Research & Program Evaluation
Which of these is an example of noninteractive research? a. Historical analysis b. Ethnography c. Case study d. Dramaturgy
a. Historical analysis
Research studies using focus groups and case studies are known as: a. Qualitative designs b. Quantitative designs c. Quasi-experimental designs d. Ex post facto designs
a. Qualitative designs
When conducting research, two counselors administer the same evaluation instrument to one group of clients participating in a support group, but the counselors get markedly different results. What type of problem does this suggest? a. Reliability b. Measurement c. Validity d. Comprehension
a. Reliability
What are the coefficient of determination and the coefficient of non-determination? a. The coefficient of determination is the degree of common variance, and the coefficient of non-determination is the error variance or unique variance b. The coefficient of determination is the degree of unique, variance and the coefficient of non-determination is the degree of common variance c. The coefficient of non-determination is the result of squaring the correlation, and the coefficient of determination is the remainder after subtracting the coefficient of non-determination d. The coefficient of determination is equal to the correlation, and the coefficient of non-determination is equal to the difference between the correlation and 100%
a. The coefficient of determination is the degree of common variance, and the coefficient of non-determination is the error variance or unique variance
A supervisor for a counseling program collects outcomes data for all clients who received services last year. When plotting the distribution, the supervisor notices that clients younger than age 12 have measures skewed to the left. Which of the following is true of distributions skewed to the left (i.e., negatively skewed)? a. The mean is less than the median. b. The mean is greater than the median. c. The mean and the median are the same value. d. The mode is the lowest value.
a. The mean is less than the median.
A person received a t-score of 40. This means that: a. her score fell one standard deviation below the mean. b. her score is very low. c. there is an error. d. her score is higher than average.
a. her score fell one standard deviation below the mean.
The psychodynamic model has a _______ unit of study; the experiential model has a ______ unit of study; the transgenerational model has a _______ unit of study; and the strategic model has a ________ unit of study. a. monadic; dyadic; triadic; dyadic and triadic b. dyadic; monadic; monadic and dyadic; triadic c. monadic; dyadic and triadic; triadic; dyadic d. triadic; monadic and dyadic; dyadic; triadic
a. monadic; dyadic; triadic; dyadic and triadic
Which of the following is true about the correlation coefficient? a. A perfect correlation coefficient can be a positive one but cannot be negative b. A correlation coefficient shows the relationship between two sets of numbers c. A correlation coefficient shows a cause and effect relationship between variables d. With a strong correlation, knowing one score will not help to predict another score
b. A correlation coefficient shows the relationship between two sets of numbers
A counselor wants to measure happiness, and decides that he will keep track of how many times his subjects laugh in the course of a day. He writes down every detail of his study so it can be replicated, specifying the measurement of "smiles" as a way to determine happiness levels. What has the counselor provided? a. A research report b. An operational definition c. A replication report d. An analogy
b. An operational definition
Which of the following tools/methods are characteristic of experimental research designs? a. Survey questionnaires and interviews b. Control groups and randomization c. Use of the correlation coefficient d. Use of numbers to describe groups
b. Control groups and randomization
What does a frequency distribution do? a. It shows the distribution of an audio frequency pitch b. It shows the number of times a particular value occurs c. It monitors the ongoing results of a research study d. Both A and B
b. It shows the number of times a particular value occurs
Which of the following is NOT true about purposeful sampling? a. It may be comprehensive with every case or instance being selected b. The researchers intend to generalize their findings to the population c. The researchers may select examples of only the most extreme cases d. The researchers may select examples of only the most typical cases
b. The researchers intend to generalize their findings to the population
Which of the following is NOT a reason to use nonparametric statistics? a. There is a homogeneous sample b. There is a normal score distribution c. There are two independent samples d. There is nominal (categorical) data
b. There is a normal score distribution
While involved with a research study, a counselor learns that several of her students are using confidential material in an unethical manner. She had no prior knowledge of this, and all of her safeguards for professional practice were appropriate. Is she, as the principal researcher, responsible for the student's behavior? a. No, if professional safeguards were in place, the counselor is not responsible b. Yes, the counselor is ultimately responsible c. Only the students who acted unethically are to be held responsible d. The counselor would only be responsible if she had knowledge of what was occurring and did nothing to stop it
b. Yes, the counselor is ultimately responsible
A researcher conducts a study in which she looks at the effects of using Nicorette gum on smoking cessation. Most likely, her statistical analysis will include: a. Pearson's r. b. a t-test. c. an ANOVA. d. a chi-square.
b. a t-test.
Dr. Miller wants to investigate certain variables in his college class. He is going to test his statement that all of the students in his class with IQ scores above 120 will finish the term with higher grades than all of the students in his class with IQ scores below 120. This statement is an example of a: a. research question. b. directional hypothesis. c. nondirectional hypothesis. d. null hypothesis.
b. directional hypothesis.
Of the following, which is the loosest acceptable p-value bound if a researcher needs to demonstrate that something is 98% statistically significant? a. p < 0.05 b. p < 0.01 c. p < 0.001 d. p < 0.10
b. p < 0.01
A scatter plot depicts: a. a multitude of single scores. b. pairs of scores. c. one score. d. the unscored results of an experiment.
b. pairs of scores.
The best kind of random sampling technique that would include 10% Asian, 10% Hispanic, and 15% African American, as well as individuals from the majority ethnic group, would be a: a. mixed randomized sampling technique. b. stratified sampling technique. c. cluster sampling technique. d. random chance sampling technique.
b. stratified sampling technique.
A researcher reports that p < 0.05 in his study. This means that: a. the probability that the results were obtained in error is less than 5%. b. the probability that no relationship between the independent variable and the dependent variable exists is less than 5%. c. the independent variable is responsible for more than 95% of the observed difference in the dependent variable. d. the study is designed to produce an incorrect conclusion less than 5% of the time.
b. the probability that no relationship between the independent variable and the dependent variable exists is less than 5%.
A researcher reports a correlation coefficient of -.43 between the amount of television viewing by children and the number of times these children are on the honor roll at school. This means: a. too much television viewing causes students' grades to be low. b. there is a moderately negative relationship between how much television a child watches and how often her or his grades are high enough to earn a position on the honor roll. c. there is very little relationship between how much television a child watches and how often her or his grades are high enough to earn a position on the honor roll. d. the more television a child watches, the more often the child's grades are high enough to earn a position on the honor roll.
b. there is a moderately negative relationship between how much television a child watches and how often her or his grades are high enough to earn a position on the honor roll.
Threats to the internal validity of a longitudinal research study are most likely caused by: a. History b. Repeated testing c. Attrition d. Experimenter bias
c. Attrition occurs when subjects naturally drop out of studies
Convergent validation and discriminant validation occur within what type of validity? a. Content validity b. Predictive validity c. Construct validity d. Concurrent validity
c. Construct validity
Behavior changing as a result of just being part of an experiment is called the _____________________ while believing that someone with an extensive vocabulary is better at communicating is called the ________________________. a. halo effect; Rosenthal effect. b. Hawthorne effect; Rosenthal effect. c. Hawthorne effect; halo effect. d. placebo effect; Rosenthal effect.
c. Hawthorne effect; halo effect.
Researchers examining teen dating and relationships consider peer influences, personal beliefs, and environmental factors. This is known as: a. The zone of proximal development b. The pleasure principle c. Reciprocal determinism d. Psychological hedonism
c. Reciprocal determinism
Experiments in which subjects whose scores on the dependent variable are extreme (i.e., too high or too low) are at risk for which of the following threats to internal validity? a. Instrumentation b. History c. Regression d. Selection
c. Regression Regression, or regression toward the mean, is a threat to internal validity that occurs when members are selected based on extremely high or extremely low pretest scores.
There are many confounding variables that can threaten an experiment's validity, but which of the following is a threat to both internal validity and external validity? a. Attrition (mortality) b. Instrumentation c. Selection of subjects d. Experimenter bias
c. Selection of subjects
Which of the following is NOT true of standard deviation? a. Standard deviation describes the variability within a distribution of scores b. Standard deviation is basically the mean of all the deviations from the mean c. Standard deviation is a term of quantity, which is equal to the term variance d. Standard deviation is an excellent way to measure the dispersion of scores
c. Standard deviation is a term of quantity, which is equal to the term variance
Which of these is true of qualitative research? a. This kind of research assumes social elements have a single objective reality b. This kind of research tends to study groups, such as samples or populations c. This kind of research assumes that different realities are socially constructed d. This kind of research tries to avoid influencing its data collection instruments
c. This kind of research assumes that different realities are socially constructed
What is stratified sampling? a. This refers to selecting naturally occurring groups of individuals b. This refers to selecting samples of convenience or of volunteers c. This refers to selecting from major subgroups of the population d. This refers to selecting so that all individuals have equal chances
c. This refers to selecting from major subgroups of the population
Which of the following correctly states the relationship between type I and type II errors? a. Type I error and type II error will both decrease if the significance level goes down b. Type I error will increase and type II error will decrease if the significance level goes down c. Type I error will decrease and type II error will increase if the significance level goes down d. Type I error and type II error will both increase if the significance level goes down
c. Type I error will decrease and type II error will increase if the significance level goes down
Research that compares findings across many studies is known as: a. quasi-experiment. b. survey method. c. meta-analysis. d. comparative research.
c. meta-analysis.
If a researcher who found a negative correlation between the amount of TV viewing done by children and academic performance were to graph her results, she would use a: a. normal bell curve. b. positively skewed curve. c. scatterplot. d. negatively skewed curve.
c. scatterplot.
A researcher looks at one subject across time and takes numerous measurements throughout the process. This is known as a(n): a. AB design. b. ABAB design. c. time-series or continuous measurement design. d. correlational design.
c. time-series or continuous measurement design.
Which group shows suggested minimum sample sizes for the kinds of research named? a. 25 for experimental research, 10 for correlational research, and 50 for survey research b. 5 for experimental research, 15 for correlational research, and 25 for survey research c. 20 for experimental research, 30 for correlational research, and 1000 for survey research d. 15 for experimental research, 30 for correlational research, and 100 for survey research
d. 15 for experimental research, 30 for correlational research, and 100 for survey research
A t-score has a mean of ____________ and a standard deviation of ______________. a. 100; 15. b. 10; 2. c. 50; 15. d. 50; 10.
d. 50; 10.
In experimental research, the researcher states a null hypothesis. A null hypothesis states that: a. there will be differences found between the experimental and control groups. b. the differences between the experimental and control groups are due to chance. c. there will be no differences between the experimental and control groups. d. Both B and C.
d. Both B and C.
What does "validity" in testing refer to? a. How sure one can be, before the test is taken, of what the outcome will be b. How many samples were used in evaluation of the test c. How consistent the test results are d. How accurate a test is
d. How accurate a test is
Which of the following is true of either inductive or deductive research? a. Deductive research is practical and begins with the real world b. Inductive research originates from previously established theory c. Deductive research is descriptive, correlational, and historical d. Inductive research often tends to lead to the building of theory
d. Inductive research often tends to lead to the building of theory
Which of the following is NOT an accurate statement about how the standard error of measurement is used? a. It is useful for the interpretation of individual test scores b. It can help determine the range where a test score falls c. Every test that is given has its own unique SEM value d. It is calculated after the test has been taken and scored
d. It is calculated after the test has been taken and scored
What is meant by the term "regression toward the mean?" a. It means that most individuals are more likely to score near the mean on most standardized tests b. It means that most individuals' standardized test scores will go down from a pretest to a posttest c. It means that those individuals scoring near the mean on a pretest will score lower on a posttest d. It means that most scoring very high or low on a pretest will score nearer the mean on a posttest
d. It means that most scoring very high or low on a pretest will score nearer the mean on a posttest
Which sampling method involves first dividing a population into subgroups followed by random sampling from each subgroup (e.g., gender, education level)? a. Systemic random sampling b. Cluster sampling c. Simple random sampling d. Stratified random sampling
d. Stratified random sampling
Which of these is true of quantitative research? a. This kind of research tends to use naturalistic observation of individual behaviors b. This kind of research tends to use impressions, feelings or judgments of researchers c. This kind of research has as its primary goal the description of the nature of reality d. This kind of research tends to investigate with a goal of finding causal relationships
d. This kind of research tends to investigate with a goal of finding causal relationships
A correlation coefficient shows: a. how strong the relationship between two variables is. b. the direction of two variables' relationship. c. the degree of relationship between two variables. d. all of the above.
d. all of the above.
If there is a 95% chance that an experiment's results are not due to chance, one might say that the experiment: a. has achieved reliability and validity. b. would create a great scatter plot. c. has a high correlation coefficient. d. is statistically significant.
d. is statistically significant.
