Information Technology Reference
In-Depth Information
Chapter 5
Ratings of Objects
5.1 Obtaining of Rating Points of Objects within the Limits of a
Qualitative Characteristic
5.1 O btai ni ng of Rati ng Po ints of O bjects
Rating points systems are widely used in various human activities (educational
process, economics, techniques, etc.) and are of great importance in decision mak-
ing problems [154-166]. These systems make it possible to get available and
timely information in the form of an aggregative index and to use it in decision
making problems. The complexity of obtaining rating points for objects with
qualitative characteristics results from the general complexity of the quantitative
assessment of qualitative characteristics. This complexity is also associated with
the necessity of taking into account characteristics and judgements of the survey-
ors who take decisions based on their personal assessment. As a rule, the qualita-
tive characteristics are scored in different scales and are often incomparable in
principle. The elements of these scales (as a rule, order-type scales) are trans-
formed into scores. Such transformation needs some substantiation because
stability of the final findings depends on it.
The following example will make the point clear. Let us suppose that two objects
got 4 and 3 points for one characteristic and 4 and 5 points for the other characteristic
correspondingly. As a result of two assessments each object gets the same total score
that equals 8. The conclusion is made that they have similar rating points and similar
rating correspondingly. Since we deal with the order-type scale while assessing ob-
jects' qualitative characteristics, we shall apply strictly increasing transformation
Φ
()
()
()
of this scale, that is acceptable:
. It is known [1] that an
acceptable transformation of the values of the assessed quality feature is such a trans-
formation that retains subject matter of the type of assessment involved. In accor-
dance with the transformation applied the total score remained the same for object 1
while it changed for object 2 and has become equal 10 points. Thus the rating point of
the second object has increased. The stability of the results after the acceptable trans-
formation is violated that testifies to the fact that transformation of verbal scales'
elements into scores needs some substantiation.
Problems of obtaining ratings and rating points of real objects arise while esti-
mating the objects considered within the limits of both quantitative and qualitative
characteristics.
Φ
3
=
3
Φ
4
=
4
Φ
5
=
7
