A comparative analysis of methods to represent uncertainly in estimating the cost of constructing wastew

Journal of Environmental Management (2002) 65: 383±409
doi:10.1006/jema.2001.0563, available online at on
1
A comparative analysis of methods to
represent uncertainty in estimating the
cost of constructing wastewater treatment
plants
Ho-Wen Chen and Ni-Bin Chang*
Department of Environmental Engineering, National Cheng-Kung University, Tainan, Taiwan,
Republic of China
Received 4 May 1999; accepted 29 January 2002
Prediction of construction cost of wastewater treatment facilities could be in¯uential for the economic feasibility of various
levels of water pollution control programs. However, construction cost estimation is dif®cult to precisely evaluate in an
uncertain environment and measured quantities are always burdened with different types of cost structures. Therefore,
an understanding of the previous development of wastewater treatment plants and of the related construction cost
structures of those facilities becomes essential for dealing with an effective regional water pollution control program. But
deviations between the observed values and the estimated values are supposed to be due to measurement errors only
in the conventional regression models. The inherent uncertainties of the underlying cost structure, where the human
estimation is in¯uential, are rarely explored. This paper is designed to recast a well-known problem of construction cost
estimation for both domestic and industrial wastewater treatment plants via a comparative framework. Comparisons were
made for three technologies of regression analyses, including the conventional least squares regression method, the fuzzy
linear regression method, and the newly derived fuzzy goal regression method. The case study, incorporating a complete
database with 48 domestic wastewater treatment plants and 29 industrial wastewater treatment plants being collected
in Taiwan, implements such a cost estimation procedure in an uncertain environment. Given that the fuzzy structure in
regression estimation may account for the inherent human complexity in cost estimation, the fuzzy goal regression
method does exhibit more robust results in terms of some criteria. Moderate economy of scale exists in constructing both
the domestic and industrial wastewater treatment plants. Findings indicate that the optimal size of a domestic wastewater
treatment plant is approximately equivalent to 15 000 m
3
/day (CMD) and higher in Taiwan. Yet the optimal size of an
industrial wastewater treatment plant could fall in between 6000 CMD and 20 000 CMD.

#
2002 Elsevier Science Ltd. All rights reserved.
Keywords: wastewater treatment, cost analysis, fuzzy linear regression, fuzzy goal regression, forecasting,
environmental management.
Introduction
Only in the last decade have annual per capita
wastewater generation rates begun to demonstrate
rapid increase due to fast economic development in
Taiwan. The concerns with domestic and industrial
wastewater disposal have become of signi®cance
while the issues of water quality management
plans turn out to be critical in many river basins.
Centralized treatment facilities have rapidly
emerged to aid in processing of domestic and indus-
trial ef¯uents in those urban/suburban areas. In
many water pollution control programs, the choice
of a primary or higher wastewater treatment levels
0301±4797/02/$ ± see front matter
#
2002 Elsevier Science Ltd. All rights reserved.
* Corresponding author. Email:
is intimately related to land availability, budget,
regulations, and managerial concerns. Two chan-
ging situations are worthwhile noticing at this
moment. First, with the condition of more
stringent ef¯uent standards for river and marine
discharge being promulgated in the last decade,
more sophisticated treatment processes have to
be putting into practice for simply meeting the
of®cial requirements. Second, the growing recogni-

tion of resources conservation motivates the use of
wastewater reclamation units to aid in processing
for wastewater recovery and reuse. Prediction of
construction cost of wastewater treatment facilities
could be in¯uential for the economic feasibility of
various levels of water pollution control programs.
In any circumstances, the costs of wastewater
treatment are going to escalate continuously over
time so that it may require advanced and compre-
hensive evaluation with regard to economic feasi-
bility for those water quality management programs
in the future. However, construction cost estima-
tion is dif®cult to precisely evaluate in an un-
certain environment and measured quantities are
always burdened with different types of cost struc-
tures. Therefore, an understanding of the previous
development of wastewater treatment plants and
of the related construction cost structures of
those facilities becomes essential for dealing with
an effective regional water pollution control pro-
gram. But deviations between the observed values
and the estimated values are supposed to be due
to measurement errors only in the conventional
regression models. The inherent uncertainties of
the underlying cost structure, where the human
estimation is in¯uential, are rarely explored.
Previous cost analyses with respect to wastewater
treatment have focused primarily on capital costs
and associated differences with facility size.
Economy of scale is a major concern. As a result,

many regression analyses have been conducted to
analyze the capital cost structures for waste treat-
ment plants (Graves et al., 1970; Robert, 1975;
Chang and Wang, 1995a). But the efforts of those
cost estimation techniques for wastewater treat-
ment in the earlier stage generally cover various
statistical regression models, such as simple linear
regression, multiple linear regressions, and other
nonlinear regression models. However, measured
quantities are always burdened with different
types of uncertainties. Due to the in¯uential im-
pacts by human estimation, more relevant proper-
ties associated with forecasting techniques are
worthwhile exploring by a more systematic, com-
parative, and comprehensive approach. Tanaka
et al. (1982) ®rst mentioned that we must deal
with a fuzzy structure of the systems in the
regression model where human estimation is in¯u-
ential. Fuzzy regression analysis, representing an
alternative to the conventional statistical regres-
sion techniques, has been becoming a promising
approach within the last decade. Its application
potentials have been relatively high in many aspects
in the way to aid in engineering planning, design,
operation, management, and control. Fuzzy
linear regression analysis has been the focus of
a number of studies utilizing advanced algorithms.
Improvement of this method in the earlier stage
can be found in the literature (Tanaka and Asia,
1984a, 1984b; Jajuga, 1986; Tanaka, 1987; Tanaka

and Watada, 1988; Tanaka et al. 1989; Chen, 1988;
Diamond, 1988). Later on, the advances in theory
have been made with respect to the measurement of
vagueness (Bardossy, 1990; Moskowitz and Kim,
1993) and the algorithms of Group Method of Data
Handling (GMDH) (Hayashi and Tanaka, 1990), the
use of a two-stage construction of a linear regression
model (Savic and Pedrycz, 1991), the linkage with
three types of multi-objective programming models
(Sakawa 1992), the development of a fuzzy vector
autoregressive model (Oh et al., 1992), the deriv-
ation of a generalized fuzzy linear regression model
(Wang and Ha, 1992), the application of Monte
Carlo simulation technique for performing a fuzzy
regression analysis (Juang et al., 1992), and the
extension of a fuzzy self-regression model (Lu and
Guang, 1993). On the other hand, many real world
applications, using the fuzzy forecasting technique
as a means, are worthy of further discussions.
Typical examples include the use of fuzzy linear
regression for the forecasting of computer sale in
the market (Heshmaty and Kandel, 1985), for
illustrating cellulose hydrolysis (Gharpuray et al.,
1986), for explaining the potential of fuzzy regres-
sion application in hydrology (Barddossy et al.,
1990), for construction cost analysis of municipal
incinerators using the fuzzy goal regression model
(Chang et al., 1996), and for construction cost
analysis of wastewater treatment plants using
fuzzy linear regression model (Wen and Lee,

1999). This practice may grow in importance in
the future because of limited resources available as
well as rapid economic and population growth in
many countries.
This paper serves as a companion study of
Chang et al. (1996) and Wen and Lee (1999). It is
designed to recast a well-known problem of con-
struction cost estimation for both domestic and
industrial wastewater treatment plants via a com-
parative framework. In short, it differs from these
earlier studies in several ways. First, this analysis
takes both domestic and industrial wastewater
384 H W. Chen and N B. Chang
treatment plants into account separately based on a
more thorough database. Second, with the aid
of fuzzy goal programming technique, advanced
information of fuzzy goal regression is coordinated
and applied to aiding in a detailed evaluation of
forecasting accuracy of constructing wastewater
treatment plants in an uncertain environment.
Third, the proposed comparative study in relation
to three forecasting methods is systematically
assessed on the basis of multiple performance
indexes. Technologies of regression analyses consist
of the conventional least square regression (LS)
method, the fuzzy linear regression (FLR) method,
and the newly derived fuzzy goal regression (FGR)
method. And, fourth, the nonlinear cost structures
in relation to economy of scale along with the use
of dummy variables for the choice of technologies

are explored in the formulation simultaneously. The
case study, incorporating a complete database
with 48 domestic wastewater treatment plants
and 29 industrial wastewater treatment plants
being collected in Taiwan, is designed to implement
three cost estimation methods in an uncertain
environment.
The principles of fuzzy linear
regression and fuzzy goal
regression
Uncertainty frequently plays an important role in
cost estimation. The random character governing
wastewater generation, treatment, re-use, and dis-
posal are all possible sources of uncertainty. Until
the early 1980's, probability was the only kind of
uncertainty handled by mathematics. The implica-
tion of probability, as symbolized by the concept of
randomness, is based on the `chance' or `opportun-
ity'. In relation to the measurement errors that
exist in a real world event, however, fuzziness takes
on another aspect of uncertainty expression. In
reality, fuzziness is the ambiguity that can be
found in the linguistic description of a concept or
feeling. For example, the uncertainty in expressions
like `the water is dirty' or `the smell in the river is
bad' can be called fuzziness. The degree of fuzziness
to be recognized in such questions is `how dirty is
dirty?' or `how bad is bad?' Therefore, random-
ness and fuzziness considered in decision-making
differ in nature. In mathematics, the probability

density function and membership function are
used to illustrate the situation of `probability' and
`fuzziness,' respectively. While the random variable
is used for the description of uncertain statistical
implication, the fuzzy membership function is
therefore de®ned for illustrating the imprecision
existing in the real world systems. Various types of
linear and nonlinear functions were suggested as
probability density functions and fuzzy member-
ship functions in the literature. Usually a large
number of samples are generally required to iden-
tify the probability density function for the occur-
rence of a phenomenon, while subjective description
of the fuzzy membership function is usually applied
in the determination of fuzziness. The more an
element or object can be said to belong to a fuzzy
set A, the closer to 1 is its grade of membership.
Such a membership value is usually called
`aspiration level' or `satisfaction level' in decision
analysis. The fuzzy sets theory, described by the
membership functions, is identi®ed as an alter-
native approach to describe the vagueness in the
planning goals and the impreciseness of related
parameter values, which could be intimately linked
to more practical or realistic aspects in decision-
making (Chang and Chen, 1997). As a consequence,
fuzzy sets theory has received wide attention for
illustrating various types of environmental man-
agement issues.
Most of the traditional regression models for

cost estimation are constructed based on the well-
known theories of probability and statistics that
have to be subject to a long-standing assumptionÐ
`Independent and Identical Distribution' (IID)Ð for
all observations. With such a limitation in theory,
conventional statistical regression analysis is
sometimes involved in a predicament in the real
world applications. While the database consists of
complex factors, it is sometimes hard to ®nd out
suitable mathematical models to describe the
behaviors of the target system that must be
consistent with the IID assumption. Tanaka et al.
(1982) ®rst mentioned that we must deal with
a fuzzy structure of the systems in the regression
model where human estimation is in¯uential. Fuzzy
regression analysis, representing an alternative to
the statistical regression technique, has been grow-
ing up rapidly in the last few years (Tanaka et al.,
1982). The fuzzy linear regression model may
release the IID assumption in the regression
analysis and allow each predicted value to exhibit
different degree of variation.
The fuzzy linear regression is thus recognized as
a mapping process based on a set of observations.
Fuzzy parameters are used for such a linkage
between the independent variables and the depend-
ent variable. To ®nd out the solution of fuzzy
parameters, an equivalent linear programming
Estimating costs of constructing wastewater treatment plants 385
model has to be solved (see Appendix I). However,

the prediction accuracy of fuzzy linear regression
model cannot always be guaranteed better than
that of conventional least-squares regression mod-
els, although fuzzy regression allows the inclusion
of expert knowledge or fuzzy information in the
model in advance (Chang et al., 1996). Chang et al.
(1996) further proposed the fuzzy goal regression
model in order to improve the performance in
comparison to fuzzy linear regression outputs. To
further upgrade the capability of fuzzy goal regres-
sion analysis, this paper provides two revised
fuzzy goal regression approaches (see Appendix II),
which address the variations or uncertainties in
a fuzzy regression analysis by a series of ¯exible
formulations in a model. But it still has to identify
the most attractive model structure among alter-
natives using a fuzzy goal programming procedure
(Chang et al., 1996). The following case study is
prepared for a comparative analysis of these three
methods representing various types of uncertainties
involved in the cost estimation of constructing
wastewater treatment plants. The methods in-
cluded in this case study cover the LS, FLR, and
FGR. Both industrial and domestic wastewater
treatment plants are included for forecasting
practices in this case study.
Case study
Taiwan is located at the west Paci®c Rim of Asian
Continental Shelf. With a small area of about
36 000 square kilometers and over twenty-three

million in population, most of the rivers in this
tiny island have been polluted for a long time. As
the situation of water pollution becomes worse
over time, one of the management strategies is
to install the intercept systems and wastewater
treatment plants to reduce the direct impacts of
ef¯uents on the river systems. Intensive debate in
the society concerns about what is the adequate
level of wastewater treatment process in those
industrial complexes and communities located at
different river reaches or coastal areas and how to
satisfy the overall pollution control requirements
by a cost-effective approach. These questions ini-
tialize a nationwide need to investigate the cost
information of wastewater treatment facilities.
Regression analysis techniques were frequently
applied to estimating engineering cost in many
pollution prevention and environmental quality
control programs (Greenberg, 1995; Chang and
Wang, 1995b; Chang et al., 1996). It is observed
that versatile engineering technologies and com-
petitive bidding processes have made the cost
estimation become relatively vague. An accurate
prediction of the construction cost of industrial and
domestic wastewater treatment plants using
a more reliable approach turns out to be of signi-
®cance for future applications.
Thus, an understanding of the background
information of domestic and industrial wastewater
treatment plants in Taiwan could become a typical

procedure for gaining advanced realization of
inherent underlying cost structure and for pro-
moting forecasting accuracy as well. Figure 1
shows the geographical locations of those planned
and existing wastewater treatment plants in
Taiwan. Tables 1 and 2 not only present a thor-
ough database but also summarize the relevant
engineering parameters for those domestic and
industrial wastewater treatment plants, respective-
ly. The plant numbers marked associated with
each treatment plant in Figure 1 are consistent
with the numbers listed in Tables 1 and 2 and
they will be used thereafter in the context of this
paper. To effectively assess the cost structure
required for wastewater treatment, the fuzzy linear
regression and fuzzy goal regression approaches
(FGR II), as elucidated in Appendix I and
Appendix II, are thus applied to gaining a better
comparative insight and perform more valuable
comparisons to the conventional statistical regres-
sion method in this practice.
Data collection, normalization, and
analysis
Cost information associated with 48 domestic was-
tewater treatment plants and 29 industrial waste-
water treatment plants was collected and included
in the cost database within a thorough investiga-
tion. As listed in Tables 1 and 2, using the primary,
secondary, and tertiary treatment levels may fur-
ther classify the collected samples with respect

to domestic and industrial wastewater treatment
plants respectively. In general, the primary treat-
ment process only employs the bar screen, grit
removal, and primary sedimentation tank to
ful®ll the basic treatment goals. The secondary
treatment process usually adds more biological
treatment units to enhance the removal of organic
content in the ef¯uents, which can be further
differentiated in terms of biological treatment
technologies, such as the contacts stabilization (CS),
386 H W. Chen and N B. Chang
Figure 1. The geographical distribution of wastewater treatment plants in Taiwan.
Estimating costs of constructing wastewater treatment plants 387
Table 1. Database of all domestic wastewater treatment plants in Taiwan
Plant
no.
Location of
treatment plant
Design
capacity
(10
2
CMD)
Total construction
cost (millions US$)
Normalized total
construction cost
(1995 millions US$)
Level
g

of
treatment
Treatment process Year
of
bidding
C.C.I.
f
I
c
II
d
III
e
EQ
a
CS
a
AS
a
RBC
a
VIP
a
A
2
/O
a
OD
a
CO

a
SF
a
D1 Hsin-Ying service area
(in highway)
0Á1 0Á48 0Á48 III 
b
 Â
b
      1995 119Á19
D2 Hai-Hu Vacation Center 0Á2 0Á11 0Á14 II
  Â Â Â Â Â Â Â 1990 94Á65
D3 The Home of Charity 0Á2 0Á17 0Á29 II
 Â  Â Â Â Â Â Â 1985 72Á76
D4 Wu-Ling Hotel (Ken-Ting) 0Á27 2Á59 3Á63 III
 Â   Â Â Â Â  1980 96Á15
D5 Kai-Sa Hotel (Ken-Ting) 0Á45 0Á89 1Á47 III
 Â  Â Â Â Â Â  1986 72Á14
D6 Tai-An service area I 0Á5 0Á87 1Á07 III
  Â Â Â Â Â   1990 96Á15
D7 Tai-An service area II 0Á5 0Á54 0Á66 III Â Â
 Â Â Â Â   1990 96Á15
D8 Ken-Ting 2 7Á59 7Á37 III
  Â Â Â Â Â   1993 122Á65
D9 Chung-Cheng University 2Á4 3Á49 4Á15 III Â
 Â Â Â Â Â   1991 100Á34
D10 Kadhsiung County I
Ã
12Á9 14Á81 14Á81 III Â Â Â Â Â  Â   1995 119Á19
D11 Wu-Lai 13 8Á19 8Á19 II Â

 Â Â Â Â Â Â Â 1995 119Á27
D12 Chi-Mei 13 18Á96 22Á70 III Â Â
 Â Â Â Â   1991 100Á34
D13 Jui-Fang 16 45Á74 44Á81 II Â Â
 Â Â Â Â Â Â 1993 121Á64
D14 Ton-Kang 17 26Á70 31Á74 III Â Â
 Â Â Â Â ± ± 1991 100Á28
D15 Wu-Chia (Kaohsiung) 18 18Á96 31Á30 III Â Â Â
 Â Â Â ± ± 1993 72Á19
D16 Tei-Ton 21Á7 20Á37 20Á37 III Â Â Â Â
 Â Â ± ± 1995 119Á19
D17 Nei-Pu 22 29Á00 34Á48 III Â Â
 Â Â Â Â ± ± 1991 100Á28
D18 Tei-Ton County 22Á8 22Á22 22Á22 III Â Â Â Â
 Â Â ± ± 1995 119Á19
D19 Chao-Wan 23 30Á19 35Á89 III Â Â
 Â Â Â Â ± ± 1991 100Á28
D20 Nan-Tou 33 18Á52 22Á15 II Â Â
 Â Â Â Â Â Â 1991 99Á60
D21 Pe-Kang 34 54Á56 53Á07 III Â Â Â Â Â Â
 Â  1993 122Á55
D22 Chu-Pe 38 30Á56 36Á30 III Â Â
 Â Â Â Â ± ± 1991 100Á34
D23 Tei-Ton 38 23Á26 22Á70 II Â Â
 Â Â Â Â Â Â 1993 122Á10
D24 Miao-Li 41 62Á19 60Á67 III Â Â
 Â Â Â Â Â  1993 119Á69
D25 Tsao-Tun 44 23Á52 28Á15 II Â Â
 Â Â Â Â Â Â 1991 99Á60
D26 Lin-Hae 54 44Á44 42Á96 II Â Â

 Â Â Â Â Â Â 1992 115Á72
388 H W. Chen and N B. Chang
D27 Keelung 63 129Á63 126Á56 II Â Â  Â Â Â Â Â Â 1993 122Á10
D28 Yi-Lan 64 50Á85 49Á63 II Â Â
 Â Â Â Â Â Â 1993 122Á10
D29 Tan-Shui 75 104Á00 86Á70 III Â Â
 Â Â Â Â ± ± 1991 100Á00
D30 Guishuic 78 16Á30 15Á91 I Â Â Â Â Â Â Â Â Â 1993 122Á10
D31 Taichung 87Á5 76Á30 74Á48 II Â Â Â Â Â Â
 Â Â 1993 122Á10
D32 Yi-Lan 89Á5 50Á89 50Á22 II Â Â
 Â Â Â Â Â Â 1993 122Á10
D33 Pan-Hsin 95 60Á56 72Á37 II Â Â
 Â Â Â Â Â Â 1991 122Á10
D34 Tei-Ton 100 44Á44 44Á44 II Â Â Â Â Â
 Â Â Â 1995 119Á19
D35 Ping-Ton 130 103Á11 122Á56 III Â Â Â Â Â
 Â ± ± 1991 100Á28
D36 An-Pin 130 39Á63 39Á70 II Â Â
 Â Â Â Â Â Â 1995 118Á82
D37 erh-ien-hsi 132 71Á63 73Á63 II Â Â
 Â Â Â Â Â Â 1993 122Á10
D38 tou-fen 133 29Á00 47Á81 II Â Â
 Â Â Â Â Â Â 1992 72Á30
D39 Hsin-Chu 138
Ã
103Á70 103Á70 III Â  Â Â Â Â Â ± ± 1995 119Á19
D40 Kaohsiung 156
Ã
74Á07 74Á07 III Â  Â Â Â Â Â ± ± 1995 119Á19

D41 Hau-Lien 165 68Á52 66Á63 II Â Â
 Â Â Â Â Â Â 1993 102Á42
D42 Nan-Zu 175 26Á30 40Á00 I Â Â Â Â Â Â Â Â Â 1988 78Á36
D43 Yung-Kuang 176 116Á11 113Á33 II Â Â
 Â Â Â Â Â Â 1992 117Á27
D44 Tao-Yuan 263
Ã
433Á33 440Á41 II Â Â  Â Â Â Â Â Â 1993 122Á67
D45 Ti-Hau 274
Ã
3Á48 5Á64 I Â Â Â Â Â Â Â Â Â 1990 73Á5
D46 Chung-Li 331 221Á56 215Á26 II Â Â
 Â Â Â Â Â Â 1993 122Á65
D47 Chung-Chou 560 62Á04 102Á13 I Â Â Â Â Â Â Â Â Â 1983 72Á40
D48 Pa-Li 1320 25Á93 267Á04 I Â Â Â Â Â Â Â Â Â 1992 115Á72
a: EQ: equalization tank; CS: contact-stabilization; AS: activated sludge; OD: oxidation ditch; RBC: rotating biological contactor; CO: coagulation; SF: sand ®lter; A
2
/O: anaerobic-anoxic-
aerobic process.
b: `
' represents the inclusion of the designated unit; `Â' represents the exclusion of the designated unit ; `±' represents no information.
c: Primary industrial wastewater treatment process.
d: Secondary industrial wastewater treatment process.
e: Tertiary industrial wastewater treatment process.
f: Construction Cost Index in Taiwan.
g: Level of treatment: I (primary treatment), II (secondary treatment), and III (tertiary treatment).
Estimating costs of constructing wastewater treatment plants 389
Table 2. Database of all industrial wastewater treatment plants in Taiwan
Plant
no.

Location of
wastewater
treatment
plant
Design
¯owrate
(10
3
CMD)
Total
construction
cost
(millions US$)
Normalized total
construction
cost
(1995 millions US$)
Operation
cost
(10
4
US$/year)
Level
g
of
treatment
Treatment process Year
of
bidding
C.C.I.

f
I
c
II
d
III
e
EQ
a
CO
a
FL
a
CS
a
AS
a
RBC
a
A
2
/O
a
OD
a
CO
a
SF
a
I1 Feng-Shan 0Á4 0Á28 0Á45 13Á5 II 

b
Â
b
        1987 75Á64
I2 Ta-Wu-Hun 1Á75 0Á56(1980)
2Á89(1991)
4Á40 29Á6 III
   Â  Â Â Â  Â 1980
1991
73Á50
100Á00
I3 Chia-Tai 2Á5 2Á96(1985)
2Á1(1993)
6Á89 54Á8 II
  Â Â Â  Â Â Â Â 1985
1993
72Á19
122Á10
I4 Yung-Kuang 3 2Á34 3Á91 48Á48 III
 Â Â Â Â Â Â  Â  1985 72Á19
I5 Yung-An 3Á2 1Á11(1983)
2Á22(1991)
4Á46 51Á9 III
 Â Â Â Â Â Â  Â  1983
1991
72Á40
100Á00
I6 Tao-Yuan 3Á3 2Á91 3Á01 35Á2 II Â Â Â Â Â
 Â Â Â Â 1992 115Á72
I7 Tou-Liu 3Á5 3Á7(1989) 4Á81 92Á6 II

 Â Â Â Â Â Â  Â Â 1989 92Á00
I8 Lung-Te 5 0Á93(1986)
11Á11(1993)
12Á33 42Á7 III
  Â Â Â  Â Â  Â 1993 122Á10
I9 Kuang-Hua 5 7Á41 9Á19 66Á7 I
  Â Â Â Â Â Â Â Â 1990 96Á15
I10 Ping-Nan 6 14Á6 14Á22 55Á3 III
  Â Â  Â Â Â Â  1993 122Á10
I11 Ta-Li 6 7Á56 9Á33 ±
b
III   Â Â  Â Â Â Â  1990 96Á15
I12 Chuan-Hsing 7 12Á1 11Á81 60Á4 III
  Â Â  Â Â  Â  1993 122Á10
I13 Kuan-Tien 10 10Á4 15Á15 92Á5 III
  Â Â  Â Â Â Â  1988 81Á57
I14 Kuan-Yin 10Á4 9Á63(1989)
1Á4(1992)
13Á93 103Á7 III
  Â Â  Â Â Â  Â 1989
1992
92Á00
115Á72
I15 Hsin-Ying 11 4Á4 7Á00 6Á22 III
 Â Â Â Â Â Â   Â 1987 75Á64
I16 Taichung (Yu-Shin) 11 6Á67 10Á93 87Á78 III
 Â Â Â Â Â Â   Â 1984 72Á64
I17 Fang-Yung 12 13Á7 13Á37 62Á22 III
  Â Â  Â Â Â  Â 1993 122Á10
390 H W. Chen and N B. Chang

I18 An-Ping 12(7) 3Á78(1981)
5Á93(1990)
13Á37 70Á37 III   Â Â  Â Â Â  Â 1981
1990
74Á73
96Á15
I19 Min-Hsiung 12 5Á93 18Á33 37Á04 III
 Â Â Â   Â Â Â  1985 72Á19
I20 Tu-Cheng 12 6Á83(1980)
4Á44(1990)
16Á62 83Á04 III
 Â Â Â  Â Â Â  Â 1980
1999
73Á5
96Á15
I21 Ping-Chen 12Á5 14Á07 14Á22 48Á19 III
  Â Â  Â Â Â Â  1994 117Á75
I22 Wu-Ku 12Á5 17Á59 20Á93 55Á56 II
  Â Â Â  Â Â Â Â 1991 100Á00
I23 Kaohsiung 15 13Á33 18Á52 495Á3 III
  Â Â  Â Â Â  Â 1981
1995
74Á73
119Á19
I24 Nan-Kang 16 17Á85 21Á26 109Á89 III
  Â Â  Â Â  Â  1991 100Á00
I25 Hsin-Chu (Hu-Kou) 21 11Á48 12Á41 162Á67 III
  Â Â  Â Â Â  Â 1980 73Á50
I26 Ta-She 22Á6 2Á22(1980)
2Á04(1990)

9Á26(1995)
15Á48 114Á81 III
 Â Â Â  Â Â Â  Â 1980
1995
73Á50
92Á00
119Á19
I27 Taichung 25 12Á22 19Á48 130Á89 II Â Â Â Â Â Â Â
 Â Â 1981 74Á73
I28 Ta-Yuan 25 2Á22(1985)
31Á11(1995)
34Á78 333Á33 III
  Â Â  Â Â Â Â  1985
1995
72Á19
119Á19
I29 Chung-Li (Nei-Li) 33Á5 876 32Á44 138Á52 III
 Â Â Â  Â Â Â  Â 1995 119Á19
a: EQ: equalization tank; FL: ¯otation; CS: contact-stabilization; AS: activated sludge; OD: oxidation ditch; RBC: rotating biological contactor; CO coagulation; SF: sand ®lter;
A
2
/O: anaerobic-anoxic-aerobic process; FL: ¯oatation tank.
b: `
' represents the inclusion of the designated unit; `Â' represents the exclusion of the designated unit ; `±' represents no information.
c: Primary industrial wastewater treatment process.
d: Secondary industrial wastewater treatment process.
e: Tertiary industrial wastewater treatment process.
f: Construction Cost Index in Taiwan.
g: Level of treatment: I (primary treatment), II (secondary treatment), and III (tertiary treatment).
Estimating costs of constructing wastewater treatment plants 391

the activated sludge (AS), the oxidation ditch (OD),
the rotating biological contractor (RBC), the unit
developed in Virginia Initiative Plant in Norfolk,
Virginia (VIP), and the relevant anaerobic-
anoxic-aerobic processes (A
2
/O). Besides, the
tertiary treatment process involves the removal of
nitrogen and phosphorus content such that add-
itional expensive units, such as coagulation (CO)
and sand ®lter (SF), are required. These methods
are frequently applied to preventing the eutrophi-
cation issues and maintaining the essential water
quality in the reservoirs/lakes close to the water
intakes.
Since the cost structures of constructing waste-
water treatment plants may cover various economic
implications at different time frames, all the col-
lected cost data must be subject to a normalization
process before the regression practices are per-
formed. The Construction Cost Index (CCI) was
thus selected as an economic factor to normalize
these cost data into a common temporal basis.
Normalization for the location difference, however,
was neglected because Taiwan is a spatially smaller
area. The currency ratio used in this analysis is
approximately 27NT$/lUS$ in 1995. Such a normal-
ized cost database, representing a large-scale cali-
brated effort to integrate the nationwide baseline
information of wastewater treatment plants, may

serve as a useful tool for the subsequent least square
and fuzzy regression analyses.
Two sets of diagrams (Figs 2±3 and 4±5) were
arranged to address the behaviour of the normalized
cost datasets. They are addressed in terms of total
construction costs and average construction costs
versus design ¯ow-rate, respectively. Although there
are several in¯uential observations (i.e. outliers)
that can be identi®ed in the database, deleting these
observations is not encouraged in the applications.
In the economic theory, it is anticipated that the
return-to-scale curve of construction cost of waste-
water treatment facilities actually ¯attens out
below some minimum size. As a result, conventional
wastewater management facilities for small com-
munities often cost signi®cantly more per capita to
construct when compared to those for larger cities.
Once the small communities become popular along
Figure 2. The distribution of total construction cost of all
domestic wastewater treatment plants in Taiwan.
Figure 3. The distribution of unit construction cost of all
domestic wastewater treatment plants in Taiwan.
Figure 4. The distribution of total construction cost of all
industrial wastewater treatment plants in Taiwan.
Figure 5. The distribution of unit construction cost of all
industrial wastewater treatment plants in Taiwan.
392 H W. Chen and N B. Chang
the river basin, this would contribute to the
increased per capita cost in the society. But the
sensitivity of the rate of increased per capita cost

remains unclear. Thus, this regression analysis can
be extended to identify the degree of economy of
scale and cost elasticity based on different types
of treatment facilities. Further observation in
Figures 2 and 4 con®rms that the variations of
total construction cost become larger as facility size
increases. This phenomenon does imply the exist-
ence of `heteroscedasticity' in statistics. Yet the
degree of heteroscedasticity of industrial waste-
water treatment plants is relatively smaller than
that of domestic wastewater treatment plants. To
identify the economy of scale easily and remove the
effect of heteroscedasticity in the least squares
regression analysis, the scatter plots of average
construction cost were therefore prepared for per-
forming the least squares regression analysis. Such
an alternation is equivalent to use the weighted
regression analyses in statistics. As shown in
Figures 3 and 5, the heteroscedasticity impact can
be reduced to a minimum extent as long as the
regression analysis is based on the plots of average
cost versus facility size. However, the heteroscedas-
ticity impact is not an issue in both fuzzy linear
regression and fuzzy goal regression practices since
they are designed to explore or explain such uncer-
tain cost structure in theory. As a consequence,
no pretreatment for the normalized datasets is
required before performing those fuzzy regression
analyses.
Model formulation and regression

analysis
Table 3 presents the formulation of several linear
and nonlinear regression models for both domestic
and industrial treatment plants. The datasets col-
lected in this study are fully applicable to support
such practices. When analyzing the cost structures
of domestic wastewater treatment plants, independ-
ent mathematical models formulated for primary,
secondary, and tertiary wastewater treatment
plants were sequentially taken into account based
on the LS, FLR, and FGR methods. It is recognized
that facility size or design ¯ow-rate is one of the
in¯uential factors in cost analysis and should be
included in the model formulation. To explore the
feature of economy of scale, the expression of design
¯ow-rate with exponent is needed in the model. The
value indicates economy of scale if the exponent is
less than 0 in these average cost equations. In
addition, dummy variables, representing a dichot-
omous option of a speci®c unit, are found helpful for
differentiating the cost impact of differing second-
ary wastewater treatment technologies. The alter-
natives of those secondary treatment technologies
cover CS, AS, OD, RBC, VIP, and the A
2
/O proces-
ses. The choice of these technologies, therefore, can
be formulated as an aggregate exponential term in
the model. Except the separate analysis designed
for each treatment level, an integrated regression

practice using all the collected data of domestic
wastewater treatment plants as a whole to provide
an overall insight of the cost structure would
also become achievable. Yet the total numbers of
samples of the industrial wastewater treatment
plants do not support basic differentiation in
terms of primary, secondary, and tertiary treatment
levels such that it is impossible to conduct a sep-
arate regression analysis with respect to different
treatment levels. But dummy variables still can be
used for differentiating the cost impact due to using
different biological treatment technologies.
Results and discussions
LINDO
1
and SAS
1
software packages were used as
computer solvers in dealing with the required linear
or nonlinear regression analyses. Tables 4 and 5
address all the regression outputs in this study. The
sign conventions in these models are generally
acceptable in most of the cases. The regression
results appear not well ®tted to the least squares
regression model in the integrated case of industrial
wastewater treatment plants. But the situation
turns out to be better in the case of domestic
wastewater treatment plants. The numbers in par-
entheses attached below those estimates in the least
squares practices are t-ratios in statistics. Some of

them pass the inference test with respect to 5%
level of signi®cance. But many of the dummy vari-
ables chosen in those separate cases of least squares
forecasting analysis are not statistically signi®cant.
This is probably due to the insuf®cient cost struc-
tures used to re¯ect the inherent uncertainties
in the cost estimation. On the other hand, the
impact of three outliers included in the database
of industrial wastewater treatment plants could be
in¯uential in the cost estimation when using the
LS model. The modi®ed coef®cients of determin-
ation (R
2
), representing the measurement of the
`goodness-of-®t' in regression, are reasonable for
those regression practices of domestic wastewater
Estimating costs of constructing wastewater treatment plants 393
Table 3. The formulation of fuzzy regression models
The categories
of wastewater
treatment plants
The levels of wastewater
treatment in different
categories of treatment plants
The cost structures designed for wastewater treatment plants
Domestic The case for primary
treatment process
CC  a
0
 a

1
 Q
The case for secondary
treatment process
CC  a
0
 Q
a1
EXP(a
2
 CS  a
3
 AS  a
4
 RBC  a
5
OD  a
6
A
2
/O)
The case for tertiary
treatment process
CC  a
0
 Q
a1
EXP(a
2
 CS  a

3
 AS  a
4
 RBC  a
5
 OD  a
6
A
2
/O  a
7
 ETU)
Integrated case for all
levels of wastewater
treatment processes
CC  a
0
 Q
a1
EXP(a
2
 CS  a
3
AS  a
4
 RBC  a
5
 OD  a
6
A

2
/O  a
7
 ETU)
Industrial CC  b
0
 Q
b1
EXP(b
2
 EQ  b
3
 CO  b
4
 FL  b
5
 AS  b
6
RBC  b
7
 OD  b
8
CO  b
9
 SF)
CC: total construction cost of wastewater treatment plants (1995Â10
6
US$); Q: design ¯ow-rate (tons/day; TPD). EQ: dummy variable designating the option of equalization tank; FL:
dummy variable designating the option of ¯otation; CS: dummy variable designating the option of contact-stabilization; AS: dummy variable designating the option of activated sludge
process; OD: dummy variable designating the option of oxidation ditch; RBC: dummy variable designating the option of rotating biological contactor; CO: dummy variable designating the

option of coagulation; SF: dummy variable designating the option of sand ®lter; A
2
/O: dummy variable designating the option of anaerobic-anoxic-aerobic process; FL: dummy variable
designating the option of ¯oatation tank, ETU: dummy variable designating the option of enhanced treatment unit.
Table 4. The outputs of regression models for industrial wastewater treatment plants
The types of
regression model
Coef®cients in regression models Tertiary treatment units The modi®ed
coef®cients of
determination (R
2
)
F values
b
0
b
1
(Q) b
2
(EQ) b
3
(CO) b
4
(FL) b
5
(AS) b
6
(RBC) b
7
(OD) b

8
(CO) b
9
(SF)
LS 22Á26
(5Á76)
Ã
0Á85
(6Á49)
0Á77
(1Á64)
0Á44
(1Á83)
0Á76
(0Á78)
À0Á16
(À0Á44)
0Á66
(1Á88)
0Á09
(0Á06)
À0Á29
(À1Á08)
0Á01
(À0Á39) 0Á69
7Á84
FLR 0Á82 0Á99 0Á71 0Á01 1Á22 À0Á33 0Á33 À0Á36 À0Á25 0Á36
FGR 17Á39 0 97 0Á71 0Á39 0Á76 À0Á18 0Á38 0Á09 À 0Á29 0Á01
Ã
t-ratios corresponding to the estimates of repressors in the regression models.

394 H W. Chen and N B. Chang
Table 5. The outputs of regression models for domestic wastewater treatment plants
The cases for
regression analysis
The types of
regression
models
a
0
a
1
a
2
(CS) a
3
(AS) a
4
(RBC) a
5
(OD) a
6
(VIP) a
7
(A2/O) a
8
(ETU) The modi®ed
coef®cients
of
determination (R
2

)
F values
The case for
primary
treatment
level
LS À406Á5
(À0Á91)
Ã
5Á68
(8Á33)
± ± ± ± ± ± ± 0Á94 69Á35
FLR À43Á4 0Á4 ± ± ± ± ± ± ± ± ±
FGR 1Á9 0Á18 ± ± ± ± ± ± ± ± ±
The case for
secondary
treatment
level
LS 187025
(1Á22 Â 10
6
)
0Á84
(11Á43)
À9Á16
(À9Á2 Â 10
À7
)
À8Á53
(À8Á6 Â 10

À7
)
± 8Á29
(À8Á3 Â 10
À7
)
± ± ± 0Á92 54Á54
FLR 1 0Á63 1Á01 1Á01 ± 1Á51 ± ± ± ± ±
FGR 1Á04 0Á88 À0Á009 À0Á002 0Á00 ± ± ± ± ±
The case for
tertiary
treatment
level
LS 19Á0
(1Á61 Â 10
À7
)
0Á76
(5Á97)
0Á76
(4Á12 Â 10
À8
)
1Á41
(7Á68 Â 10
À7
)
1Á86
(1Á02 Â 10
À7

)
1Á66
(5Á81 Â 10
À7
)
1Á06
(6Á08 Â 10
À8
)
1Á11
(9Á05 Â 10
À8
)
± 0Á82 13Á18
FLR 0Á10 0Á91 1Á56 1Á24 1Á38 0Á79 0Á93 1Á32 ± ± ±
FGR 33Á95 0Á92 0Á38 0Á00 0Á54 0Á48 0Á06 1Á03 ± ± ±
The integrated
case for all
treatment
levels
LS 0Á6
(7Á35)
Ã
0Á84
(17Á89)
0Á83
(2Á08)
0Á94
(3Á56)
1Á55

(3Á53)
1Á15
(2Á82)
0Á51
(1Á16)
0Á60
(1Á11)
0Á63
(3Á68)
0Á93 75Á92
FLR 0Á36 0Á89 1Á06 1Á37 1Á09 0Á65 0Á78 1Á22 0Á75 ± ±
FGR 0Á48 0Á86 0Á65 0Á87 1. 04 1Á22 0Á39 0Á47 0Á77 ± ±
Ã
t-ratios corresponding to the estimates of repressors in the regression models.
treatment plants. F values, representing the ef®-
ciency of overall model ®tting, also present statis-
tically signi®cant feature with respect to 5% level
of signi®cance for those regression practices of
domestic wastewater treatment plants. But it is
not the case when dealing with the industrial
wastewater treatment plants.
Figures 6±8 present a series of scatter plots of
observed values versus predicted values based on
different treatment levels and different methods
applied for regression analyses. Given the same
comparative framework, Figures 9 and 10 exhibit
the regression analyses associated with mixed types
of domestic and industrial wastewater treatment
plants, respectively. To further address the variance
changes over different facility sizes, Figure 11

illustrates the principles for the estimation of sam-
ples variance when applying the least squares and
fuzzy regression analyses. In particular, the estima-
tion of samples variance when applying the FLR and
Figure 6. The prediction of construction cost of primary
domestic wastewater treatment process by different
regression models.
Figure 7. The prediction of construction cost of second-
ary domestic wastewater treatment process by different
regression models.
Figure 8. The prediction of construction cost of tertiary
domestic wastewater treatment process by different
regression models.
Figure 9. The prediction of construction cost of mixed
types of domestic wastewater treatment process by
different regression models.
Figure 10. The prediction of construction cost of mixed
types of industrial wastewater treatment process by
different regression models.
396 H W. Chen and N B. Chang
FGR methods must rely on the use of linear and goal
programming models, respectively. While Figure 12
shows the bandwidth of con®dence interval over
samples based on the LS method, Figures 13 and 14
describe the fuzzy trajectories over observations
based on the FLR and FGR methods. Note that
discrepancies always exist in the presentation of
variations via the use of FLR and FGR analyses. The
numbers shown on each small axis in Figure 14
correspond to the degree of ®tting for each predicted

value. It can be seen that the way for the FLR and
FGR analyses to handle the variance changes and
outlier impacts are generally more ¯exible than that
for the LS method so that the overall ®tting can be
optimized.
Focus has also been placed on comparing the
overall prediction accuracy of construction cost of
wastewater treatment plants over different predic-
tion models. Several indexes have to be de®ned in
advance to determine whether any method of them
can be favored than the others. Tables 6±8 sum-
marize such assessment in terms of three perform-
ance indexes, including sum of absolute residual,
sum of squared residual, and average of the absolute
error percentage, with respect to primary, second-
ary, or tertiary treatment process, respectively.
Within these three tables, ®ndings clearly indicate
that the FLR method cannot always be favoured
over the others except for the case of analyzing
tertiary wastewater treatment plants. Although the
LS method always has better performance in terms
of the index of `sum of squared residual', the FGR
method may present relatively better outputs in
terms of the other two indexes considered. Table 9,
representing an integrated analysis associated with
all treatment levels of domestic wastewater treat-
ment plants, also con®rms the application potential
of the FGR method with respect to at least two
indexes considered. Similar conclusion can be made
based on an integrated analysis associated with all

treatment levels of industrial wastewater treatment
plants. Table 10 con®rms this conclusion. When
taking Tables 9 and 10 into account simultaneously,
it can be recognized that using the FGR method may
always generate the lowest value of average of the
absolute error percentage but exhibit relatively
higher values of sum of absolute residual and sum
of squared residual. In any circumstances, the FGR
method can always achieve a better performance
than the FLR method.
It can be concluded that the fuzzy linear regres-
sion model might not be suitable to deal with the
nonlinear regression issues although the proposed
model in this study can be linearized in advance
before the regression analysis is performed; on the
other hand, a higher forecasting capability of cost
estimation can be con®rmed via the use of the FGR
method in most of the cases. This is much due to the
fact that the FGR method may handle the complex-
ity of observations with smaller facility sizes, poten-
tial outliers, and/or non-homogeneous features in
sample variance over facility sizes. Conventional
Figure 11. The expression of uncertainties in relation to different regression models.
Estimating costs of constructing wastewater treatment plants 397
Figure 12. The prediction results and associated con®dence interval for industrial wastewater treatment plants based on
the LS method.
Figure 13. Fuzzy trajectory of fuzzy linear regression model for industrial wastewater treatment plants.
398 H W. Chen and N B. Chang
least squares method cannot control fragmental and
uncertain datasets easily. This ®nding, coupled with

the exposition of previous work done by Chang et al.
(1996), makes the derivation of the FGR method
applied to forecasting analysis become crucial.
In most real world applications, moderate econ-
omy of scale does exist in constructing both the
domestic and industrial wastewater treatment
plants. Overall, the optimal size of a domestic
wastewater treatment plant is approximately
Figure 14. Fuzzy trajectory of fuzzy goal regression model for industrial wastewater treatment plants.
Table 6. The comparative study of primary wastewater treatment plant
Plant no. Design
capacity
(1000 CMD)
Normalized
construction cost
(1995 million US$)
LS FLR

FGR
Predicted
value
Residual Predicted
value
Residual Predicted
value
Residual
30 78 15Á91 36Á23 20Á33 À12Á45 À28Á36 15Á89 À0Á02
42 175 40Á00 21Á73 À18Á27 26Á01 À13Á99 33Á13 À6Á87
45 274 5Á64 42Á54 36Á90 65Á27 59Á63 50Á73 45Á09
47 560 102Á13 102Á67 0Á54 178Á69 76Á56 101Á57 À0Á56

48 1320 267Á04 262Á43 À4Á61 480Á09 213Á05 236Á69 À30Á35
Sum of absolute residual

80 391 82
Sum of squared residual

2130 55808 3001
Average of absolute error percentage

166% 285% 166%
aX e
i
 0; bX

residual
j j
; gX

residual
2
; dX

Y À residual
j j
residual
 
6100%X
Estimating costs of constructing wastewater treatment plants 399
Table 7. The comparative study of secondary wastewater treatment plants
Plant

no.
Design
capacity
(1000 CMD)
Normalized
construction cost
(1995 million US$)
LS FLR

FGR
Predicted
value
Residual Predicted
value
Residual Predicted
value
Residual
2 0Á2 0Á14 0Á00 À0Á14 1Á00 0Á86 0Á14 0Á00
3 0Á2 0Á29 0Á36 0Á07 1Á00 0Á71 0Á29 0Á00
11 13 8Á19 0Á00 À8Á19 13Á82 5Á63 5Á76 À2Á43
13 16 44Á81 14Á10 À30Á71 15Á75 À29Á06 13Á65 À31Á16
20 33 22Á15 25Á90 3Á75 24Á85 2Á70 25Á86 3Á71
23 38 22Á70 29Á20 6Á50 27Á16 4Á46 29Á30 6Á60
25 44 28Á15 33Á00 4Á85 29Á79 1Á64 33Á34 5Á19
26 54 42Á96 39Á20 À3Á76 33Á89 À9Á07 39Á95 À3Á01
27 63 126Á56 44Á60 À81Á96 37Á34 À89Á22 45Á77 À80Á79
28 64 49Á63 45Á20 À4Á43 37Á72 À11Á91 46Á42 À3Á21
31 87Á5 74Á48 74Á50 0Á02 15Á56 À58Á92 74Á49 0Á01
33 89Á5 50Á22 59Á90 9Á68 75Á73 25Á51 62Á41 12Á19
34 95 72Á37 63Á00 À9Á37 46Á59 À25Á78 65Á78 À6Á59

36 130 39Á70 82Á00 42Á30 48Á37 8Á67 86Á77 47Á07
37 132 73Á63 83Á00 9Á37 58Á94 À14Á69 87Á94 14Á31
38 133 47Á81 83Á60 35Á79 59Á51 11Á70 88Á53 40Á72
41 165 66Á63 100Á00 33Á37 59Á79 À6Á84 107Á09 40Á46
43 176 113Á33 106Á00 À7Á33 68Á49 À44Á84 113Á37 0Á04
46 331 215Á26 180Á00 À35Á26 71Á34 À143Á92 198Á00 À17Á26
Sum of absolute residual

327 496 314
Sum of squared residual

13618 37076 13812
Average of absolute error percentage

37% 75% 29%
aX e
i
 0; bX

residual
j j
; gX

residual
2
; dX

Y À residual
j j
residual

 
6100%X
Table 8. The comparative study of tertiary wastewater treatment plants
Plant
no.
Design
capacity
(1000 CMD)
Normalized
construction cost
(1995 million US$)
LS FLR

FGR
Predicted
value
Residual Predicted
value
Residual Predicted
value
Residual
1 0Á1 0Á48 0Á26 À 0Á22 0Á33 À 0Á15 0Á38 À 0Á10
4 0Á27 3Á63 1Á68 À 1Á95 2Á34 À 1Á29 0Á55 À 3Á08
5 0Á45 1Á47 2Á47 1Á00 0Á94 À 0Á53 0Á88 À 0Á59
6 0Á5 1Á07 0Á88 À 0Á19 1Á44 0Á37 1Á67 0Á60
7 0Á5 0Á66 1Á70 1Á03 1Á04 0Á37 0Á66 0Á00
8 2 7Á37 2Á53 À 4Á84 5Á10 À 2Á27 6Á02 À 1Á35
9 2Á4 4Á15 2Á90 À 1Á25 6Á03 1Á88 7Á12 2Á97
10 12Á9 14Á81 14Á81 0Á00 14Á82 0Á01 14Á82 0Á01
12 13 22Á70 19Á95 À 2Á75 20Á31 À 2Á39 13Á47 À 9Á23

14 17 31Á74 24Á45 À 7Á29 25Á94 À 5Á80 17Á26 À 14Á48
15 18 31Á30 40Á29 8Á99 31Á47 0Á17 26Á70 À 4Á60
16 21Á7 20Á37 20Á87 0Á50 20Á86 0Á49 20Á37 0Á00
17 22 34Á48 29Á71 À 4Á77 32Á83 À 1Á65 21Á90 À 12Á58
18 22Á8 22Á22 21Á67 À 0Á55 21Á82 À 0Á40 21Á32 À 0Á90
19 23 35Á89 30Á73 À 5Á16 34Á19 À 1Á70 22Á82 À 13Á07
21 34 53Á07 53Á07 0Á00 53Á24 0Á17 53Á07 0Á00
22 38 36Á30 44Á93 8Á63 54Á07 17Á77 36Á29 À 0Á01
24 41 60Á67 47Á59 À 13Á08 57Á95 À 2Á72 38Á93 À 21Á74
29 75 86Á70 75Á17 À 11Á53 100Á59 13Á89 68Á03 À 18Á67
35 130 122Á60 113Á98 À 8Á62 122Á15 À 0Á45 113Á10 À 9Á50
Sum of absolute residual

82 54 113
Sum of squared residual

675 573 1579
Average of absolute error percentage

30% 19% 27%
aX e
i
 0; bX

residualj j; gX

residual
2
; dX


Y À residual
j j
residual
 
6100%X
equivalent to 15 000 CMD and higher in Taiwan.
The greater the design capacity, the less the unit
construction cost appears. On the other hand, the
optimal size of an industrial wastewater treatment
plant turns out to be more ¯exible. It falls in
between 6000 CMD and 20 000 CMD.
Conclusions
The awareness of the need for conservation of water
resources and for control of wastewater streams has
motivated various water reuse, treatment, and
Table 9. The comparative study based on all domestic wastewater treatment plants
Plant
no.
Design
capacity
(1000 CMD)
Normalized
construction cost
(1995 million US$)
LS FLR

FGR
Predicted
value
Residual Predicted

value
Residual Predicted
value
Residual
1 0Á1 0Á48 0Á31 À0Á17 0Á29 À0Á19 0Á27 À0Á21
2 0Á2 0Á14 0Á29 0Á15 0Á25 0Á11 0Á23 0Á08
3 0Á2 0Á29 0Á33 0Á04 0Á34 0Á06 0Á29 0Á00
4 0Á27 3Á63 1Á46 À2Á17 2Á83 À0Á80 0Á95 À2Á68
5 0Á45 1Á47 2Á25 0Á78 1Á50 0Á03 1Á47 0Á00
6 0Á5 1Á07 1Á20 0Á12 1Á21 0Á13 1Á08 0Á01
7 0Á5 0Á66 1Á34 0Á68 1Á64 0Á98 1Á35 0Á69
8 2 7Á37 3Á85 À3Á52 4Á14 À3Á23 3Á55 À3Á82
9 2Á4 4Á15 4Á49 0Á35 4Á87 0Á72 4Á15 0Á00
10 12Á9 14Á81 14Á81 0Á00 16Á45 1Á63 14Á82 0Á00
11 13 8Á19 9Á98 1Á80 10Á35 2Á16 8Á19 0Á00
12 13 22Á70 20Á96 À1Á74 29Á87 7Á17 22Á14 À0Á56
13 16 44Á81 13Á33 À31Á49 16Á98 À27Á84 12Á25 À32Á56
14 17 31Á74 26Á29 À5Á45 37Á93 6Á19 27Á87 À3Á87
15 18 31Á30 50Á70 19Á41 30Á16 À1Á13 34Á85 3Á55
16 21Á7 20Á37 20Á84 0Á47 22Á94 2Á57 21Á30 0Á93
17 22 34Á48 32Á68 À1Á80 47Á71 13Á23 34Á77 0Á29
18 22Á8 22Á22 21Á72 À0Á50 23Á97 1Á75 22Á23 0Á01
19 23 35Á89 33Á93 À1Á96 49Á64 13Á75 36Á13 0Á24
20 33 22Á15 24Á55 2Á41 32Á33 10Á18 22Á80 0Á65
21 34 53Á07 57Á75 4Á68 60Á50 7Á42 71Á50 18Á42
22 38 36Á30 51Á84 15Á54 77Á60 41Á31 55Á58 19Á29
23 38 22Á70 27Á66 4Á96 36Á66 13Á95 25Á73 3Á03
24 41 60Á67 55Á28 À5Á39 83Á03 22Á37 59Á33 À1Á34
25 44 28Á15 31Á30 3Á16 41Á77 13Á62 29Á18 1Á03
26 54 42Á96 37Á21 À5Á75 50Á12 7Á15 34Á79 À8Á17

27 63 126Á56 42Á38 À84Á17 57Á49 À69Á07 39Á71 À86Á85
28 64 49Á63 42Á95 À6Á68 58Á30 8Á67 40Á25 À9Á38
29 75 86Á70 92Á04 5Á33 142Á13 55Á42 99Á61 12Á91
30 78 15Á91 19Á76 3Á85 17Á67 1Á76 20Á00 4Á09
31 87Á5 74Á48 68Á45 À6Á04 66Á28 À8Á20 74Á49 0Á01
32 89Á5 50Á22 57Á01 6Á79 78Á57 28Á35 53Á67 3Á45
33 95 72Á37 59Á95 À12Á42 82Á86 10Á49 56Á49 À15Á88
34 130 122Á56 146Á43 23Á88 128Á54 5Á99 159Á70 37Á14
35 130 39Á70 78Á13 38Á42 109Á54 69Á83 73Á94 34Á23
36 132 73Á63 79Á14 5Á51 111Á04 37Á41 74Á91 1Á28
37 133 47Á81 79Á65 31Á83 111Á78 63Á97 75Á40 27Á58
38 165 66Á63 95Á55 28Á92 135Á43 68Á80 90Á72 24Á09
39 175 40Á00 39Á09 À0Á91 36Á26 À3Á74 40Á01 0Á01
40 176 113Á33 100Á90 À12Á44 143Á44 30Á10 95Á89 À17Á45
41 331 215Á26 171Á98 À43Á28 251Á65 36Á39 164Á87 À50Á39
42 560 102Á13 104Á37 2Á24 102Á11 À0Á02 108Á55 6Á42
43 1320 267Á04 215Á25 À51Á79 219Á02 À48Á02 226Á55 À40Á49
Sum of absolute residual

489 746 473
Sum of squared residual

17848 32646 18398
Average of absolute error percentage

28% 40% 23%
aX e
i
 0Y b X


residual
j j
Y g X

residual
2
; dX

Y À residual
j j
residual
 
6100%X
Estimating costs of constructing wastewater treatment plants 401
disposal programs. All of them require accurate
prediction of cost information to support a success-
ful planning and assessment. But cost analysis
involves many uncertain factors that could become
one of the impediments in decision-making. Apart
from providing direct investigation of the issues of
cost structures for building wastewater treatment
plants in an uncertain environment using different
model formulations, this study also tries to answer
what is the optimal size of small community that
would suffer the least degree of higher cost in
wastewater treatment and what are the possible
uncertainties in estimating the cost of constructing
wastewater treatment plants when using different
estimation methods. The case study starts from the
illustration of the latest development information of

wastewater treatment plants in Taiwan. With the
help of recently derived fuzzy regression techni-
ques, the application potential for the cost estima-
tion of wastewater treatment plants was assessed by
a comparative approach. Three regression analysis
techniques were applied in terms of three perform-
ance indexes. The model outputs clearly verify
that, with the merits of ¯exible patterns of fuzzy
membership function and minimum required
degree of ®tting, the newly derived fuzzy goal
regression model owns the most robust algorithm
in practice, and generally exhibits a higher predic-
tion accuracy when compared to previous analytical
techniques. Such an improvement is signi®cant in
search of the better management strategy in the
real world applications.
Table 10. The comparative study based on all industrial wastewater treatment plants
Plant no. Design
capacity
(1000 CMD)
Normalized
construction cost
(1995 million US$)
LS FLR

FGR
Predicted
value
Residual Predicted
value

Residual Predicted
value
Residual
1 0Á4 0Á45 0Á55 0Á54 0Á48 0Á03 0Á45 0Á00
2 1Á75 4Á40 4Á40 5Á30 5Á55 1Á14 4Á40 0Á00
3 2Á5 6Á89 5Á91 0Á86 5Á79 À1Á10 6Á89 0Á00
4 3 3Á91 4Á27 À0Á52 4Á92 1Á01 4Á19 0Á27
5 3Á2 4Á46 4Á53 À0Á92 5Á25 0Á79 4Á46 0Á00
6 3Á3 3Á01 3Á69 0Á38 3Á70 0Á69 3Á01 0Á00
7 3Á5 4Á81 4Á20 À0Á10 4Á00 À0Á82 4Á81 0Á00
8 5 12Á33 9Á70 À1Á70 8Á96 À3Á38 10Á09 À2Á25
9 5 9Á19 8Á30 0Á72 8Á27 À0Á92 9Á18 0Á00
10 6 14Á22 9Á77 À3Á10 10Á20 À4Á02 9Á23 À4Á99
11 6 9Á33 9Á77 1Á79 10Á20 0Á87 9Á23 À0Á10
12 7 11Á81 10Á36 6Á84 8Á29 À3Á52 11Á72 À0Á09
13 10 15Á15 15Á49 0Á19 16Á92 1Á77 15Á15 0Á00
14 10Á4 13Á93 12Á05 3Á62 9Á56 À4Á37 11Á64 À2Á28
15 11 7Á00 10Á37 1Á59 9Á68 2Á68 10Á93 3Á93
16 11 10Á93 10Á37 À2Á34 9Á68 À1Á25 10Á93 0Á00
17 12 13Á37 13Á71 5Á84 11Á01 À2Á36 13Á38 0Á01
18 12 13Á37 13Á71 5Á84 11Á01 À2Á36 13Á38 0Á01
19 12 18Á33 18Á39 À10Á20 27Á83 9Á50 17Á99 À0Á34
20 12 16Á62 10Á38 À9Á12 10Á87 À5Á75 9Á06 À7Á56
21 12Á5 14Á22 18Á95 3Á44 21Á10 6Á88 18Á80 4Á58
22 12Á5 20Á93 25Á26 0Á42 28Á49 7Á56 32Á80 11Á87
23 15 18Á52 16Á77 3Á59 13Á74 À4Á78 16Á61 À1Á91
24 16 21Á26 21Á85 10Á14 18Á80 À2Á46 26Á12 4Á87
25 21 12Á41 22Á73 14Á92 19Á16 6Á76 23Á01 10Á61
26 22Á6 15Á48 18Á38 À4Á30 20Á34 4Á86 16Á74 1Á26
27 25 19Á48 15Á91 À4Á18 13Á77 À5Á71 15Á97 À3Á51

28 25 34Á78 35Á43 À7Á45 41Á92 7Á14 36Á83 2Á05
29 33Á5 32Á44 26Á22 À18Á11 30Á04 À2Á41 24Á52 À7Á92
Sum of absolute residual

60Á86 96Á87 70Á42
Sum of squared residual

297Á72 504Á26 490Á62
Average of absolute error percentage

96% 25% 15%
aX e
i
 0; bX

residual
j j
; gX

residual
2
; dX

Y À residual
j j
residual
 
6100%X
402 H W. Chen and N B. Chang
The inherent uncertainties when making choice

of the centralized treatment facilities require more
comprehensive evaluation. This study con®rms that
moderate economy of scale does exist in construct-
ing both the domestic and industrial wastewater
treatment plants. The optimal size of a domestic
wastewater treatment plant is approximately
equivalent to 15 000 CMD and higher in Taiwan.
The greater the design capacity, the less the unit
construction cost appears. On the other hand, the
optimal size of an industrial wastewater treatment
plant turns out to be more ¯exible. It falls in
between 6000 CMD and 20 000 CMD. Small com-
munities do not bene®t the economy of scale that are
possible with the construction of wastewater man-
agement facilities for larger communities. Thus,
integrated planning with neighboring sewage sys-
tems can be encouraged when shipping cost is not
an in¯uential factor.
Acknowledgements
The authors acknowledge the ®nancial support from the
National Science Council (NSC89-2211-E-006-005) in
Taiwan and helpful comments raised by all anonymous
referees in this study.
References
Bardossy, A., Bogardi, I., and Duckstein, L. (1990). Fuzzy
regression in hydrology. Water Resources Research 26,
1497±1508.
Bardossy, A. (1990). Note of fuzzy regression. Fuzzy Sets
and Systems 37, 65±75.
Bellman, R. E. and Zadeh, L. A. (1970). Decision making

in a fuzzy environment. Management Science 17,
B141±B164.
Chang, N. B. and Chen, H. W. (1997). Water pollution
control in a river basin by interactive fuzzy interval
multi-objective programming. Journal of Environmen-
tal Engineering, ASCE 123, 1208±1216.
Chang, N. B. and Wang, S. F. (1995a). Optimal planning
for the coastal wastewater treatment and disposal
system. Coastal Management 23, 153±166.
Chang, N. B. and Wang, S. F. (1995b). The development
of material recovery facilities in the United States:
status and cost structure analysis. Resources Con-
servation and Recycling 13, 115±128.
Chang, N. B., Chen, Y. L., and Yang, H. H. (1996). A fuzzy
goal regression model for the construction cost
estimation of municipal waste incinerators. Interna-
tional Journal of Systems Science 27, 433±445.
Chen, S. Q. (1988). Analysis for multiple fuzzy regres-
sions. Fuzzy Sets and Systems 25, 59±65.
Diamond, P. (1988). Fuzzy least squares. Information
Science 46, 141±157.
Gharpuray, M. M., Tanaka, H., and Fan, L. T. (1986).
Fuzzy linear regression analysis of cellulose hydro-
lysis. Chemical Engineering Communication 41,
299±314.
Graves, G. W., Whinston, A. B., and Hat®eld, G. B. (1970).
Mathematical programming for regional water quality
management. Department of Interior, Washington DC,
USA.
Greenberg, H. J. (1995). Mathematical programming

models for environmental quality control. Operations
Research, 43, 578±622.
Hannan, E. L. (1981). On fuzzy goal programming.
Decision Science 12, 522±531.
Hayashi, I. and Tanaka, H. (1990). The fuzzy GMDH
algorithm by possibility models and its application.
Fuzzy Sets and Systems 36, 245±258.
Heshmaty, B. and Kandel, A. A. (1985). Fuzzy linear
regression and its applications to forecasting in
environment. Fuzzy Sets and Systems 15, 159±191.
Jajuga, K. (1986). Linear fuzzy regression. Fuzzy Sets
and Systems 20, 343±353.
Juang, C. H., Huang, X. H., and Holtz, R. D. (1992).
Determination of fuzzy relationship by fuzzy regres-
sion. Civil Engineering Systems 5, 299±318.
Lu, F. and Guang, X. X. (1993). A forecasting model
of fuzzy self-regression. Fuzzy Sets and Systems 58,
239±242.
Moskowitz, H. and Kim, K. (1993). On assessing the
H-value in fuzzy linear regression. Fuzzy Sets and
Systems 58, 303±327.
Narasimha, R. (1980). Goal programming in a fuzzy
environment. Decision Science 11, 325±338.
Oh, S. B., Kim, W., and Lee, J. K. (1992). An approach
to causal modeling in fuzzy environment and its
application. Fuzzy Sets and Systems 51, 179±188.
Robert, H. V. N. 1975. A Guide to the Selection of Cost-
effective Wastewater Treatment Systems. US EPA.
Sakawa, M. (1992). Multi-objective fuzzy linear regres-
sion analysis for fuzzy input-output data. Fuzzy Sets

and Systems 47, 173±181.
Savic, D. A. and Pedrycz, W. (1991). Evaluation of fuzzy
linear regression models. Fuzzy Sets and Systems 39,
51±63.
Tanaka, H., Uejima, S., and Asia, K. (1982). Linear
regression analysis with fuzzy model. IEEE Transac-
tions on Systems, Man and Cybernetics 12, 275±280.
Tanaka, H. and Asia, K. (1984a). Fuzzy solution in fuzzy
linear programming problems. IEEE Transactions on
Systems, Man and Cybernetics 14, 325±328.
Tanaka, H. and Asia, K. (1984b). Fuzzy linear program-
ming with fuzzy numbers. Fuzzy Sets and Systems 13,
1±10.
Tanaka, H. (1987). Fuzzy data analysis by possibilistic
linear model. Fuzzy Sets and Systems 24, 363±375.
Tanaka, H. and Watada, J. (1988). Possibilistic linear
system and their application to the linear regression
model. Fuzzy Sets and Systems 27, 275±289.
Tanaka, H., Hayashi, I., and Watada, J. (1989).
Possibilistic linear regression analysis for fuzzy
data. European Journal of Operational Research 40,
389±396.
Wang, X. and Ha, M. (1992). Fuzzy linear regression
analysis. Fuzzy Sets and Systems 51, 179±188.
Wen, Ching-Gung and Lee, Chih-Sheng (1999). Develop-
ment of a cost function for wastewater treatment
Estimating costs of constructing wastewater treatment plants 403
systems with fuzzy regression. Fuzzy Sets and Systems
106, 143±153.
Zedah, L. A. (1965). Fuzzy sets. Information and Control

8, 338±353.
Zimmermann, H. J. (1978). Fuzzy programming and
linear programming with several objective functions.
Fuzzy Sets and Systems 25, 175±182.
Zimmermann, H. J. (1985). Application of fuzzy sets
theory to mathematical programming. Information
Science 35, 29±58.
Appendix I: the theory of fuzzy
linear regression models
In fuzzy sets theory (Zedah, 1965), a fuzzy set A can
be characterized by a membership function, usually
denoted m, which assigns to each object of a domain
its grade of membership in A. The more an element
or object can be said to belong to a fuzzy set A,
the closer to 1 is its grade of membership. Such
an uncertainty description has been successfully
applied to many real-world problems for engineer-
ing planning, design, operation, management, and
control. The following sections provide a brief
review of previous fuzzy linear regression model
(Tanaka et al., 1982) and the derivation of the
proposed fuzzy goal regression model.
Tanaka et al. (1982) introduced the idea of fuzzy
linear regression. According to their discussions,
fuzziness must be considered in systems where
human estimation is in¯uential. The fuzzy regres-
sion structure actually focuses on ®nding a set of
fuzzy parameters to achieve a speci®c mapping
between the explanatory variables (independent
variables) and the explained variable (dependent

variable). If Y and x are the set of dependent vari-
ables and independent variables respectively, the
mapping can be performed by using fuzzy function
Y  (x, A), where A is the set of fuzzy parameters. In
order to establish the target of minimum vagueness
in the mapping process, a linear programming
model must be built up, subject to the minimum
required degree of ®tting on each observation. The
algorithm is illustrated below. The fuzzy para-
meters used in the algorithm can be de®ned by the
multidimensional fuzzy sets. Figure A1 illustrates a
two-dimensional case. This fuzzy set can therefore
be represented as (A1)
m
A
a  minm
Aj
a
j

m
Aj
a
j
 
1 À
a
j
Àa
j

j j
c
j
if a
j
À c
j
a
j
a
j
 c
j
0 otherwise
@
A1
Given fuzzy parameter A  {a,c}, described by the
center a and the width c, the fuzzy linear function is
Y  A
1
x
1
 A
2
x
2
 Á Á Á  A
n
x
n

A2
where A  (A
1
,A
2
, F F F ,A
n
), a  (a
1
,a
2
, F F F a
n
)
t
and
c  (c
1
,c
1
, F F F ,c
n
)
t
In this method, Y could be non-fuzzy or fuzzy
input data, as shown in Figure A2. The membership
function of dependent variable Y can then be
de®ned by (A3).
m
Y

y
i
 
1 À
y
i
Àx
t
a
j j
c
t
x
j j
if x=0
1 if x  0, y  0
0 if x  0, y=0
V
b
`
b
X
A3
where and jxj  jx
1
jY jx
2
j, F F F jx
n
j

t
, when m
Y
(y
i
)  0,
when jc
t
xj jy
i
À x
t
ajw. Regardless of the type
of the data, the vagueness of the fuzzy linear
Figure A1. Fuzzy set of parameter A: A approximates a.
404 H W. Chen and N B. Chang
model is expressed in (A4) (Tanaka et al. 1982,
Tanaka 1987).
J  c
1
 c
2
 Á Á Á  c
n
or
J  c
t
x







i
c
t
jx
i
j


i

j
c
t
j
x
ij




X
A4
which can be minimized subject to h
i
! H, where
H is the prescribed degree of ®tting and h

i
is the
individual degree of ®tting corresponding to each
observation Y
i
.
For the case of having a fuzzy dependent variable,
as illustrated in Figure A3, h
i
can be de®ned by (A5)
h
i
 1 À
y
i
À x
t
i
a





j
c
t
j
x
ij





À e
i
A5
where e
i
is the subjective measure of vagueness for
the observed Y value. The following linear program-
ming model, in (A6)±(A9), is therefore used to ®nd
fuzzy parameter A
*
i
 (a
i
,c
i
):
minimize J 

i
c
t
x
i
j j A6
subject to
a

t
x
i
 1 À H

j
c
t
j
x
ij




! y
i
 1 À He
i
Vi A7
Àa
t
x
i
 1 À H

j
c
t
j

x
ij




! Ày
i
 1 À He
i
Vi
A8
c
j
! 0 Vj A9
in which H is the minimum required degree of
®tting.
Appendix II: the theory of fuzzy
goal regression models
Fuzzy goal regression model is derived from the
concept of fuzzy goal programming. Since the
Figure A2. The fuzzy type of input-output data in fuzzy
linear.
Non fuzzy input-fuzzy output data
Sample number Fuzzy output, Y
i
Inputs, X
ij
1 Y
1

 (y
1
,e
1
) x
11
,F F Fz
1n
F
F
F
F
F
F
F
F
F
N Y
N
 (y
N
,e
N
) x
N1
,F F Fz
Nn
Figure A3. The fuzzy type of input-output data in fuzzy linear regression.
Estimating costs of constructing wastewater treatment plants 405
solution approach of fuzzy mathematical program-

ming is generally designed to satisfy the fuzzy
objectives and constraints simultaneously, a deci-
sion space in a fuzzy environment is thus de®ned as
the intersection of those membership functions
corresponding to those fuzzy objectives and con-
straints (Zimmermann, 1985). Therefore, if {m
G1
,
m
G2
, F F F , m
G2m
} and {m
C1
, m
C2
, F F F , m
Cp
} are denoted
as the fuzzy membership functions for those fuzzy
objectives {G
l
, G
2
, F F F , G
m
} and fuzzy constraints
{C
1
, C

2
, F F F , C
p
} respectively in a decision space X,
all the fuzzy membership functions of G
m
and C
p
may then be combined to form a decision D, which is
a fuzzy set resulting from the intersection of all
related G
m
and C
n
as shown below.
D  G
1
 G
2
 F F F  G
m
 C
1
 C
2
 F F F  C
p
Since the decision D is de®ned as a fuzzy set, the
optimal decision is any alternative s [ S that can
maximize the minimum attainable aspiration levels

in decision-making. The aspiration level of each
fuzzy membership function is actually a common
membership value achieved in the decision set,
m
D
(s), ®nally. Thus, the max-min convolution
requires maximizing the minimum membership
values of those elements, as below (Zimmermann,
1978):
max
s
m
D
max
s
minfm
G
1
, m
G
2
, F F F , m
G
2m
;
m
C
1
, m
C

2
, F F F , m
C
p
g
Since Narasimhan (1980) and Hannan (1981)
applied the fuzzy sets theory for solving fuzzy
goal-programming models, many similar achieve-
ments have been made and recorded in the litera-
ture. In this section, we will present a typical
approach that eventually leads to a full illustration
of the theory of fuzzy goal regression model for use
in various forecasting practices.
In a goal-programming problem, planning goals
are stated precisely and algebraic equations are
formulated to correspond to the stated goal. The
realization of goals can be described by a set of goal
constraints in a given environment. In other words,
the most important characteristic of goal program-
ming is that goals and all the de®nitional con-
straints are treated as fully symmetric.
Symbolically, it can be formulated as:
find x
such that Ax  b and x ! 0 A10
Where b is the vector of goals and resources
available, and A is the matrix of the technological
coef®cients. If the decision-maker may feel that it is
impossible to precisely state exact goals or exact
resources available, the problem can be formulated
as a deterministic goal programming model. How-

ever, in many circumstances, the linguistically
vague statement such as `around b' is more
acceptable and comfortable in the decision-making
process. For instance, `the annual cost should be
about $20 000'. Such a goal programming with
linguistic goals can be formulated as:
find x
such that (Ax)
i

~
b
i
, i  1,2, F F F ,m
x ! 0 A11
where
~
b
i
express linguistic goals such as `the cost
should be around
~
b
i
.' We may have the following
similar problem:
find x
such that (Ax)
i
%b

i
, i  1,2, F F F ,m
x ! 0 A12
where the fuzzy equality constraints express that
earned pro®ts should be around b
i
if the membership
functions can be applied for modeling the imprecise
nature of `fuzzy goals' and `fuzzy equality'.
To resolve those fuzzy equalities, we should elicit
their membership functions based on the preference
concept from the decision-makers. For the sake of
mathematical tractability, the membership func-
tions for short m
i
((Ax)
i
) (or m
i
(x) for short) of fuzzy
equations are assumed to be symmetrically triangu-
lar functions (see Figure A4 where d
i1
 d
i2
 d
i
).
That is:
m

i
x

Ax
i
À b
i
À d
i

Â
ad
i
b
i
 d
i
 À Ax
i
ÃÂ
ad
i
0
V
b
`
b
X
if b
i

À d
i
Ax
i
b
i
if b
i
Ax
i
b
i
 d
i
if b
i
 d
i
Ax
i
or Ax
i
 b
i
À d
i
A13
Figure A4. Triangular membership functions for fuzzy
equations/goals.
406 H W. Chen and N B. Chang

Where d
i
are the maximum acceptable deviations
(subjectively determined) from the center b
i
. On
the other hand, triangular membership functions
can also be expressed (b
i
, b
i
À d
i
, b
i
 d
i
) where b
i
is the most preferred value and b
i
À d
i
(the most
pessimistic value) and b
i
 d
i
(the most optimistic
value) are the least preferred values, Vi.

To solve Equation (A12) when Equation (A13)
is given, Narasimhan (1980) proposed the follow-
ing 2
m
sub-problems of equivalent standard goal
programming.
max min
i
Axf
i
Àb
i
À d
i
ad
i
g, for some i
such that b
i
À d
i
Ax
i
b
i
and x ! 0
A14
and
max min
i

b
i
 d
i
 À Ax
i
ÂÈ
ad
i
g
, for other i
such that b
i
Ax
i
b
i
À d
i
and x ! 0
A15
By linking Equations (A14) and (A15) together, we
obtain:
max a
subject to
Ax
i
À b
i
À d

i
ad ! a for some i
b
i
À d
i
Ax
i
b
i
b
i
 d
i
 À Ax
i
ad ! a for other i
b
i
Ax
i
b
i
À d
i
a [ 0,1  and x ! 0 A16
That is equivalent to consider the issue by a
superimposition between two fuzzy membership
functions. In general, a non-increasing and a non-
decreasing linear membership functions are

frequently used for those fuzzy constraints with
`approximately smaller than or equal to' and
`approximately larger than or equal to' relation-
ships, respectively, as shown in most previous liter-
ature (Bellman and Zadeh, 1970; Zimmermann,
1978; Zimmermann, 1985).
Hence, the fuzzy structure illustrated in (A16)
can be applied for solving the fuzzy goal regression
model. In a fuzzy goal regression analysis, the
proposed linear regression model (

a
i
x
i
) can be
viewed as a linear function that is designed to
approach the target value or the observed value
of dependent variable Y. The regression effort
for each set of observation, corresponding to one
dependent variable and several independent vari-
ables, is to achieve the goal where the target value
is approximated by a set of fuzzy parameters, a
i
,
multiplied by the observed input data, x
i
. For n sets
of observations, we have n set fuzzy goals to be
handled in the fuzzy goal-programming model. The

regression analysis problem can therefore be stated
as a maximization process of the minimum degree
of ®tting for these goal constraints from a global
perspective. However, the achievement of each goal
constraint, expressed by a triangular membership
function, can be regarded as a superimposition of
two linear fuzzy membership functions. One is a
non-increasing function, while the other is a non-
decreasing function, as shown in Figure A5(a).
The highest degree of ®tting may be attained
when the observed value of dependent variable Y is
Figure A5. The membership functions used in fuzzy goal regression model.
Estimating costs of constructing wastewater treatment plants 407