PSYCH ASS W1

How do states different from traits?

A. A trait is biologically determined, whereas a state in environmentally determined.

B. A trait is measurable, whereas a state is not.

C. A trait is relatively enduring, whereas a state is relatively short-lived.

D. A trait is unchangeable, whereas a state is easily influenced.

C. A trait is relatively enduring, whereas a state is relatively short-lived.

Typically, which of the following is the primary objective of psychological testing and assessment?

A. to measure a trait

B. to predict future behavior

C. to obtain a score on a test

D. to observe a sample of behavior

B. to predict future behavior

An assumption inherent in classical test theory (CTT) is that

A. each test-taker has a true score that would have been obtained if not for measurement error.

B. testtakers can be ranked according to the level of the trait or ability that they exhibit in much the same way that rankings can be made by height.

C. measurement can be perfectly accurate if the measuring tool is well-constructed.

D. All of these

A. each test-taker has a true score that would have been obtained if not for measurement error.

This tool is used to estimate or infer how far an observed score deviates from a true score, and it is called

A. a standard deviation.

B. a measure of central tendency.

C. the variance.

D. a standard error of measurement.

D. a standard error of measurement.

The statistic known as the standard error of measurement is BEST associated with which of the following?

A. validity

B. reliability

C. test standardization

D. test administration

D. test administration

A distribution of raw scores from a test administration is normally distributed. The test user wishes to summarize these data using percentiles. A potential problem here is that score differences in the middle area of the distribution

A. may be minimized.

B. may be exaggerated.

C. may not be accurate if the test is "pass/fail."

D. will only be accurate if scored in a timely fashion.

B. may be exaggerated.

Raw scores may be converted to norms

A. so that the scores are more easily interpreted.

B. so that scores are easily communicated to others.

C. Both so that the scores are more easily interpreted and so that scores are easily communicated to others.

D. None of these

C. Both so that the scores are more easily interpreted and so that scores are easily communicated to others.

What index of reliability would be BEST use to compare two evaluators' assessments of a group of job applicants?

A. KR-20

B. coefficient alpha

C. the Kappa statistic

D. the Spearman-Brown correction

C. the Kappa statistic

A test containing 100 items is revised by deleting 20 items. What might be expected to happen to the magnitude of the reliability estimate for that test?

A. It will be expected to increase.

B. It will be expected to decrease.

C. It will be expected to stay the same.

D. It cannot be determined based on the information provided.

B. It will be expected to decrease.

The greater the proportion of the total variance attributed to true variance, the more ____________ the test.

A. scientific

B. variable

C. reliable

D. Expensive

C. reliable

What is the relationship between the coefficient of determination and the correlation coefficient?

A. The larger the correlation coefficient, the larger the coefficient of determination.

B. The larger the correlation coefficient, the smaller the coefficient of determination.

C. The relationship between them would have a correlation coefficient of zero exactly.

D. The larger the correlation coefficient, the more variance can be attributed to error or chance.

A. The larger the correlation coefficient, the larger the coefficient of determination.

The correlation coefficient of choice when both sets of measurements are in rank-order form and when fewer than 30 pairs of measurements are involved is

A. the Pearson r.

B. the tetrachoric r.

C. the Spearman rho.

D. the ROTC.

C. the Spearman rho.

In classical test theory, an observed score on an ability test is presumed to represent the testtaker's

A. true score.

B. true score less the variance.

C. true score combined with extraneous factors.

D. the testtaker's true score and error.

D. the testtaker's true score and error.

The more homogeneous a test is, the

A. less inter-item consistency it can be expected to have.

B. more utility the test has for measuring multifaceted variables.

C. more inter-item consistency it can be expected to have.

D. None of these

C. more inter-item consistency it can be expected to have.

A confidence interval is a range or band of test scores that

A. has proven test-retest reliability.

B. is calculated using the standard error of the difference.

C. is likely to contain the true score.

D. None of these

C. is likely to contain the true score.

Test-retest estimates of reliability are referred to as measures of ________, and split-half reliability estimates are referred to as measures of ________.

A. true scores; error scores

B. internal consistency; stability

C. inter-scorer reliability; consistency

D. stability; internal consistency

D. stability; internal consistency

Psychological tests share commonalities. For example, they all

A. include an analysis of a naturally occurring behavior.

B. include an analysis of a sample of behavior.

C. include paper-and-pencil and oral responses.

D. All of these

B. include an analysis of a sample of behavior.

In the everyday practice of psychological assessment, how do questions and issues about a testtaker's proficiency in the English language typically get resolved?

A. by a determination based on the number of years of formal education in English

B. by the score achieved on a test of English as a Second Language

C. on a case-by-case basis

D. informal evaluation of comprehension of "knock-knock" jokes

C. on a case-by-case basis%

A frequency distribution typically includes

A. the average score and a measure of diversion around it.

B. each possible score and how often it occurs.

C. an estimate of how spread out the scores are.

D. an index of how "popular" a particular frequency is.

*B. each possible score and how often it occurs.

For which type of distribution of scores is the mean the preferred

measure of central tendency?

A. a symmetrical distribution

B. a skewed distribution

C. a flat distribution

D. a curved distribution

A. a symmetrical distribution%

Which is the only measure of central tendency that can be used for all nominal, ordinal, interval, and ratio scales of measurement?

A. the mode

B. the median

C. the mean

D. the standard deviation

*A. the mode

If a distribution of scores has a few extremely low scores and no corresponding high scores, which of the following would be TRUE?

A. The mean would be smaller than the median.

B. The mean would be larger than the median.

C. The mean and the median would be equal.

D. The mean, median, and mode would all be the same.

A. The mean would be smaller than the median.

Which statistic conveys the LEAST precise measure of dispersion?

A. the range

B. the variance

C. the standard deviation

D. the semi-interquartile range

A. the range

Users of psychological tests are frequently tempted to treat ordinal data as if it were interval data. This is the case because of the

A. difficulties that would be encountered if the data were treated as ratio data.

B. frequent need to do more than simply rank order test scores.

C. data manipulation capabilities given the equal intervals between points measured.

D. added flexibility of interval level data for statistical manipulation.

D. added flexibility of interval level data for statistical manipulation.

Which is NOT a part of the formula for calculating a standard deviation?

A. each test score

B. the total number of items in the test

C. the mean of the distribution

D. the total number of test scores

B. the total number of items in the test

What does the "tail" of a normal distribution refer to?

A. the area of the normal curve between 2 and 3 standard deviations above the mean

B. the area of the normal curve between 2 and 3 standard deviations below the mean

C. the extremes of the distribution

D. the bottom of the distribution

C. the extremes of the distribution

If a particular measure yields scores that are normally distributed, this may be characterized as a desirable feature of that measure. A normal distribution of scores is desirable because

A. it provides evidence that the measure is valid, reliable, and psychometrically sound.

B. it shows that both the testtakers and the test users were quite diligent in completing their respective tasks.

C. the proportion of testtakers having scores in specific ranges can be estimated accurately.

D. it reflects a good sampling procedure used in selecting the normative group.

C. the proportion of testtakers having scores in specific ranges can be estimated accurately.

When test scores are found to be normally distributed, they take on the shape of the familiar "bell curve." In these kinds of graphs, which variable is on the y (vertical) axis?

A. the test score

B. the frequency

C. the deviation from the mean

D. the standard deviation

B. the frequency

The purpose of deriving a standard deviation of a distribution is

A. to average all the scores in a distribution.

B. to determine the central value of the scores in a distribution.

C. to determine the dispersion of scores around the mean of a distribution.

D. to determine the range of scores in each of the quartiles of a distribution.

C. to determine the dispersion of scores around the mean of a distribution.

Which of the following is most directly associated with the process of predicting scores using regression techniques?

A. a standard error of the estimate

B. a standard error of the mean

C. a standard error of measurement

D. a standard error of the difference

A. a standard error of the estimate

What is the relationship between the correlation coefficient and the standard error of estimate?

A. It is a positive relationship.

B. It is an inverse relationship.

C. It's complicated.

D. There is no relationship.

B. It is an inverse relationship.

Norm-referenced testing and assessment is both a method of evaluation and a way of deriving meaning from tests scores. Individual testtaker scores are evaluated against

A. the scores achieved by a matched group of testtakers on a comparable test.

B. the scores of a comparison group of testtakers.

C. scores from a demographically more diverse group of testtakers.

D. the scores achieved by a guy named norm.

B. the scores of a comparison group of testtakers.

Referring to a psychological trait as a construct means that it

A. is an idea whose time has come, gone, and come back again.

B. has few practical "real-world" applications and is used for academic purposes.

C. was developed by naturalistic observation rather than any theory.

D. is a scientific concept developed to describe or explain behavior.

D. is a scientific concept developed to describe or explain behavior.

Any influence on psychological test scores from factors other than what the test is intended to measure is referred to by measurement specialists as

A. spurious artifact.

B. bias.

C. error.

D. construct-irrelevant stimuli.

C. error.