tripleC 9(2): 494-501, 2011
ISSN 1726-670X
http://www.triple-c.at
CC: Creative Commons License, 2011.
Abduction as Incomplete Parameter Estimation
Moto Kamiura
kamiura@rs.noda.tus.ac.jp, moto@goo.jp, Faculty of Science and Technology, Tokyo University of Science,
Japan
Abstract: Abduction is a kind of logical inference, and has been studied in computer science and artificial intelligence (Fin-
lay and Dix 1996). Recently, Sawa and Gunji (2010) introduced a diagram to represent three types of inference: i.e. deduc-
tion, induction, and abduction, which are articulated by C.S.Peirce. Sawa-Gunji’s representation provides a new approach to
a numerical aspect of abduction. In the present paper, we show that Sawa-Gunji's representation of abduction is consistent
with Finlay-Dix's one, and integrate the two representations. Both parameter estimation and abduction occupy a similar
position on the integrated representation, although they are not completely corresponding. We present "incomplete" pa-
rameter estimation as a sort of "simulated abduction", which is a numerical aspect of abduction. It is applied to a first-order
autoregressive (AR(1)) model. As a result of numerical analyses on AR(1), the incompletely estimated parameter (IEP)
follows a Cauchy distribution, which has a power law of the slope -2 in the tail, although conventionally estimated parameter
is normally distributed. It is shown that the Cauchy distribution of the IEP is based on structure of ratio distribution of normal
random variables generated from the AR(1). This research suggests that the distribution of the IEP is not based on a mech-
anism of system itself, but on relationship between data structure on the given system (i.e. the given AR(1) process) and
one on the system observer (i.e. the estimator of the AR(1) parameter).
Keywords: Autoregressive model, Parameter Estimation, Observation, Cauchy distribution, Power law
Acknowledgement: Part of this work was carried out under the Cooperative Research Project Program of the Research
Institute of Electrical Communication, Tohoku University.
1. Introduction
C.S. Peirce who is a philosopher/logician classifies reasoning/inference into three types: i.e. deduc-
tion, induction and abduction (Peirce 1868; 1955). Abduction has been studied not only in philoso-
phy but also in artificial intelligence and computer science (Bylander et al 1991; Tanner and Jo-
sephson 1996; Finlay and Dix, 1996; Abe 2003). Recently, Sawa and Gunji presented a model
representing dynamic change in logical inference (Sawa and Gunji 2010). To define the model
dynamics, they propose an arrow diagram which is a tool to illustrate each of the three types of
inference. Sawa-Gunji’s representation of abduction is an operation in which an arrow in the dia-
gram is derived from the other arrows. This formalization for abduction is not only consistent with
the preceding studies (Peirce 1868; Finlay and Dix 1996), but also provides a new approach to a
numerical aspect of abduction (Kamiura 2010).
In the present paper, inheriting the Sawa-Gunji’s representation, we formalize a numerical as-
pect of abduction and find “incomplete” parameter estimation as a sort of “simulated abduction”.
Auto-regressive (AR(1)) model is used for numerical experiments and the results are shown. In the
conclusion, we discuss abduction mediating a relationship between system observer and power
law distributions.
2. Diagrams of Inference and Positioning of Abduction
Peirce assumes the three types of inference as the following operations: i.e. (i)Deduction: the major
premise and minor premise derive the conclusion. (ii)Induction: the minor premise and conclusion
derive the major premise. (iii)Abduction: the major premise and conclusion derive the minor prem-
ise.