Psychometrics 1 & 2 Final Reviewer Flashcards
Construct identification procedures of validating a test aims to:
a. ) Check how consistent a test is in computing for average test scores
b. ) Check if a test can predict a psychological trait in the future
c. ) Check reliability of each test items
d. ) Check if the test is measuring the construct it aims to measure
d.) Check if the test is measuring the construct it aims to measure
Which of the followng is TRUE abou psychological assessment?
a. ) It goes first before measurement
b. ) It can be done without measurement
c. ) The process is used for decision making
d. ) The process is used to quantify tests results
c.) The process is used for decision making
Percentile rank refers to:
a. ) The number of scores that are placed above a given score
b. ) The number of scores that falll below the mean
c. ) The number of scores that was outscored by a givens core
d. ) The number of scores above a given score
c.) The number of scores that was outscored by a givens core
The weakness of split half technique as a procedure is:
a. ) Does not consider all possible orders of both halves of test items
b. ) Does not work if a test has many subtests
c. ) Both A and B are weaknesses of split half technique
d. ) No weakness of split half technique is presented
c.) Both A and B are weaknesses of split half technique
The main weakness of split half technique is:
a. ) It makes more time than doing a test-retest reliability
b. ) It can be done in a single administration of a test
c. ) It only assures the reliability of half of the test
d. ) None of the choices
c.) It only assures the reliability of half of the test
Which of the following is FALSE about achivement tests?
a. ) Measures an individual’s past learning of a material
b. ) The tests are mostly done by giving test takers tasks
c. ) Most of these tests are untimed
d. ) B and C are false
d.) B and C are false
Which of the following is FALSE about test-retest reliability?
a. ) It is a procedure that involves more than one test administration
b. ) Practice effect can be a problem
c. ) It measures the reliability of the scoring of a test
d. ) None of the statements are false
c.) It measures the reliability of the scoring of a test
Which of the following statements reflect the influence of standardized intelligence tests to the development of standardized personality tests?
a. ) The development of projective tests
b. ) The development of laboratory based personality assessment
c. ) Personality is also quantified
d. ) None of the above
c.) Personality is also quantified
Which of the following is true about KR20?
a. ) It is a validity procedure
b. ) It measures how valid each items are in a test
c. ) Gets the ration of right to wrong responses in an item
d. ) Multiplies half test to become a whole
c.) Gets the ration of right to wrong responses in an item
Which of the following shows a reliable test using a test-retest method?
a. ) r = -.90
b. ) = +.75
c. ) r = +.10
d. ) r = -.75
b.) = +.75
Which of the following situations WILL NOT make application of Stanine system work?
a. ) Scores are very spread from each other
b. ) Scores have high means
c. ) Some scores are not in the normal curve
d. ) None of the above
b.) Scores have high means
Which of the following statements describe what KR20 does?
a. ) A method used to establish reliability of objective items
b. ) Computes for reliability of individual items
c. ) Gets the ratio of correct to incorrect responses per item
d. ) All of the above
d.) All of the above
Which of the following is TRUE about the norm reference approach in norming?
a. ) The passing score is already set
b. ) The passing score depends on the test developer
c. ) The passing mark depends on the performance of the testing population
d. ) The scores are organized from highest to lowest
c.) The passing mark depends on the performance of the testing population
The first step in organizing scores using the Stanine system is:
a. ) Get the range of the set of scores
b. ) Get the standard deviation of the set of scores
c. ) Organize the scores from highest to lowest
d. ) The first step is not indicated in the choices
c.) Organize the scores from highest to lowest
Which of the following statements is TRUE about the Stanine system?
a. ) The process involves organizing scores according to their class interval
b. ) The stanine system is independent of the normal curve
c. ) The qualitative meaning of stanine is determined by the assesor
d. ) The number of scores that will fall under a stanine is already fixed
d.) The number of scores that will fall under a stanine is already fixed
Which of the following is FALSE about the relationship between psychological measurement and assessment?
a. ) Measurement and assessment are two processes
b. ) Assessment muist be based on measurement
c. ) Measurement must be based on assessment
d. ) Letters A and B are false
c.) Measurement must be based on assessment
A test-retest reliability coefficient of -.90 means that:
a. ) The test is valid
b. ) The test is reliable
c. ) The test is not reliable
d. ) The test is both reliable and valid
c.) The test is not reliable
A criterion referenced approach to establishing a norm means that:
a. ) Qualitative interpretations of scores depend on the performance of the population
b. ) Qualitative interpretations of scores depend on the performance of the highest scorer
c. ) Qualitative intepretations of score depends on median of the entire test scores
d. ) None of the above
d.) None of the above
The disadvantage of using the measure of central tendency in interpreting raw scores is:
a. ) The qualitative interpretation is too specific
b. ) There is not enough variation of a score’s interpretation
c. ) Both A and B are true
d. ) None of the choices
a.) The qualitative interpretation is too specific
The most important step to be done in doing a content validity is:
a. ) Identify the conceptual definitions of the test construct
b. ) Identify the criterion of the test
c. ) Decide if the concurrent validity or predictive is better to use
d. ) Judge if a test looks like a test
a.) Identify the conceptual definitions of the test construct
Establishing the construct validty of a test using discriminant validity and obtaining a coefficient of -.10 between two unrelated variable means:
a. ) What the constructed test is measuring is different from the other test it was correlated to
b. ) The test is invalid
c. ) Both A and B are TRUE
d. ) Both A and B are FALSE
a.) What the constructed test is measuring is different from the other test it was correlated to
Which of the following is FALSE about the Z-score?
a. ) You need to know standard deviation to compute for it
b. ) You need to know the mean to compute for it
c. ) The middle of the curve in the z-score is 0
d. ) One can compute for z-score after knowing the score and standard deviation
d.) One can compute for z-score after knowing the score and standard deviation
Which of the following is TRUE about aptitude tests?
a. ) Helps determined if an aspiring psychologist can be a good psychologist
b. ) Common tool used for students undergoing career counseling
c. ) Measures level of skills that can be expressed in the future
d. ) All are true
d.) All are true
Which of the following describes the function of standard deviation?
a. ) Estimates the number of units that separate the points in the normal curve
b. ) Estimates how many units are there within a compartment of a normal curve
c. ) Tells you the distance of a score from the mean
d. ) All of the above
c.) Tells you the distance of a score from the mean
Which of the following interpretations is correct in describing a correlation coefficient of +.10 between hours of sleep and memory performance?
a. ) Sleeping a lot is very related to having a very good memory
b. ) The more people sleep less, the poorer their memory performance
c. ) People who sleep more have higher memory performance
d. ) Sleeping hours is insignificant to one’s memory performance
d.) Sleeping hours is insignificant to one’s memory performance
The responses of a test taker in individual tests:
a. ) Does not have a right or wrong answer
b. ) Involves giving the single correct answer
c. ) Involves the test taker giving a range of possible right answers
d. ) None of the above
c.) Involves the test taker giving a range of possible right answers
What is with KR21 that cannot be done by KR20 in establishing the reliability of test items?
a. ) KR21 can compute reliability of 30 test items, KR20 can’t
b. ) KR21 can compute reliability of items with equal difficulty, KR20 can’t
c. ) KR21 can compute reliability of items with unequal difficulty, KR20 can’t
d. ) KR21 can only be used with test items with equal difficulty
c.) KR21 can compute reliability of items with unequal difficulty, KR20 can’t
The main purpose of using a norm in a standardized test is:
a. ) Helps psychologist to make sense of test performance by the test takers
b. ) Helps psychologist to easily correct papers
c. ) The raw scores are easily organized
d. ) All of the above
a.) Helps psychologist to make sense of test performance by the test takers
The compartment in the normal curve where a test score will fall into…
a. ) Can be determined by computing the mean of the entire test scores
b. ) Can be determined by organizing the scores from highest to lowest
c. ) Can be determined by computing for the mean and standard deviation
d. ) Can be determined by computing for the mean and the median of the test scores
c.) Can be determined by computing for the mean and standard deviation
Which of the following is FALSE about Cronbach’s alpha?
a. ) It can compute reliability of individidual test items
b. ) It overcomes the weakness of split half technique
c. ) The process includes also doing a Spearman Brown formula
d. ) It can compute reliability of the test’s scoring system
d.) It can compute reliability of the test’s scoring system
