Information Technology Reference
In-Depth Information
~
~
~
(
)
(
)
(
)
Y
=
0
0
566
;
+
0
412
;
0
104
;
X
+
0
466
;
0
X
+
1
2
~
(
)
+
0
130
;
X
;
3
S
=
0
454
;
HR
=
0
827
;
HS
=
0
213
.
As one can see form the building process, fuzzy regression model with fuzzy
coefficients has more accurate indexes then regression model with definite
coefficients.
The classical linear regression model is constructe
d
Y
=
-0.708
+
0
301
X
+
0
428
X
+
0
394
X
;
1
2
3
S
Y
=
0
949
;
R
=
0
808
;
S
=
0
509
.
Table 6.1
Progress data
X
X
X
No.
Y
3
1
2
1
2
3
3
2
2
3
4
3
3
3
3
2
2
2
4
4
4
3
4
5
5
4
5
5
6
4
3
3
3
7
5
5
4
4
8
5
3
4
3
9
2
3
3
2
10
3
4
3
3
Table 6.2
Parameters of membership functions of evaluations in subjects
Term
No.
X
X
X
Y
3
1
2
1
(0;0,10;0;0,10)
(0;0,05;0;0,10)
(0;0,15;0;0,20)
(0;0,10;0;0,15)
2
(0,20;0,40;0,10;0,30) (0,15;0,45;0,10;0,30)
(0,35;0,20;0,30)
(0,25;0,60;0,15;0,10)
3
(0,70;0,80;0,30;0,15) (0,75;0,85;0,30;0,10) (0,65;0,85;0,30;0,05) (0,70;0,90;0,10;0,05)
4
(0,95;1,00;0,15;0)
(0,95;1,00;0,10;0)
(0,90;1,00;0,05;0)
(0,95;1,00;0,05;0)
Considering an incorrectness of operating with elements of ordinal scales, we may
assume that the constructed model does not initially have essential and substantial
sense. However, in practice similar models are applied rather often. Therefore, the
classical model is constructed to compare its determination coefficient with values
of analogue determination coefficient for the fuzzy hybrid regressions (other
