B. Increase the number of items in the measure C. Decrease the number of items in the measure D. Be sure there is variability between true score and measurement error

B. Increase the number of items on the measure

Results are generally said to be statistically significant when there is a ____ probability of the results occurring if the population means are actually equal. A. High B. Low C. Specifiable D. None of these

B. Low

A teacher writes the results of a test on the board: 7 students received A's. 10 students received B's, 18 students received C's, 4 students received D's and 1 student received an F. The grade of C would represent which measure of central tendency? A. Mean B. Mode C. Median D. Standard Deviation

B. Mode

If you had been asked to rate a new movie on a "thumbs-up" scale with 3 thumbs up as academy-award material, 2 thumbs up as television quality, and 1 thumb up as straight to DVD, you would be employing a(n) _____ scale of measurementf. A. Nominal B. Ordinal C. Interval D. Ratio

B. Ordinal

A researcher measures the time it takes for subjects to press a button following a signal. This is a(n) ________ measure. A. Nominal scale B. Ratio scale C. Ordinal scale D. Interval scale

B. Ratio scale

A type I error is a decision to A. Reject the null hypothesis when it is false B. Reject the null hypothesis when it is true C. Accept the null hypothesis when it is true D. Accept the null hypothesis when it if false

B. Reject the null hypothesis when it is true.

When you took an I.Q. test last week, your score was 112. This week, taking the same test, your I.Q. was 96. This I.Q. test seems to lack A. Validity B. Reliability C. Reactivity D. Generalizability

B. Reliability

If Jack proposes that "there is a difference in hiring preferences between veterans and non-veterans," this represents the ____ hypothesis. If he proposes that "there is no difference in hiring preferences between veterans and non-veterans," this represents the _____ hypothesis. A. Null; research B. Research; null C. Inferential; descriptive D. Descriptive; inferential

B. Research; null

Imagine that a survey reports that 57% of individuals prefer the Democratic candidate and that 43% report that they prefer the Republican candidate. The survey reports a confidence interval (CFI) of 95% +/-3. What can we conclude from these results? A. That the republican candidate will win B. That we have a 95% chance of making a correct prediction about the election C. That we have a 5% chance of making a correct prediction about the election D. That there is no way of knowing which candidate has a higher likelihood of being elected.

B. That we have a 95% chance of making a correct prediction about the election

The null hypothesis is rejected whenever A. Past studies prove it to be wrong B. There is a low probability that the obtained results could be due to random error C. There is a high probability that the obtained results could be due to random error D. The researcher is convinced that the variable is ineffective in causing changes in behavior

B. There is a low probability that the obtained results could be due to random error

A negative value of r means that A. There is no relationship between the two variables B. Those who score high on one variable tend to score low on the other C. Those who score high on one variable tend to score high on the other D. There was a mistake in calculating the value of r

B. Those who score high on one variable tend to score low on the other

Rejecting the null hypothesis when it is true is called a _____ error, whereas not rejecting a false null hypothesis is called a _______ error. A. Type II; Type I B. Type I; Type II C. Minor; major D. Significant; nonsignificant

B. Type I; Type II

The Census Bureau reports that the median US household income in 2009 was $50.229. If the average income for your community is very close to the national average and most people make close to $50.229, we could conclude that _____? A. Only the modal score is being used B. Your community has a small standard deviation in household income C. Your community has a large standard deviation in household income D. Your community has a large range in household income.

B. Your community has a small standard deviation in household income

Sandra has developed a program designed to increase reading comprehension scores in 6th graders. She randomly selects 3 students and has them participate in her program. When she compares the mean score from the students who completed the program to 3 students who did not participate in the program, she finds no significant difference between their mean scores. What is most likely the reason for the non-significant finding? A. Too strong of a manipulation B. The use of 6th grade children C. A small sample size D. A true research hypothesis

C. A small sample size

Dr. Stefanek finds that when he smiles and makes eye contact with Sam, she becomes more responsive to his questions. He tries the same behavior with Andrew, Bri, and Christina and finds that is also influences their responses to questions. What type of since-case design did Dr. Stefanek employ? A. Across situation multiple-baseline design B. Across behaviors multiple-baseline design C. Across subjects multiple-baseline design D. Across subjects ABA design

C. Across subjects multiple-baseline design

Which of the following is true with regard to single case design? A. It may be difficult to generalize the results B. Manipulation may be effective in changing the behaviors of some participants but not others C. All of the above D. None of the above

C. All of the above

The reactivity of a measure is reduced when you A. Use an unobtrusive measure B. Allow the participant to get accustomed to being observed C. Both A and B D. Neither A nor B

C. Both A and B

Research that examines the relationship between a measure and the criterion behavior at the same time is assessing which type of validity? A. Face B. Divergent C. Concurrent D. Convergent

C. Concurrent

When a scale designed to measure honesty actually measures a person's honesty, the scale is said to have A. Reactivity B. Reliability C. Construct Validity D. Consistency

C. Construct Validity

_____ is an indicator of reliability in which the researcher calculates the correlation of each item with every other item. A. Test-retest B. Split-half C. Conbach's Alpha D. All of these

C. Cronbach's Alpha

Renisha goes to several elementary schools where she tests students who are in the first, third, and sixth grade to examine the effect of age on a reasoning ability task. Renisha used the ___________ method. A. Longitudinal B. Sequential C. Cross-sectional D. Time-analysis

C. Cross-sectional

Jack finds his measure of math ability is not related to a person's language skills. This finding illustrates which type of validity? A. Predictive B. Face C. Discriminant D. Convergent

C. Discriminant

Brewster measures the height and age of four and five year-olds. To his surprise, he finds no correlation between height and age. What is most likely responsible for his results? A. Age and height are not correlated B. A curvilinear relationship exists between the two variables C. He has restricted the range of the variables D. There is too much variability in the sample to accurately calculate a correlation coefficient

C. He has restricted the range of the variables

A correlation coefficient can be used when both variables use___? A. Different scales of measurement B. Nominal scale properties C. Interval or ratio scale properties D. Ordinal and interval scale properties

C. Interval or ratio scale properties

How does sample size affect determinations of statistical significance? The _______ the sample, the ________. A. Larger; greater probability that the variable has an effect B. Smaller; greater probability that the variable has an effect C. Larger; the more confident you can be in your decision to reject or retain the null D. Smaller; the more confident you can be in your decision to reject or retain the null

C. Larger; the more confident you can be in your decision to reject or retain the null hypothesis

An interval scale is preferable to an ordinal scale because A. Simpler statistics can be used B. It rank orders individuals on some characteristic C. Sophisticated statistics can be used D. It allows the measurement of individual differences

C. Sophisticated statistics can be used

What is the difference between descriptive and inferential statistics? Descriptive statistics _______ while inferential statistics ________. A. Use ratio data, use nominal data B. Use nominal data, use ratio data C. Summarize data; determine the probability that results are due to chance D. Determine the probability that results are due to chance; summarize data

C. Summarize data; determine the probability that results are due to chance

When he analyzes the difference between two means, Professor Demento finds an effect size of .85 using the statistic Cohen's d. Professor Demento can conclude A. 85% of the effect on the DV is due to the manipulation B. There is a correlation of .85 between the IV and DV C. The means are separated by a .85 standard deviation D. The results would only occur 85% of the time

C. The means are separated by a .85 standard deviation

Which significance level would minimize the probability of a Type I error? A. .25 B. .10 C. .05 D. .01

D. .01

Face to Face interviews are: A. Almost always the best way to gather information about attitudes and opinions B. Particularly good for gathering information about sensitive topics C. The quickest and least costly way to gather the highest quality of information. D. A less preferred way for gathering information about sensitive topics.

D. A less preferred way for gathering information about sensitive topics.

A difference between an interval scale and a ratio scale is A. An interval scale has equal intervals; a ratio scale does not B. A ratio scale has equal intervals; an interval scale does not C. An interval scale has an absolute zero point; a ratio scale does not D. A ratio scale has an absolute zero point; an interval scale does not

D. A ratio scale has an absolute zero point; an interval scale does not

A Type II error is a decision to A. Reject the null hypothesis when it is false B. Reject the null hypothesis when it is true C. Accept the null hypothesis when it is true D. Accept the null hypothesis when it is false

D. Accept the null hypothesis when it is false

A measure is reliable if it: A. Results in similar scores for the same person B. Contains a large amount of true score C. Contains little measurement error D. All of the above

D. All of the above

An "operational definition" of the variable "anxiety" might be: A. A physiological measure of sweating B. A score on a reliable and valid measure of an anxiety measure C. The number of "ah's" and "Um's" in a speech D. All of these

D. All of these

Confidence intervals are often calculated when examining differences between means. The confidence interval A. Defines the most likely range of actual population values B. Is an alternative way of thinking about statistically significant differences C. Allows a greater understanding of the meaning of your data D. All of these

D. All of these

The range and standard deviation are both A. Measures of variability B. Descriptive statistics C. Useful ways to summarize data D. All of these

D. All of these

Focus group interviews: A. Should be used before any survey B. Should ensure that a representative sample is used for each focus group C. Are a preferred way of testing your hypothesis D. Are often used to generate hypotheses

D. Are often used to generate hypotheses

Non-experimental designs may differ from experimental designs by: A. Not assigning subjects to groups randomly B. Not manipulating and dependent variables C. Neither A nor B D. Both A and B

D. Both A and B

To assess the reliability of a measure, one should ___ the measures. A. Directly observe the amount of true score in B. Directly observe the amount of measurement error in C. Systematically study the variables in D. Calculate the correlation coefficient between scores on

D. Calculate the correlation coefficient between scores on

______ is a type of correlation coefficient that indicates the ______ the effect of the IV. A. t ; difference in B. t ; magnitude of C. Effect size r ; difference in D. Effect size r ; magnitude of

D. Effect size r ; magnitude of

The correlation coefficient A. Indicates the amount of spread of scores in the distribution B. Is a measure of central tendency C. Is a measure of variability D. Is a statistic that describes how strongly variables are related to one another.

D. Is a statistic that describes how strongly variables are related to one another.

If we say we have statistically significant results, we mean the results are A. Very important B. Meaningless C. Likely to be due to chance differences between the groups D. Likely to be due to true differences between the groups

D. Likely to be due to true differences between the groups

The Terman Life Cycle Study began in 1921 and tracked California school children with particular intelligence scores. This study measures aspects of the individual's' cognitive and social development until their death. This is an example of a ____________. A. Cross-sectional method B. Interrupted time series design C. Single case experimental design D. Longitudinal study

D. Longitudinal study

Every test score is thought to have two components. In a score from a reliable test, which component should be relatively low? A. Validity B. Reliability C. True Score D. Measurement Error

D. Measurement Error

A consumer analyst asks participants to rate the comfort of the ride for two brands of all-terrain tires: Trail Cushion and Mud Handler. Trail Cushion was rated more comfortable with a mean of 5.5 than Mud Handler with a mean of 4.3. The Type I error would be to conclude that Trail Cushion was A. More comfortable than Mud Handler when a true difference in comfort exists B. No more comfortable than Mud Handler when Trail Cushion is actually more comfortable C. No more comfortable than Mud Handler when no differences in comfort exists D. More comfortable than Mud Handler when the two tires are identical in comfort

D. More comfortable than Mud Handler when the two tires are identical in comfort.

Jim examines the effect of type of music (jazz, rock, rap) on task performance. Type of music represents which type of measurement scale? A. Ratio B. Interval C. Ordinal D. Nominal

D. Nominal

Dr. Devine is studying the effect of exercise on cholesterol level. She first measures her patient's' cholesterol level before recommending an exercise program and after one month of participating in an exercise program, she measures their cholesterol level again. What type of research design has Dr. Devine employed? A. Between-groups design B. One-shot case study C. Missing control group design D. One group pretest-posttest design

D. One group pretest-posttest design

Which statistical test would be most appropriate to examine the relationship between temperatures and number of ice-cream cones sold during the month of July? A. Chi-square B. Analysis of Variance C. t D. Pearson Correlation

D. Pearson Correlation

The advantage of reporting effect size is it A. Represents the amount of variability in one variable that can be accounted for by another variable B. It can be represented in a pie chart C. Is more accurate than the correlation coefficient D. Provides a scale of values that is consistent across all types of studies

D. Provides a scale of values that is consistent across all types of studies

Tiari is comparing the heart rates of a group of former smokers to non-smokers after they have walked on a treadmill for 15 minutes. This would be an example of a A. Program evaluation B. True experiment C. Time series design D. Quasi-experimental design

D. Quasi-experimental design

Correlating the total score of the first twenty questions on a test with the total score of the last twenty questions on a test is an example of what type of reliability? A. Test-retest B. Alternative-forms C. Item-total D. Split-half

D. Split half

In alternative forms reliability, different versions of the same test are given to ____ at ____ in time A. Different individuals; one point B. Different individuals; two points C. The same individuals; one point D. The same individuals; two points

D. The same individuals; two points

Which statement is least correct regarding the correlation coefficient? A. The absolute size of r indicates the strength of the relationship B. The values of r can range from -1.0 to +1.0 C. The correlation coefficient indicates whether there is a positive linear or negative linear relationship D. The sign of the correlation coefficient indicates the strength of the relationship

D. The sign of the correlation coefficient indicates the strength of the relationship.

Jenny reports that individuals who follow her diet plan lose more weight than individuals who follow Richard's diet plan. In actuality, there is no difference in weight loss between those on Jenny's versus those on Richard's plan. Jenny's claim illustrates a _________ error. A. Type IV B. Type III C. Type II D. Type I

D. Type I

Fred has concluded that there is no difference in driving ability between drivers who have consumed 1 versus 3 cans of beer. However, there really is a difference in ability between drivers. Fred has made a(n) _________ error. A. Null B. Alternative C. Type I D. Type II

D. Type II

Measures of ______ indicate how scores are spread out in a distribution, while measures of ____ indicate how a sample scores as a whole. A. Error; true score B. Probability; significance C. The mode; the median D. Variability; Central Tendency

D. Variability; Central Tendency

Nonprobability sampling: A. Includes haphazard or convenience sampling B. Is the best way to sample due to cost and time C. May be likely to introduce bias into the findings D. Both a and b E. Both a and c

E. Both a and c

True or false: In the multiple-across subjects design, each subject experiences the manipulation at the same time.

False

True or false: In an ABA design, B refers to the baseline period.

False: B refers to the treatment period and A refers to the baseline period

True or false: One-group posttest-only designs lack internal validity.

True

True or false: Quasi-experiments do not include random assignment to conditions.

True