welcome to my website teachingonline.net
Teaching Online Contents
- 1 Interpretation of Data of Criterion Referenced Tests
- 1.1 Loss Ratio for Domain Referenced Test of All the Students
- 1.2 Loss-Ratio for Domain-Referenced Test of Rural Students
- 1.3 Loss Ratio for Domain-Referenced Test of Urban Students
- 1.4 Validity
- 1.5 Content Validity
- 1.6 Construct Validity
- 1.7 Criterion-Related Validity
- 1.8 Standardization
- 1.9 Interpretation of Data of Criterion Referenced Tests (Part-1):- Click Here
- 1.10 Interpretation of Data of Criterion Referenced Tests (Part-2):- Click Here
- 1.11 Interpretation of Data of Criterion Referenced Tests (Part-3):- Click Here
Interpretation of Data of Criterion Referenced Tests
Loss Ratio for Domain Referenced Test of All the Students
Loss Ratio for Domain referenced test of all the Students in home science have been shown in Table-24. In the Table A stands for the criterion level or the 1evel of functioning that is sufficient to evidence mastery. Cut off score for mastery is 70%. B stands for the expected mean level of functioning that is 70%.
The Table-24 shows in 83 item domain referenced test and a passing score of 62 (75%) is recommended when the mastery criterion is 70% the groups expected mean level of functioning is 70%. Table indicates that only 0.6% students have obtained 75% and the loss ratio is 1.5 that is, it is 1.5 times as serious error to retain the student as non master than to advance him as master. The figures for other loss ratio in paper-II can be interpreted in the same manner.
Loss-Ratio for Domain-Referenced Test of Rural Students
The Table-25 shows that none of rural students have obtained 75% and above scores in both the papers of home science so there will not be a question of retaining the rural students. All the rural students should not-be advanced to mastery category.
Loss Ratio for Domain-Referenced Test of Urban Students
The Table-26 shows that only 1% students have obtained 75% score in paper-I and the loss ratio is 1.5. That is it is 1.5 times as serious error to retain the students as non-master as to advance her as master. 1.61. Urban students have obtained 75% score in paper- – IIso they should be advanced in mastery category.
It was stated that the latest thinking is to consider only the following three types of validity.
- Criterion related
It indicates how far the test samples the universe of content (including behavioral objectives). The content validation requires the subjective judgment of experts who ensure that there is maximal overlapping of the curriculum by the test. In the case of the present tests, the content validation was ensured before the items were finally selected, and again when the items were posted in the test form so that each domain gets adequately referenced in the test. For further information see relevance report in the chapter 7. Domain specifications and (objective) Competency statements are given in the Appendix C and Blue prints are given in the Appendices D.E.F.G.
Construct validity is usually estimated for psychological tests, for educational achievement test they are seldom reported. The present investigator did not consider it necessary to estimate construct validity.
This shows to what extent the test scores correlate with the criterion scores, the criterion test to be available in future (as is the case with aptitude tests). Since the present test were constructed mainly with a view to estimate the students achievement against a set of performance standards, and no valid criteria for finding out a criterion related validity of these tests were available, the criterion related validity was not worked out.
CRTs are primarily used for formative evaluation; they are generally not standardized though they are amenable to standardization. Another reason that weighed with the researcher was that the sample size was not considered adequate for the purpose. In future when the schools effectiveness is estimated against prescribed performance standard, may be standardization could be useful.