Critical Analysis: Item Validity Index

1405 Words6 Pages
as the criterion difficulty index approaches one, the majority of the students are unable to respond to the item and do not therefore understand the information. As this ratio approaches zero, the majority of the students responding the item respond correctly. Thus the index of criterion difficulty ranges between zero and one. If a test composed only of items of higher indices of difficulty or only of lower indices of difficulty, it will never be a good measuring instrument. The acceptable range of difficulty index is between 0.10 and 0.90. In the present study, the indices of difficulty of the test items were computed by the formula mentioned above. On the basis of the acceptable index of difficulty (ID) the investigator selected 58 items…show more content…
The Index of discrimination has been vehemently described by Mosier & McQuitty (1940), Johnson (1951) and Ebel (1965). It is that ability of the item on the basis of which the discrimination is made between superiors and inferiors (Blood & Budd, 1972). Bean (1953) has defined this index as “the degree to which the single seperates the superior from the inferior individuals in the trait or group of traits being measure.” A number of methods have been devised for use in determining the discriminating power of an item. Marchall & Hales (1972) have suggested a very simple and quick method of determining the index of discrimination. They have called the index ‘Net D index of discrimination’. This method demands the setting up the two extreme groups- one consisting the upper 27% and the other consisting the lower 27% of the examinees on the basis of their obtained scores. This method, as it is clear from the following formula, is directly based upon the difference between the proportion of correct answers of the top 27% and the bottom 27%…show more content…
The test was split into two equal halves. These independent sub-tests are then used as a source of the two independent scores needed for eligibility estimation. The odd and even number items were scored separately and the correlation between scores on the odd and even numbered items was calculated by product moment correlation method. To obtain an estimate of the reliability based on the full length test it is necessary to correct, or step up the half test correlation to the full length correlation. This was done with the help of the Spearman-Brown formula to predict score reliability from a test twice as long as a given test, as in the split half method, the formula is: r_(2 = 2(r)/((r+1) )) Where ‘r’ is the reliability of the original scores and ‘r2’ is the reliability of the lengthened test. Here the reliability of the original scores by product moment correlation method was calculated as 0.43 and the reliability of the lenghened i.e. the whole test was calculated as: r_(2= (2

More about Critical Analysis: Item Validity Index

Open Document