The chi-square test is used to determine whether there is a significant difference between

an obtained distribution and an expected distribution

What is the order of complexity of measurement scales from simplest to most complex?

Nominal, ordinal, interval, ratio

Which journal publishes the most counseling research articles in the field?

Journal of Counseling Psychology

A Type I error occurs when

you reject null when it is true

Which of the following is a trend in counseling research?

Qualitative research is getting more attention

mindfulness training; test scores

If a distribution is bimodal, it is likely that

the researcher is working with two distinct populations

Which is true about sampling error?

It means that the sample does not adequately mimic the population.

Joe takes an achievement test. In order to predict his score if he takes it again, you would need to know

the standard error of measurement (SEM)

If an ANOVA yields a significant F value, you could rely on _____ to test significant differences between group means.

Duncan's multiple-range, Tukey's, or Scheffe's test

The terms "synchronic" method and "diachronic" method refer to

cross-sectional or longitudinal studies.

Counterbalancing means

switching the order in which stimuli are presented to a subject in a study

What is the benefit of standards scores (percentiles, t-scores, stanines, etc.) over raw scores?

They allow you to analyze data in relation to the bell curve.

Which is true about the ordinal scale?

provides relative placement or standing

A platykurtic distribution looks

a sort of flat American football lying on its side

studbud

Ch 9 Research and Program Evaluation

81 termsStudBud Administration60 plays

These are alternate questions on the Research and Program Evaluation chapter.

Flashcards81 cardsFPractice quizPHost liveL

Questions 81

Answers

1
The y axis is also called the _______ and is used to plot the frequency of the _____.
ordinate; independent variable
vertical axis; IV
abscissa; DV
ordinate; dependent variable
2
A two-tailed t test
red and blue are both true
is often called a nondirectional experimental hypothesis
has less predictive power than the one-tailed t test
Neither of the answers are true
3
The chi-square test is used to determine whether there is a significant difference between
the mode and the mean
the median and the mode
an obtained distribution and an expected distribution
the median and the mean
4
The ANCOVA
All of the above
helps to control for variables that may intervene in the IV-DV relationship
allows you to correct for possible covariates in the different samples
stands for Analysis of Covariance
5
A distribution curve that is higher at the peak and narrower in range than a normal bell curve is called a
a bimodal distribution
Olympic curve
platykurtic distribution
leptokurtic distribution
6
What is the order of complexity of measurement scales from simplest to most complex?
Nominal, ratio, interval, ordinal
Interval, ratio, nominal, ordinal
Nominal, ordinal, interval, ratio
ratio, interval, ordinal, nominal
7
Which journal publishes the most counseling research articles in the field?
Colossal Counseling Journal
Journal of Counseling and Development
Journal of Counseling Psychology
Journal of Multicultural Counseling and Development
8
Which of these tests are nonparametrical (not evenly distributed) measures?
All of the above
Mann-Whitney U test, or just U test
Wilcoxon signed-rank test for matched pairs
Soloman and the Kruskal-Wallis H test
9
A Type I error occurs when
you have a beta error
you fail to use a test of significance
you reject null when it is true
you accept null when it is false
10
(see below)
contaminated
confounded/flawed
both blue and yellow above
enhanced
11
A _____ design seeks to find a relationship between an IV and a DV some time after the action or event has occurred.
experimental
a cohort study
correlational
causal-comparitive
12
Which of the following is a trend in counseling research?
More studies are submitted by single, field-based authors
Qualitative research is getting more attention
Less attention to multicultural issues
More studies relying on children as subjects
13
Which illustrates the function of the nominal scale?
A child's body temperature
The score on the Beck's Depression inventory
A grade received on a test
The race of various clients
14
The average score is 200. SD is 25. Therefore, a score of 230 is
close enough to be considered the mean
+ or - 1 SD of the mean
too far away to fall on the normal distribution curve
+ or - 2 SD of the mean
15
(see below)
mindfulness training; test scores
school counselor; students
anxiety; mindfulness training
standardized test scores; mindfulness training
16
If you cannot randomly assign subjects to both experimental and control groups, the research is considered
lame
a quasi-experiment
qualitative
a pilot study
17
If a distribution is bimodal, it is likely that
the data does not represent valid information about the population
the researcher is working with two distinct populations
the curve will be shaped like a symmetrical bell
the curve will be normal
18
a t-score of 60 is the same as
There is not enough info to answer this question
a z-score of +1.0
the average
a standard deviation of .6
19
(see below)
a Type II error
a Type I error
a null hypothesis
a waste of time
20
Which is true about the ratio scale?
It is an interval scale with a true zero point
Addition, subtraction, multiplication, and division can all be utilized
All of the above
The intervals between each point are equal to each other
21
Type I and Type II errors are called ______ and ______ respectively.
What do you think I am, stupid?
beta; alpha
alpha; beta
.01 and .05
22
When the comparison group lowers their performance because they resent being denied the experimental treatment
it is called "compensatory equalization".
it is called the sore loser effect.
Both red and blue are correct.
it is called "resentful demoralization of the comparison group".
23
The study that would best rule out chance factors would have a significance level of P =
.001
.05
.01
.08
24
Which is true about sampling error?
It means that the sample does not adequately mimic the population.
All of the above
It can only be avoided with simple random sampling.
It is more likely to occur with large samples
25
The mean of the Binet IQ test is
5
50
100
500
26
In an experiment, if DVs were truly influenced by IVs and not other factors, the study is said to have
reliability
external validity
internal validity
relevance
27
Parsimony in counseling research is similar to
Lloyd Morgan's 1894 Canon
Occam's Razor
the principle of economy
all of the above
28
(see below)
The Halo effect
a self-fulfilling prophecy
The Rosenthal effect
The Hawthorne effect
29
Joe takes an achievement test. In order to predict his score if he takes it again, you would need to know
the range of scores in his class
the standard error of measurement (SEM)
the standard deviation
the mode for the test
30
If an ANOVA yields a significant F value, you could rely on _____ to test significant differences between group means.
percentile rank
summative or formative evaluation
Duncan's multiple-range, Tukey's, or Scheffe's test
one- and two-tailed t tests
31
(see below)
ANOVA
two-way ANOVA
t test
mean
32
When the choice of answers to a survey question are strongly agree, agree, disagree, & strongly disagree it is called a
Solomon test
a projective measure
a deductive measure
Likert scale
33
ANOVA
can be used in trend analysis
is used to see if performance on one variable mimics the same on another
All of the above
means Analysis of Variance
34
The terms "synchronic" method and "diachronic" method refer to
using either one or two independent variables in a research design.
looking for similarities or looking for differences.
cross-sectional or longitudinal studies.
using one subject group or two subject groups in a research design.
35
Counterbalancing means
the same as multiple treatment interference
a research design in which past and current stimuli are considered
switching the order in which stimuli are presented to a subject in a study
the romantic tension that can occur between subject and experimenter
36
What is the benefit of standards scores (percentiles, t-scores, stanines, etc.) over raw scores?
They allow you to analyze greater amounts of data
They allow you to analyze data in relation to the bell curve.
They allow you to analyze data for which you cannot obtain a raw score.
There is no benefit. Raw scores are more useful.
37
What is an example of an interval scale?
an IQ test
categorization of religion on a demographic survey
the number of calories consumed each day
all of the above
38
In observation research when the subject's behavior is influenced by the process of being watched it is called
both a and b
a "reactive effect" or "reactivity" of observation/experimentation
The Hawthorne effect
a nocebo
39
Which is true about the ordinal scale?
all of the above
provides relative placement or standing
delineates absolute differences
indicates equal differences between points on the scale
40
What is the term that refers to 25% of a distribution?
quartile
a fourth
percentile
quarter
41
The letter P, in relation to a test of significance, stands for
proportion
population parameter
portion
probability
42
When P, or the level of significance, is set at .05 it means
results would occur via chance only 5 times in 100
results would occur via chance as little as 5 times in 1000
there is a 95% chance the results reflect reality and not a mistake
both red and blue
43
When a researcher observes behavior but does not intervene, it is called
participant observation
the Hawthorne effect
qualitative research
naturalistic observation
44
A platykurtic distribution looks
a very tall, skinny version of the bell curve
a two-humped camel's back
a normal bell curve
a sort of flat American football lying on its side
45
When subjects strive to prove that a treatment (that could threaten their livelihood) is not effective, it is called
both red and yellow
demoralization of the comparison group
the John Henry effect
compensatory rivalry
46
When using standard deviation, about ____ of the cases will be within 1 SD of the mean.
99%
68%
95%
100%
47
A true experiment in which the groups are not randomly assigned is called
correlational research
qualitative research
a double blind study
a causal comparative design
48
Which is true about factor analysis?
It can narrow down the most important things among many
it is parsimonious
all of the above
It can summarize a lot of variables
49
To be considered accurate, a survey should have a _____ return rate.
95%
50-75%
15-40%
5%
50
In a ______ the subjects are matched in regard to any variable that could be "correlated" with the DV.
independent groups design
deductive logic design
Mann-Whitney U test, often just called the U test.
matched design
51
A Type II error
means you reject the null hypothesis when it is true
is also called a beta error
both red and yellow
means you accept the null hypothesis when it is false
52
You observe the success of CBT on many clients with depression and conclude CBT is effective treatment for depression.
This is an example of deductive logic or reasoning
This is depressing
This is an example of inductive logic or reasoning
You shouldn't be doing research on your own clients.
53
Statistical regression toward the mean
indicates that extreme scores will get more average if tested again.
is a problem for internal validity
Neither a nor b
Both a and b are true
54
Which of the following is NOT a trend in counseling research
Action research
Field-based professionals submitting more contributions
Using the internet to conduct an experiment
Neuroscience guiding diagnosis and treatment
55
The x axis is used to plot the IV scores. The x axis is also called the
DV
vertical axis
abscissa
56
Which of the following is a NOT trend in counseling research?
Large sample sizes are getting priority over single-subject studies
Cohen's d effect size statistic is used to gauge relationship strength
Counselors want more APA training to submit journal articles
Meta-studies are being used to summarize findings
57
To do a true experiment, the researcher needs
an experimental group and a control group
to manipulate both the IV and the DV
all of the above
at least 100 subjects
58
______ attempts to ascertain how well a goal has been met. _______ is ongoing while the program/treatment is underway.
Ipsative evaluation; normative evaluation
Summative evaluation; Formative evaluation
None of the above
Longitudinal research; Cross-sectional research
59
A z-score is
the standard deviation (SD)
a standard score
all of the above
the square root of the variance.
60
If the researcher in the previous question utilized two IVs, then the statistic of choice would be the
t test
two-way ANOVA or MANOVA
media
ANOVA
61
What is Ipsative assessment?
Assessment of individual progress
Assessing against peer progress
Initial Assessment
1:1 assessment
62
When a research design uses different subjects for each condition (exposure to the IV, and no exposure) it is called
indecent exposure
between-subjects design
within-subjects design
carcinogenic
63
Which is true about stanine scores?
all of the above
"Stanine" comes from "standard" and "nine"
A stanine score of 9 represents the highest portion of the curve.
They divide the distribution into 9 equal parts.
64
In a ___________ there will be proportionate representation of all important subgroups within the population
horizontal sample
chain-referred sample
random sample
stratified random sample
65
A z-score of 2.5 means
all of the above
2.5 SD above the mean
the same as a t-score of 75
the same as a CEEB score of 750
66
On most IQ tests, the mean is ____ and the SD is _____.
100; 10
50; 10
100; 15
1000; 50
67
Occam's razor suggests that experimenters interpret the results
using a clinical interview
in the most complex manner
using a correlation coefficient
in the simplest manner
68
A one-tailed t test
is called a "directional experimental hypothesis"
places the rejection area at one end of the distribution
all of the above
hypothesis specifies that one average mean is larger than another
69
To complete a t test you would consult a tabled value of t. To see if significant differences exist in an ANOVA,
consult the chi-square
consult a table for F values
consult a table of t values
consult the median
70
In the social sciences, the accepted probability level, or confidence level, is usually
.05 or less
1.0 or higher
.0001 ir kess
.05 or higher
71
A pictorial diagram of two variables being correlated is called a
sociogram
histogram
scattergram
bar graph
72
To calculate the inclusive range you would
subtract the lowest number from the highest number.
subtract the lowest number from the highest number and add 1.
either way because inclusive range is no different than exclusive range
73
The lower the significance (confidence)level a researcher sets for results,
the greater the chance of a Type II , or beta error
the greater the chance of a Type I error
it makes no difference in an alpha or beta error
the harder it is to conduct the research
74
Any bit of knowledge that the subject in an experiment is aware of that can influence their behavior is called a ______
both red and blue.
demand characteristic, and can confound an experiment.
demand characteristic and deception has been used to mitigate it.
spurious effect.
75
The variable you manipulate or control in an experiment is the
IV (independent variable)
the one that shows your results
the variable you will measure to determine the outcome
DV (dependent variable)
76
Statistically, to compare a control group to the experimental group, the researcher will need
only descriptive statistics like mean, median & mode
a test of significance, like a t test
a correlation coefficient
percentile rank
77
A hypothesis is an educated guess that can be tested. Hypothesis testing is most closely related to the work of
Karissa Kephart
Sigmund Freud
Robert Hoppock
R.A. Fisher
78
In order to reduce the chance of a Type I or II error, the researcher can
use an internet-based statistical program for calculations
increase the sample size in the experiment
utilize interviews instead of surveys
use stratified random sampling
79
___ occurs when a trait which is not being evaluated influences a researcher's rating on another trait.
The Halo effect
A self-fulfilling prophecy
The Rosenthal effect
The Hawthorne effect
80
P = .05 really means that
there is a 95% error factor
differences do exist; results will be the same 95% of the time
differences do exist; results will be the same 99% of the time
there is a 5% error factor
81
That test of significance (like a t or a z) refers to how confident we are that the ________ did not occur by chance.
randomization of the sample
differences between experimental and control group, as a result of the IV
effect of the DV
relevance of the results

Ch 9 Research and Program Evaluation Flashcards | StudBud