O'Reilly logo

Statistical Methods for Fuzzy Data by Reinhard Viertl

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

5.1 Fuzzy frequency of a fixed class

Due to the possible inability to decide in which class a fuzzy data point xi* lies it seems natural to consider fuzzy values of relative frequencies. For n fuzzy observations x1*,…,xn* and classes K1,…,Kk the fuzzy relative frequencies of the classes are denoted by hn*(Kj), j = 1(1)k. The characterizing function of hn*(Kj) is constructed via its δ-cuts

Unnumbered Display Equation

where the limit points (Kj) and (Kj) are defined in the following way:

Unnumbered Display Equation

and

Unnumbered Display Equation

for all δ ∈ [0; 1].

The characterizing function ηj(·) of hn*(Kj) is obtained by Lemma 2.1.

Remark 5.1:

The characterizing function of a fuzzy relative frequency is a step-function. In Figure 5.2 the characterizing functions of a sample of size 8 are given. In Figure 5.3 the characterizing function of the fuzzy relative frequency of the class [1; 2] is depicted.

Figure 5.2 Fuzzy sample.

c05f002.eps

Figure 5.3 Characterizing function of ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required