Published on natboard website. Link to PDF file...
RESULTS - EQUATING & SCALING
The question paper of DNB
CET comprises of 180 multiple choice questions each with four options
and only one correct response. Multiple question papers are used for DNB
CET for different sessions and days.
A standard
psychometrically-sound approach is employed for the scoring process of
DNB CET. This approach has been applied to score all large scale
Computer Based Examination utilizing multiple question papers.
Step 1: Calculation of Raw Marks
Raw marks are calculated based on the number of questions answered correctly, incorrectly or omitted.
Correct Answer
|
+1 point
|
Incorrect Answer
|
-0.1 point (10%)
|
Omitted
|
0 point
|
Step 2: Raw Marks are equated
While
all question papers (forms) are carefully assembled to ensure that the
content is comparable, the difficulty of each form may be perceived by
different subjects undertaking the test to slightly vary. Such minor
differences in the overall difficulty level are accurately measured
after all the different question papers have been administered and the
results analyzed. A post-equating process is necessary to ensure
validity and fairness.
Equating is a psychometric process to adjust
differences in difficulty so that scores from different question papers
are comparable on a common metric and therefore fair to candidates
testing across multiple papers. To facilitate this comparison, each form
contains a pre-defined number of questions (items) selected from a
large item bank, called an equating block, which is used as an anchor to
adjust candidates scores to the metric of the item bank. Taking into
account of candidates' differential performance on these equating
blocks, each individual's raw marks are adjusted for difference in
question paper difficulties.
During post-equating, test items are
concurrently analyzed and the estimated item parameters (item difficulty
and discrimination) are put onto a common metric. Item Response Theory
(IRT), a psychometrically supported statistical model, is utilized in
this process. The result is a statistically equated raw score that takes
into account the performance of the candidate along with the difficulty
of the form administered.
Step 3: Equated raw score is scaled
In order to ensure appropriate interpretation of an equated raw
score, the scores must be placed on a common scale or metric. A linear
transformation is used for this scaling process, which is a standard
practice for such test administration.
Post equating takes into
account any statistical differences in examination difficulty and
ensures all candidates are evaluated on a common scale.
The aforesaid steps ensure that all examination scores are valid, equitable and fair.
Criteria for Qualifying DNB CET- July 2012:
The scaled scores for DNB CET will range from 0 to 800.
S.No.
|
Category
|
Passing Criteria
|
Minimum score required
|
1.
2.
3.
|
General
SC/ST/OBC
PWD
|
50% of score
40% of score
45% of score
|
400/800
320/800
360/800
|