Document Type : Research Paper


1 Department of Mathematical Sciences, Isfahan University of Technology, Isfahan 84156-83111, Iran and Department of Statistics, School of Mathematical Sciences, Ferdowsi University of Mashhad, Mashhad, Iran

2 Department of Mathematical Sciences, Isfahan University of Technology, Isfahan 84156-83111, Iran


This study is an investigation of fuzzy linear regression model for
crisp/fuzzy input and fuzzy output data. A least absolutes deviations approach
to construct such a model is developed by introducing and applying a new
metric on the space of fuzzy numbers. The proposed approach, which can deal
with both symmetric and non-symmetric fuzzy observations, is compared with
several existing models by three goodness of t criteria. Three well-known
data sets including two small data sets as well as a large data set are employed
for such comparisons.


A. R. Arabpour and M. Tata, {it Estimating the parameters of a
fuzzy linear regression model}, Iranian Journal of Fuzzy Systems,
{bf 5} (2008), 1-20.
A. Bargiela, W. Pedrycz and T. Nakashima, {it Multiple regression
with fuzzy data}, Fuzzy Sets and Systems, {bf 158} (2007),
A. Celmins, {it Least squares model fitting to fuzzy vector
data}, Fuzzy Sets and Systems, {bf 22} (1987), 260-269.

J. Chachi and  S. M. Taheri, {it A least-absolutes approach to multiple
fuzzy regression}, In: Proc. of
58th ISI Congress, Dublin, Ireland, (2011), CPS077-01.
J. Chachi,  S. M. Taheri and R. H. Rezaei Pazhand, {it An interval-based approach
to fuzzy regression for  fuzzy input-output data}, In: Proc. of
the  IEEE Int. Conf. Fuzzy Syst. (FUZZ-IEEE 2011), Taipei, Taiwan, (2011), 2859-2863.

P. T. Chang and C. H. Lee, {it Fuzzy least absolute deviations
regression based on the ranking of fuzzy numbers}, In: Proc. of
the Third IEEE World Congress on Computaional Intelligence, Orlando, FL, {bf 2} (1994), 1365-1369.

L. H. Chen and C. C. Hsueh, {it A mathematical programming method
for formulating a fuzzy regression model based on distance
criterion}, IEEE Transactions on Systems, Man, Cybernetics B, {bf 37} (2007), 705-712.
L. H. Chen and C. C. Hsueh, {it Fuzzy regression models using the least-squares method based on the concept of distance}, IEEE Transactions on Fuzzy Systems, {bf 17} (2009), 1259-1272.

S. H. Choi and J. J. Buckley, {it Fuzzy regression using least
absolute deviation estimators}, Soft Computing, {bf 12} (2008), 257-263.
 S. H. Choi and K. H. Dong, {it Note on fuzzy regression model}, In: Proc.
of the 7th Iranian Statistical Conference, Allameh-Tabatabaie
Univ., Tehran, (2004), 51-55.
R. Coppi, P. D'urso, P. Giordani and A. Santoro, {it Least
squares estimation of a linear regression model with LR fuzzy
response}, Computational Statistics and Data Analysis, {bf 51} (2006), 267-286.

P. Diamond, {it  Least squares fitting of several fuzzy
variables}, In:  Proc. of Second IFSA Congress, Tokyo, (1987), 20-25.
 Y. Dodge and ed., {it Statistical data analysis based on the L1-Norm
and related methods}, Elsevier Science Publishers B. V., Netherlands, 1987.

 P. D'Urso and A. Santoro, {it Goodness of fit and variable selecion in
the fuzzy multiple linear regression},
 Fuzzy Sets and Systems, {bf 157} (2006), 2627-2647.
 S. Fattahi, S. M. Taheri and S. A. Hoseini Ravandi, {it Cotton yarn engineering via fuzzy
 least squares regression},
 Fibers and Polymers, to appear.

P. Guo and H. Tanaka, {it Dual models for posibilistic regression
analysis}, Computational Statistics and Data Analysis, {bf 51} (2006), 253-266.
H. Hassanpour, H. R. Maleki and M. A. Yaghoobi, {it A goal programming approach to fuzzy linear regresion with non-fuzzy input and fuzzy output data}, Asia-Pacific Journal of Operational Research, {bf26} (2009), 587-604.
H. Hassanpour, H. R. Maleki and M. A. Yaghoobi, {it Fuzzy linear regression model with crisp coefficients: a goal programming approach}, Iranian Journal of Fuzzy Systems, {bf7} (2010), 19-39.

C. Kao and C. L. Chyu, {it A fuzzy linear regesion model with
better  explanatory power}, Fuzzy Sets and Systems, {bf126} (2002), 401-409.
B. Kim and R. R. Bishu, {it Evalaution of fuzzy linear
regresssion models by comparing membership functions}, Fuzzy Sets
and Systems, {bf 100} (1998), 343-352.
K. J. Kim, D. H. Kim and S. H. Choi, {it Least absolute deviation
estimator in fuzzy regression}, Journal of Applied Mathematics and Computing, {bf18} (2005), 649-656.
R. K"orner and W. N"ather, {it Linear regression with random
fuzzy variables extended classical estimates, best linear
estimates, least squares estimates}, Information Sciences, {bf109} (1998), 95-118.
J. Mohammadi and S. M. Taheri, {it Pedomodels fitting with fuzzy least squares regression}, Iranian Journal of Fuzzy Systems,
{bf 1} (2004), 45-61.
C. P. Pappis and N. I.  Karacapilidis, {it A comparative
assessment of measure of similarity of fuzzy values}, Fuzzy Sets
and Systems, {bf 56} (1993), 171-174.
S. Pourahmad, S. M. T. Ayatollahi and S. M. Taheri, {it  Fuzzy logistic regression: a new possibilistic model and its application in clinical vague status}, Iranian Journal of Fuzzy Systems,
{bf 8} (2011), 1-17.

S. Pourahmad,  S. M. T. Ayatollahi, S. M. Taheri and Z. Habib Agahi, {it Fuzzy logistic regression based on the least squares approach with application in clinical studies}, Computers and Mathematics with Applications, {bf 62} (2011), 3353-3365.
H. Rezaei,  M. Emoto and M. Mukaidono, {it New similarity measure
between two fuzzy sets}, Journal of Advanced Computational Intelligence and Intelligent Informatics, {bf 10} (2006), 946-953.
P. J. Rosseeuw and A. M. Leroy, {it Robust regression and outlier
detection}, Wiley, 1987.
 M. Sakawa and H. Yano, {it
Multiobjective fuzzy linear regression analysis for fuzzy
input-output data}, Fuzzy Sets and Systems, {bf 47} (1992), 173-181.
S. M. Taheri and M. Kelkinnama, {it Fuzzy least absolutes regression}, In: Proc. 4th Internatinal IEEE Conferance on Intelligent Systems, Varna, Bulgaria, (2008), 55-58.
%W. Stahel and S. Weisberg, (ed.s), {it Directions in robust
%Statistics and Diagnistics}, Springer- Verlag, New York, 1991.
H. Tanaka and P. Guo, {it Possibilistic data analysis for operations
research}, Springer-Verlag, New York, 1999.
H. Tanaka, S. Vejima and K. Asai, {it Linear regression analysis
with fuzzy model}, IEEE Transactions on Systems, Man, Cybernetics, {bf12} (1982), 903-907.
H. Torabi and  J. Behboodian, {it Fuzzy least-absolutes estimates
in linear models}, Communications in Statistics-Theory and
Methods, {bf 36} (2007), 1935-1944.
%bibitem[Yang and Ko]{}
%M.S. Yang,
 M. S. Yang and  C. H. Ko, {it On a class of fuzzy c-numbers
clustering procedures for fuzzy data}, Fuzzy Sets and Systems,
{bf 84} (1996), 49-60.
 M. S. Yang and  C. H. Ko, {it On cluster-wise fuzzy regression
analysis}, IEEE Transactions on Systems, Man, Cybernetics B, {bf 27} (1997), 1-13.
M. S. Yang and  T. S. Lin, {it Fuzzy least-squares linear
regression analysis for fuzzy input-output data}, Fuzzy Sets and
Systems, {bf 126} (2002), 389-399.
 K. K. Yen, G. Ghoshray and G. Roig, {it A linear regression
 model using triangular fuzzy number coefficient}, Fuzzy Sets and
 Systems, {bf 106} (1999), 167-177.
H. J. Zimmermann, {it Fuzzy set theory and its applications},
Kluwer, Dodrecht, 3rd ed., 1995.