Psychological Testing Questions and Answers

Answer: A

The median T score for the inventory would be 50.

T scores are normalised scores with a mean of 50 and a standard deviation of 10. Because the scores are normalised, their distribution is normal, and in a normal distribution the median equals the mean, which is 50. The values 100 and 120 do not fit a scale centred on 50, and the data given are enough to answer, so option D, saying they are inadequate, is wrong.

Answer: D

The data indicate unsatisfactory concurrent validity.

Concurrent validity is shown by the correlation of the new inventory with an established measure of the same trait taken at the same time. The correlation found, 0.20, is low, which suggests the new inventory is not measuring what the established one does. Parallel form reliability needs two equivalent forms, which the passage does not give, so options A and B are not answerable from it, and a correlation of 0.20 is too low to call satisfactory.

Answer: A

The inventory shows satisfactory internal consistency reliability.

Cronbach's alpha is a direct measure of internal consistency, and a value of 0.80 is generally regarded as acceptable. No split-half coefficient has to be computed first, since alpha already gives the internal consistency, and the passage does give the data needed, so options B, C and D are wrong.

Answer: D

The item to remove is Item 5.

In IRT the b parameter is item difficulty on the same scale as ability, with average ability at about 0. An item suits people of a given ability when b is near their level.

Item 5 has b = 3.2, more than three units above the mean, so almost no average person would answer it correctly; it is the item furthest from average ability. Items 2 (b = 2.2) and 3 (b = 1.3) are also above average but much closer. Item 4 (b = -1.0) is an easy item, and removing it would make the test harder, not better suited to average examinees.

Answer: B

The item easiest to guess is Item 3.

In the three-parameter model the c parameter is the pseudo-guessing parameter, the lower asymptote of the item characteristic curve: the chance that a very low-ability person still gets the item right.

Comparing the c column, Item 3 has c = .08, the highest. Item 1 has .03, Item 5 .02, and Items 2 and 4 only .002 each, so 'Item 4 and item 2' are in fact the hardest to guess, and Items 1 and 5 are easier to guess than they are but still below Item 3.

Answer: C

The key states that the measurement of interests began as a narrow, specialised development in the study of personality. Interest inventories grew out of attempts to describe the person's likes and dislikes as part of personality assessment. Aptitude, attitude and job orientation are named in the other options, but the key does not accept them.

Answer: B

The key credits J. M. Ojha with standardising and adapting the Differential Aptitude Test for India. The Differential Aptitude Tests were originally made by Bennett, Seashore and Wesman in the United States. I could not verify the Indian adaptation history independently, so the key is followed as printed. The other three names are Indian psychologists associated with other tests and are not the key's choice.

The Differential Aptitude Tests measure verbal reasoning, numerical ability, abstract reasoning, clerical speed and accuracy, mechanical reasoning, space relations, spelling and language use.

Answer: A

The Spearman-Brown formula is used to estimate reliability by the split-half method, because correlating two halves of a test gives the reliability of only half the test length, and the formula steps this up to the full length. The Kuder-Richardson formulas and Cronbach's alpha measure internal consistency from all items, and there is no 'Wallis-Richardson formula' for reliability.

The split-half correlation is for half-length tests only, so the Spearman-Brown formula, r = 2r(hh) / (1 + r(hh)), is applied to find the reliability of the full test.

Answer: A

Aptitude is a combination of characteristics that indicates a person's capacity to acquire a particular knowledge or skill after training. Attitude is a lasting evaluation of something, and 'psycho-social ability' and 'skilling ability' are not standard terms for this idea.

Answer: D

Only the word association test and the sentence completion test indirectly assess the unconscious part of behaviour. These are projective techniques: the person responds to ambiguous or open material, and the response reveals hidden feelings and conflicts. The Seguin form board is a performance test of intelligence in which the person fits shaped blocks into a board, so it is not a probe of the unconscious, and options including 3 are wrong.