What is the relationship between measurement and abstract constructs?
a. Measurement uses abstract constructs to provide indicators.
b. Abstract constructs provide measurements for indicators.
c. Measurement uses indicators to represent abstract constructs.
Which of the following are types of scales?
a. measurement scale
b. ratio scale
c. percentile scale
d. ordinal scale
e. interval scale
A study was carried out in which the numbers of specific behaviors in a classroom
were counted. What type of measurement scale would be used in this study?
a. ordinal scale
b. nominal scale
Researchers must use previously developed testing instruments for their
measurement purposes.
a. True
b. False
Which of the following should researchers do when developing their own
measurement instrument?
a. Develop their own theory upon which to base indicators.
b. Identify behaviors that can be indicators.
c. Use research or experience to support or revise the instrument.
d. Examine the theory behind the construct.
The objectivity of a test is a function of:
a. the judgments made by scorers.
b. the agreement of answers with a standard.
Which of the following are kinds of achievement tests?
a. norm-referenced tests
b. researcher-made tests
c. aptitude tests
d. performance tests
e. standardized tests
What is the difference between achievement tests and aptitude tests?
a. Achievement tests are norm-referenced.
b. Aptitude tests measure general abilities.
Many common standardized tests are now administered by computer.
a. True
b. False
In objective personality assessments, individuals:
a. are interviewed by an examiner.
b. project their attitudes onto ambiguous stimuli.
c. choose between possible personality types.
d. respond to forced-choice items.
Which of the following are advantages of personality inventories?
a. objectivity
b. simplicity
c. economy
The use of a scale is most appropriate when:
a. determining objectively how personalities differ.
b. measuring students' attitudes about their classes.
Which of the following are advantages of direct observation?
a. It does not require much time.
b. It can be done at low cost.
c. It provides a record of actual behavior.
d. It is appropriate for use with young children.
e. It can be done in natural settings
Observer bias occurs when people being observed behave differently.
a. True
b. False
Which of the following are measurement tools often used in qualitative research?
a. interviews
b. inventories
c. document analysis
d. observation
The concept of validity as used in measurement today mainly refers to the
interpretation of measurements.
a. True
b. False
In testing, validity mainly depends on:
a. the indicators that the test uses.
b. the use for which the test was intended.
What is the basic reason that validity is an important issue in interpreting
educational test scores?
a. Any interpretation of scores must be made using statistical tools.
b. Mathematical accuracy is important in such tests.
c. Test scores are based on indicators that represent constructs
What are the three main categories of evidence that establish the validity of score
interpretations?
a. statistical
b. criterion-related
c. content
d. education-related
e. construct-related
You are seeking an appropriate test for determining whether students have acquired
certain math skills. Verifying validity in which area would be most important for such
a test?
a. construct
b. content
Which of the following are types of validity related to a criterion?
a. face validity
b. predictive validity
c. coefficient validity
d. divergent validity
e. concurrent validity
Which of the following are ways to determine construct-related evidence of
validity?
a. known-groups technique
b. response processes
c. multitrait-multimethod matrix
While searching for a test for measurement purposes in a research study, you find
one that seems to suit your needs. In the section of the test's documentation that
discusses validity, the test author simply claims that the test is valid. What is
missing from this claim?
a. the author's credentials as a statistician
b. an explanation of whether the test is reliable
c. a specification of the uses for which the test is valid
The reliability of a test is most fundamentally an indicator of its:
a. appropriateness for a given use.
b. precision of measurement.
c. accuracy.
d. consistency.
Which of the following could be sources of random error in test scores?
a. a test that contains too few questions
b. a test being too difficult
c. individuals with different abilities to understand the test questions
d. test questions that rely on background knowledge other than what is being tested
e. a test being administered with different instructions each time
In order for a test to be considered reliable, it must first be shown to be valid.
a. True
b. False
What does a true score on a test reflect?
a. a score that shows that the test is a valid indicator of what it measures
b. an accurate measurement of an individual's performance
Which of the following are the main categories of reliability coefficients?
a. equivalent-forms
b. test-retest
c. criterion-referenced
d. content-based
e. internal-consistency
Validity is more difficult to establish than reliability.
a. True
b. False
Which of the following are kinds of questions that need to be answered in order to
establish the validity of a test?
a. the credentials of the test authors
b. the appropriateness of the test content
c. the adequacy of the criteria that are tested
d. the theory behind the test content
Descriptive statistics are used for:
a. collecting data.
b. summarizing information.
What kind of scale ranks individuals according to an attribute?
a. ordinal
Which of the following are types of measurement scales for which the differences
between numbers have meaning?
a. frequency
b. ratio
c. ordinal
d. interval
e. nominal
Which of the following are formats for presenting data graphically?
a. frequency polygon
b. error bar
c. histogram
d. frequency distribution
e. boxplot
Suppose you want to graphically represent the distributions of certain ranges of
scores on a test. What type of graph would be most suitable for this purpose?
a. frequency polygon
b. error bar
c. histogram
Which of the following are measures of central tendency?
a. frequency
b. mode
c. median
d. mean
Why is the median often a better indicator of typical scores than the mean?
a. It takes all of the scores into account.
b. It does not take extreme scores into account.
For which type of measure is the mode the only possible index of central tendency?
a. ordinal
b. ratio
c. nominal
Which of the following are indices of variation in a set of scores?
a. range
b. standard deviation
c. median
d. variance
Standard deviation is calculated as the square root of the mean of the deviations
from the mean.
a. True
b. False
What are the basic elements that are used to calculate a z score?
a. the median
b. the standard deviation
c. variance
d. the mean
e. a raw score
What does the normal curve represent?
a. the distribution of passing scores on a test
b. the mean score as compared to the median
c. naturally occurring distributions
Which of the following are points to keep in mind when interpreting correlation
coefficients?
a. The variability of distributions affects the size of a correlation.
b. Variables that are highly correlated often also correlate to a third variable.
c. Correlation coefficients can be usefully converted to percentages.
d. Correlation typically indicates causation.
e. The value of correlation coefficients is relative to the context of use.
Effect size is a measure of both magnitude and direction.
a. True
b. False
Which of the following are some of the uses of meta-analysis?
a. studying the effects of specific treatments
b. averaging overall achievement for a population
c. comparing effect sizes
d. estimating the relationships among multiple variables
e. integrating the findings of nonexperimental studies
The purpose of sampling is to:
a. generalize from a whole to a part.
b. generalize from a part to a whole.
The goal of statistical inference is to:
a. estimate parameters.
A biased sample is one that is unrepresentative.
a. True
What is the first step in sampling?
a. Identify the target population.
You have been conducting a research study on the classroom habits of fourth-
graders and have concluded that you need to study an additional sample. Since you
need to complete the study by a deadline and have no time to prepare a probability-
based, random sample, you decide to study a single class that is available. Which of
the following sampling methods would this be considered?
a. convenience sampling
Which of the following are steps in quota sampling?
a. Select variables as the basis for stratification.
b. Determine the size of each segment of the population.
c. Select typical cases to fill the quotas.
Which of the following are known laws in sampling errors of the mean?
a. Sampling error is an inverse function of the standard deviation of the population.
b. Sampling error is a direct function of sample size.
c. The expected mean of sampling errors is zero.
d. Sampling errors always occur in nonrandom sample selections.
e. Sampling errors are distributed in a normal or near-normal manner.
Suppose you are testing a behavioral treatment on groups of special education
students. If you are testing the null hypothesis, you are testing whether:
a. the treatment had an effect that was different from what was expected.
b. the treatment has an adverse effect on the experimental group(s).
c. any differences in behavior between groups are due to some factor other
than the treatment.
Rejecting a true null hypothesis can often lead to unwarranted changes.
a. True
Which of the following is one of the differences between a directional test and a
nondirectional test?
a. A decision to use a nondirectional test is made before any other statistical
tests are made.
b. Rejecting the null hypothesis in a nondirectional test requires a smaller z
value.
c. A directional test is best used for comparison of effects.
d. A directional test makes it easier to reject the null hypothesis.
The greater a statistic is than the error term, the less likely it is that it is due to
chance.
a. True
Which of the following terms appear in the equation for the standard error of
the difference between two independent means?
a. the number of subjects in each group
b. the sampling error
c. the mean of the entire population
d. the number of observations
e. the sum of the squared deviation scores in each group
The t test for independent samples is equivalent to what ratio?
a. the observed difference between the means divided by the difference
expected through chance alone
An analysis of variance (ANOVA) test is especially suited for analyzing:
a. the null hypothesis.
b. relationships between multiple variables.
c. data from more than two groups.
What conditions must be met for valid interpretations to be made with a chi-square
test?
a. There are statistically significant differences between groups.
b. Categories of observations are exclusive.
c. Observations are measured as frequencies.
d. Observations are independent.
Powered by TCPDF (www.tcpdf.org)
