T
O
Centre for Regional Science Research
Applied Methods
for Analysis of
Economic Structure
and Change
Christer A nderstig
CERUM RAPPORT/CERUM REPORT 1988:2.
APPLIFD METHODS FOR ANALYSES OF ECONOMIC
STRUCTURE AND CHANGE
AKADEMISK AVHANDLING
som for avläggande av filo s o fie doktorsexam en
vid sam h ällsvetensk apliga fa k u lteten vid Um eå u n iversitet
fram lägges till o ffe n tlig granskning
fredagen den 10 juni 1988 kl 13.00
i hörsal E, H um anisthuset, U m eå u n iversitet
ABSTRACT
Applied methods for analyses of economic structure and change
Languuge: English and Swedish, 276 pages
by Christer Anderstig, Department of Economics,
University of Umeft, Sweden
The thesis comprises five papers and an introductory overview o f applied
models and methods. The papers concern interdependences and interrela
tions in models applied to empirical analyses o f various problems
related to production, consumption, location and trade. Among different
definitions of 'structural analysis' one refers to the study of the
properties o f economic models on the assumption of invariant structural
relations, this definition is close to what is aimed at in lire present case.
Although the subjects cover widely differing aspects of the economic system,
applied models and methods, i.e. entropy maximizing (information minimizing)
models and random utility maximizing models, are in many cases closely
connected.
Tlic first paper reports on a regional input-ouput study applied to
Norrbotten, Sweden. The paper is mainly concentrated on developing and
estimating an econometric model, describing the structural interdependences
in the Norrbotten economy. The chapter is composed of three parts. The first
part concerns the theoretical basis of the model, the main fields of
application and principal problems in connection with the estimation. The core
of the estimated model is defined by the intersectoral dependences in the
Norrbotten economy. This model can be viewed as a part of a more general
model of the regional economy, and such a general model is briefly outlined.
The second part reports on the collection and arranging of data, and the
methods used for the estimation of the model. In the third part the results
are presented. A special interest concerns the effects of production changes
in the basic industries in the county, as to the expected impact on different
industries and occupational groups.
The second paper concerns some aspects of the problem of predicting trade flows
in the forest sector. The model, based on information theory, is predicting
current trade flows by adjusting the historical, a priori, trade flows to
satisfy current export and import totals.
In the third paper an entropy model is employed to decompose the interregional
and intraregional employment change in Sweden and Stockholm, during the period
1960 - 1980, into effects attributed to regions (zones), industries, occupations
and interaction effects.
The fourth paper presents an empirical analysis o f housing choice, based on
individual data of households in Stockholm. The consumer choice is regarded as
a complex choice from a finite set of discrete alternatives and a probabilistic
choice mode! (multinomial logit) is employed, where secondary dwelling is
included in the housing choice decision.
In the final paper spectral analysis is used for identifying the significant
components of cycle behaviour in time series of Swedish exports o f forest
products over a twenty year time period.
Keywords:
Economic structure
Input-output models
Information theory
Multinomial logit
Housing choice
Spectral analysis
Urban development
Distribution and author's address
CFKUM, U niversity of Um eâ, S-901 87 Um eâ
ISSN Ü282-Ü277 1 SUN 91-7174-366-9
P la ce of publication: U m eâ
Year o f publication: 1988
Applied methods for analyses of economic structure and change
Language: English and Swedish, 276 pages
hy Christer Anderstig, Department of Economics,
University of Umeâ, Sweden
The thesis comprises five papers and an introductory overview of applied
models and methods. The papers concern interdependences and interrela
tions in models applied to empirical analyses of various problems
related to production, consumption, location and trade. Among different
definitions o f ’structural analysis’ one refers to the study of the
properties of economic models on the assumption of invariant structural
relations, this definition is close to what is aimed at in the present case.
Although the subjects cover widely differing aspects of the economic system,
applied models and methods, i.e. entropy maximizing (information minimizing)
models and random utility maximizing models, are in many cases closely
connected.
rITie first paper reports on a regional input-ouput study applied to
Norrbotten, Sweden. The paper is mainly concentrated on developing and
estimating an econometric model, describing the structural interdependences
in the Norrbotten economy. The chapter is composed of three parts. The first
part concerns the theoretical basis of the model, the main fields of
application and principal problems in connection with the estimation. The core
of the estimated model is defined by the intersectoral dependences in the
Norrbotten economy. This model can be viewed as a part of a more general
model of the regional economy, and such a general model is briefly outlined.
The second part reports on the collection and arranging of data, and the
methods used for the estimation of the model. In the third part the results
are presented. A special interest concerns the effects of production changes
in the basic industries in the county, as to the expected impact on different
industries and occupational groups.
The second paper concerns some aspects of the problem of predicting trade flows
in the forest sector. The model, based on information theory, is predicting
current trade flows by adjusting the historical, a priori, trade flows to
satisfy current export and import totals.
In the third paper an entropy model is employed to decompose the interregional
and intraregional employment change in Sweden and Stockholm, during the period
1960 - 1980, into effects attributed to regions (zones), industries, occupations
and interaction effects.
The fourth paper presents an empirical analysis of housing choice, based on
individual data of households in Stockholm. The consumer choice is regarded as
a complex choice from a finite set of discrete alternatives and a probabilistic
choice model (multinomial logit) is employed, where secondary dwelling is
included in the housing choice decision.
In the final paper spectral analysis is used for identifying the significant
components of cycle behaviour in time series of Swedish exports of forest
products over a twenty year time period.
Keywords:
Economic structure
Input-output models
Information theory
Multinomial logit
Housing choice
Spectral analysis
Urban development
Preface
This thesis contains papers written during the past ten years, in connection with manifold
research projects relating to regional development, the forest sector, the building sector, urban
development and the housing market. The early papers were written during years on the staff on
the Department of Economics at University of Umeå, while two papers of more recent date have
been produced at the Regional Planning Office in Stockholm.
Diregarding the general view where everything depends on everything, it may seem an awkward
task to find the link between research efforts in these disparate fields. Yet there are at least two
kind of links that I would like to point at. First, the financial support given by the Swedish Council
of Building Research to next to all research projects. Second, the personal link, involving several
people.
My thesis adviser, Âke E Andersson, has convinced me that the disparate papers have to do
with structural analysis (albeit of a less modern kind) and has during past years offered support
and encouragement to complete the work, even if the structure of papers has changed. Börje
Johansson, who has acted as leader for some projects, has likewise been supporting and
encouraging, not least by the regular question: Have you finished yet? Björn Hårsman, co
author of chapter four, and Lennart Fridén, both at the Regional Planning Office, have gratefully
been understanding to my situation in the last months.
I have benefitted greatly from Lars Lundberg, co-author of chapter two, as to his excellent
guidance into applied economics.
A great many people at the Department of Economics in Umeå and at the Regional Planning
Office have made contributions in many respects, not least typing the various manuscripts. I
want to thank you all!
1. APPLIED METHODS FOR ANALYSES OF ECONOMIC
STRUCTURE AND CHANGE - AN OVERVIEW
2. ECONOMY AND EMPLOYMENT IN NORRBOTTEN -
A REGIONAL INPUT-OUTPUT STUDY (*)
3. ACTUAL AND PREDICTED TRADE FLOWS OF
FOREST PRODUCTS
4. ON OCCUPATION STRUCTURE AND LOCATION PATTERN
IN THE STOCKHOLM REGION
5. RESIDENTIAL LOCATION, TENURE AND SECONDARY
DWELLING - A MODEL OF HOUSING CHOICE APPLIED
TOSTOCKHOLM
6. SPECTRAL ANALYSIS APPLIED TO SWEDISH EXPORTS
OF FOREST PRODUCTS (*)
SUMMARY
APPLIED METHODS FOR ANALYSES OF ECONOMIC
STRUCTURE AND CHANGE - AN OVERVIEW
1. INTRODUCTION
2. AGGREGATIVE VERSUS DISAGGREGATIVE ANALYSIS
3. INFORMATION MINIMIZATION AND RANDOM
UTILITY MAXIMIZATION
4. ANALYZING THE STRUCTURE OF REGIONAL PRODUCTION
1. I N T R O D U C T I O N In this th es i s f i v e p a p e r s a r e c o l l e c t e d , i n c l u d i n g as m a n y s u bj ects: 11) A r e g i o n a l i n p u t - o u t p u t study, (II) A m o d e l f o r p r o j e c t i o n of i n t e r n a t i o n a l t ra d e f l o w s of f o r e s t p r o d u c t s , (III) M o d e l s r e f e r i n g to Inter- a n d l n t r a r e g i o n a l l o c a t i o n a l a n a l y s i s , (IV) A n a n a l y s i s of h o u s i n g c h o i c e a n d (V) A n a p p l i c a t i o n of s p e c t r a l a n a l y s i s to e x p o r t s e ri es of f or e s t prod uc t s. Si n c e the p a p e r s r e p r e s e n t w i d e l y d i f f e r i n g a s p e c t s of the e c o n o m i c
s ys tem, an o p e n i n g q u e s t i o n c o n c e r n s the a i m a n d p r i n c i p l e of the
c o l l e c t i o n . As a p r e l i m i n a r y a n d g e n e r a l a n s w e r it c o u l d be sai d that
all p a p e r s ar e f o c u s e d on e m p i r i c a l a n a l y s e s of e c o n o m i c s t r u c t u r e s ,
a n d that the m e t h o d s e m p l o y e d a r e c l o s e l y related.
As to the d e f i n i t i o n a n d use of the a m b i g u o u s c o n c e p t 'structure'
a r e m a r k b y M a c h l u p (1963) c o u l d b e q u o t e d : "In g e n e r a l , the ter m
Is m o r e o f t e n u s e d as a n u n n e c e s s a r y Ja r go n a n d as a p l a i n w e a s e l w o r d
than it Is u s e d as a t e c h n i c a l t e r m w i t h c l e a r l y d e f i n e d m e a ni n g. T h i s
s h o u l d be r e a s o n e n o u g h for a v o i d i n g it." Now, M a c h l u p ' s d i s c o u r a g i n g
a t t i t u d e r e fe r s to c o n t e x t s w h e r e structure' is u s e d fo r a p o l o g e t i c
alms, w h i l e in the p r e s e n t c as e a t e c h n i c a l t e r m is a i m e d at.
But e v e n w i t h r e s p e c t to ' s t ru c tu ra l a n alysis' t h e re a r e s e v e r a l
d e f i n i t i o n s , a n d let us b r i e f l y t o u c h on the d i s t i n c t i o n s b e t w e e n
th re e m e a n i n g s of this con c ep t. Fi r s t , w i t h i n m o d e r n m a t h e m a t i c s the
a n a i y s i s of s t r u c t u r a l s t a b i l i t y has d u r i n g the last d e c a d e s b e c o m e a
c l e a r L y d e f i n e d sub j ec t, b a s e d on b i f u r c a t i o n a n d c a t a s t r o p h e th eory,
g e n e r a l l y c o n c e r n i n g the s t r u c t u r a l s t a b i l i t y of d y n a m i c mod el s.
In this f i e i d one ca n f i n d s e v e r a l w o r k s r e f e r i n g to e c o n o m i c
2
T h e w o r k by P u u ia of r e l a t e d i nt er e st , as it c o n c e r n s the s p a t i a l s t a b i l i t y of t r a n s p o r t a t i o n a n d l o c a t i o n s t r u c t u r e s , a n d s p a t i a l s t a b i l i t y h a s p a r a l l e l s w i t h t e m p o r a l d y n a m i c s t a b i l i t y , (see P u u (1979, 1988) , B e c k m a n n a n d P u u (1985), P u u a n d W e i d l i c h (1986)). T h e s e c o n d m e a n i n g is re la t e d , viz. the a n a l y s i s of ' s t r u ct u ra l v a r i a b i l i t y ' w i t h i n e c o n o m e t r i c s . W h e r e a s t i m e - v a r y i n g p a r a m e t e r m o d e l s h a v e b e e n l o n g c o n s i d e r e d , the e c o n o m e t r i c a n a l y s i s of s p a t i a l l y s t r u c t u r a l l y v a r y i n g e c o n o m i c s y s t e m s h a s just r e c e n t l y b e e n a d d r e s s e d , see e.g. W e s t l u n d (1985). C o n t r a r y to this, the t h i r d m e a n i n g of ' s t r u c t u r a l a n al y s i s ' re f e r sto the s t u d y of the p r o p e r t i e s of e c o n o m i c m o d e l s o n the a s s u m p t i o n
of I n v a r i a n t s t r u c t u r a l r el a ti o n s . T h i s d e f i n i t i o n a p p l i e s to m u c h
of the w o r k in the t r a d i t i o n of i n p u t - o u p u t a n a l y s i s , a n d c o m e s v e r y
c l o s e to w h a t is a i m e d at in the p r e s e n t case. T o a v o i d c o n f u s i o n of
ideas, the t it l e thus r e f e r s to a n a l y s e s of e c o n o m i c s tr u ct u r e ,
i n s t e a d of s t r u c t u r a l an a l y s i s .
In the p r e s e n t c a s e the g e n e r a l a p p r o a c h a p p l i e d c o u l d be i l l u s t r a
ted b y a s t a t e m e n t by B r o d y (1970, p. 18): "By a s s u m i n g a p p r o x i m a t e
m e a s u r a b i l i t y w e d o n o t a s s u m e t hat i n p ut c o e f f i c i e n t s a r e stable.
By a s s u m i n g the e x i s t e n c e a n d m e a s u r a b i l i t y of the s p e e d of a car
w e d o not d e n y a c c e l e r a t i o n . W e a r e c o n c e r n e d o n l y in the i n t e r d e p e n d e n c e a n d r e g u l a r i t i e s a m o n g the c o e f f i c i e n t s t h e m s e l v e s , e m e r g i n g in t he c o n t e x t of a g i v e n m o m e n t . " Th u s , a c c e p t i n g this f i x e d pr o p o r t i o n s ' a p p r o a c h , the p r e s e n t a n a l y ses of e c o n o m i c s t r u c t u r e s a r e c o n c e r n i n g I n t e r d e p e n d e n c i e s a n d i n t e r r e l a t i o n s in s p e c i f i c m o d e l s , a p p l i e d to e m p i r i c a l a n a l y s e s of v a r i o u s p r o b l e m s r e l a t e d to p r o d u c t i o n , c o n s u m p t i o n , l o c a t i o n a n d trade.
2
.
A G G R E G A T I V E V E R S U S D I S A G G R E G A T IV E A N A L Y S I ST h e m o d e l s d i s c u s s e d a r e a ll r e f e r i n g to the m e s o or m i c r o le ve l
of the e c o n o m y a n d all m o d e l s a r e m o r e or less d i s a g g r e g a t e d . T h e
e m p h a s i s put on d i s a g g r e g a t i o n is p a r t l y a c o n s e q u e n c e of the a u t h o r ' s i n t e r e s t in a n d p r e d i s p o s i t i o n to this k i n d of a p p l i e d e c o n o m i c s , i r r e s p e c t i v e of the p r e s e n t p o s i t i o n as r e s e a r c h w o r k e r at a r e g i o n a l p l a n n i n g office. Bu t w h a t is m o r e i n t e r e s t i n g than h a v i n g t h e se s u b j e c t i v e r e a s o n s is to c o n s i d e r the a g g r e g a t i o n p r o b l e m In r e l a t i o n to e c o n o m i c s as a b e h a v i o u r a l scienc e . F r i e d r i c h v o n H a y e k h as put the a g g r e g a t i o n p r o b l e m v e r y c o n c i s e l y : "In fact, n e i t h e r a g g r e g a t e s no r a v e r a g e s d o a c t u p o n o n e a n o t h e r ” . O t h e r s h a v e g i v e n the p r o b l e m a m o r e s y s t e m a t i c t r e a t m e n t , e.g.
1
)
T h e i l (1954) a n d G r e e n (1964).C o n s i d e r i n g the i n f l u e n c e tha t p h y s i c s has h a d o n e c o n o m i c s ,
a c o m p a r i s o n of th e r e s p e c t i v e a g g r e g a t i o n p r o b l e m tu rn s out
I n t e r es t in g . A s r e m a r k e d b y L a n c a s t e r (1966a, p. 2 0 1 ) , " . . . the l evel
of d i r e c t a w a r e n e s s in e c o n o m i c s is at the i n d i v i d u a l (micro-) level,
w h i l e the a g g r e g a t e s ( m a c r o - v a r i a b l e s ) a re a b s t r a c t i o n s . T h e r e v e r s e is t y p i c a l l y t rue of p hy s i c s , w h e r e , fo r e x a m p l e , the p r e s s u r e of a gas ( a g g r e g a t e b e h a v i o r of m o l e c u l e s ) is o b s e r v a b l e a b o u t as d i r e c t l y as a n y p h y s i c a l p h e n o m e n o n , w h i l e the b e h a v i o r of a s i n g l e m o l e c u l e In that a g g r e g a t e is o b s e r v a b l e o n l y in an i n d i r e c t f a s h i o n . ” As far as a p p l i e d e c o n o m i c s is c o n c e r n e d the c o n c l u s i o n is o b v i o u s - in g e n e r a l the m o d e l s m u s t be c o n f i n e d to m a c r o - v a r i a b l e s , b a s e d on m o r e or less a g g r e g a t e d m i c r o - v a r i a b l e s . 1) See a l s o A l l e n (1956).
4
N ow, in this m a t t e r th e r e is a m o n g e c o n o m i s t s a n u s u a l a r g u m e n t of g r e a t c o m f o r t , a m o n g o t h e r s put f o r w a r d b y S a m u e l s o n (1947, p. 144); " Th er e is n o t h i n g i n t r i n s i c a l l y r e p r e h e n s i b l e in w o r k i n g w i t h .. a g g r e g a t e c on ce p t s . On the c o n t r a r y , a b s t r a c t i o n f r o m c o m p l e x i t y is a n e c e s s a r y t h o u g h t p r o c e s s . . . But it is i m p o r t a n t to r e a l i z e the l i m i t a t i o n s of t he s e a g g r e g a t e s a n d to a n a l y z e the n a t u r e of th ei r c o n s t r u c t i o n . "W h i l e the f i r s t p ar t of the a r g u m e n t r e p r e s e n t s the e s t a b l i s h e d
o p i n i o n , the c o n c l u s i o n is less r e c o g n i z e d . T h e a g g r e g a t i o n
p r o b l e m h a s m o r e o f t e n b e e n o v e r l o o k e d th an l o o k e d over, and, as
L e i j o n h u f v u d (1968, p. Ill) puts it, "the a g g r e g a t e s u s e d t en d to
b e c o m e p r o f e s s i o n a l c o n v e n t i o n s w h i c h a r e s e l d o m e x a m i ne d" .
As n o t e d b y A l l e n (1956), the s e r i o u s d i s c u s s i o n a b o u t the a g g r e g a t i o n
p r o b l e m w a s s t a r t e d w i t h a s e r i e s of a r t i c l e s b y K l e i n a n d o t h e r s in
1946. In r e t r o s p e c t , the d i s c u s s i o n at tha t tim e ca n be s e e n as a
p r e l i m i n a r y to the c o m i n g m a c r o - e c o n o m i c m o d e l - b u i l d i n g t r a di ti o n.
It is i n t e r e s t i n g to not e , t hat w h i l e the d i s c u s s i o n of a g g r e g a t i o n
p r o b l e m s a n d s p e c i f i c a t i o n e r r o r s a r o s e f r o m the a d v a n c e of m a c r o - e c o n o m i c m o d e l - b u i l d i n g , this t r a d i t i o n p r o v i d e d , a c c o r d i n g to G r i l i c h e s (1974), a n ' e r r o r s - c a n c e l - o u t - i n - a g g r e g a t e s ' j u s t i f i c a t i o n for no t d e a l i n g w i t h e r r o r s in v a r i a b l e s . T h i s p o i n t s to the g e n e r a l p r o b le m, d i s c u s s e d in e.g. A l o n s o (1968), of a c o n f l i c t b e t w e e n s p e c i f i c a t i o n e r r o r s a n d m e a s u r e m e n t e r r o r s , the f o r m e r d e c r e a s i n g a n d the l a t t e r i n c r e a s i n g w i t h d i s a g g r e g a t i o n a n d m o d e l co m p l e x i t y . F u r t h e r , as e x e m p l i f i e d in G r u n f e l d a n d G r i l i c h e s (1960), in c as e
the b e h a v i o u r is i n f l u e n c e d b y v a r i a b l e s at the a g g r e g a t e level,
1
)the m a c r o - r e l a t i o n m a y p e r f o r m e v e n b e t t e r t h a n the m i c r o - r e l a t i o n .
T h e c o n c l u s i o n is no t v e r y s e n s a t i o n a l : E a c h a g g r e g a t i o n p r o b l e m
m u s t b e s o l v e d in its o w n w ay, a n d as to the p r e s e n t study, a
s t a t e m e n t b y J o h a n s e n (1964, p.l) m a y g i v e the g u i d i n g p r i n c i p l e :
" Indeed, X d o not b e l i e v e that in g e n e r a l the a p p l i c a t i o n of the
a n a l y s i s in t e rm s of less a g g r e g a t e d c o n c e p t s is s u p er io r . T h e d e g r e e of a g g r e g a t i o n to a p p l y a n d the c o n c e p t s to u s e d e p e n d o n the p r o b l e m s w h i c h on e w a n t s to e x a m i n e , a n d t h e r e is c e r t a i n l y a n e e d for b o t h a g g r e g a t i v e a n d d i s a g g r e g a t i v e a n a l y s e s . " N e x t f o l l o w s a n a c c o u n t of h o w this g e n e r a l 'principle' h a s b e e n i m p l e m e n t e d . Fi rs t , the r e f e r e n c e m a d e to m o d e l s o n the m i c r o le v el a c t u a l l y r ef e rs
to the p a p e r on h o u s i n g c h o i c e (IV). A n d e v e n in th i s c a s e the micro'
da ta , that is the f a m i l y e x p e n d i t u r e a n d i n c om e da ta , h a v e b e e n
a g g r e g a t e d o v er i n d i v i d u a l f a m i l y m e m b e rs . T h e o t h e r f o u r p a p e r s a r e
r e f e r i n g to w h a t is l a b e l e d the m e s o level, b e t w e e n m i c r o a n d macro.
In the f irst p ap e r (I) a r e g i o n a l i n p u t - o u t p u t s t u d y is p r e s e n t e d .
At the time the s t u d y w a s p e r f o r m e d , it wa s p r i m a r i l y a i m i n g at
a n a n a l y s i s of the im p a c t on the r e g i o n a l e c o n o m y of e s t a b l i s h i n g
a n e w s t eel mill. A n i n p u t - o u t p u t m o d e l w a s c h o s e n s i n c e this m o d e l
Is b a s e d o n w h a t is c r u c i a l in the im p a c t a n a l y s i s , viz. the i n t e r
d e p e n d e n c e b e t w e e n i n d u s t r i e s in the r e g i o n a l eco no m y.
Now, in c o m p a r i s o n to a n a l t e r n a t i v e r e p r e s e n t a t i o n of the e c o n o m y ,
e.g. an e c o n o m i c b a s e mo d e l , the i n p u t - o u t p u t m o d e l is d i s a g g r e g a t i v e ,
by d e f i n i t i o n . But w h a t is true of i n p u t - o u t p u t t a b l e s in g e n e r a l ,
a n d the p r e s e n t on e in p a r t i c u l a r , is sti ll a c o n s i d e r a b l e d e g r e e
of a g g r e g a t i o n . In the p r e s e n t s i n g l e r e g i o n m od e l, the f l o w s are
c o m p l e t e l y a g g r e g a t e d o v e r g o o d s a n d s e r v i ce s , a n d a c t i v i t i e s a r e
6
T h u s , w h a t e.g. C h e n e r y a n d C l a r k (1965) p o i n t ou t a s the b a s i c d i f f e r e n c e b e t w e e n i n p u t - o u t p u t a n d m o r e a g g r e g a t i v e m o d e l s , "the e x p l i c i t r e c o g n i t i o n of s p e c i f i c c o m m o d i t i e s h a v i n g d i f f e r e n t p r o d u c t i o n r e q u i r e m e n t s a n d us e s " , m u s t b e s o m e w h a t q u a l i f i e d w h e n 1) it c o m e s to a p p l i e d i n p u t - o u t p u t mo d e l i n g . T h e s e c o n d p a p e r (II) c o n c e r n s s o m e a s p e c t s of the p r o b l e m of p r e d i c t i n g t r a d e f l o w s, the p r o b l e m b e i n g r a i s e d in a r e s e a r c h p r o j e c t r e l a t e d to the f o r e s t s ector. T h e m o d e l o u t l i n e is a p p l i e d to a n u m b e r of r e a s o n a b l y h o m o g e n e o u s f o r e s t p r o d u c t s w h i l e the g l o b a l t ra d e n e t w o r k c o n s i s t s of o n l y f o u r regio n s. In o n e f o r m a l r e s p e c t th i s m o d e l is d i s a g g r e g a t i v e , r e f e r i n g to t r a d e f l o w s of s p e c i f i c p r o d u c t s , w h e r e a s a g g r e g a t e d f l o w s h a v e b e e n t r e a t e d in t r a d i t i o n a l t r a d e f l o w s a n a l y s e s . In e s s e n c e , h o w e v e r , th is d i f f e r e n c e d o e s n o t r e f l e c t d i f f e r e n t a p p r o a c h e s b u t d i f f e r e n t alms. W h a t h e r e is r e f e r e d to as 't r a d i t i o n a l ' a n a l y s e s h a v e m a i n l y b e e n c o n c e r n i n g the l e ve l of b i l a t e r a l i n t e g r a t i o n et c. , w h i l e inthe p r e s e n t c a s e the b a s i s h a s b e e n the p r o b l e m of p r e d i c t i n g
s p e c i f i c t r a d e flows. T h e m od e l , b a s e d on i n f o r m a t i o n t h e o ry , is p r e d i c t i n g c u r r e n t t r a d e f l o w s s i m p l y b y a d j u s t i n g the h i s t o r i c a l , a p r i o r i , t r a d e f l o w s to s a t i s f y c u r r e n t e x p o r t a n d i m p o r t totals. T h e r e s u l t s s u g g e s t that a c o n s i d e r a b l e d e g r e e of i n e r t i a is c h a r a c t e r i s t i c of s ome of the h i s t o r i c a l t r a d e p a t t e r n s , e s p e c i a l l y w i t h r e s p e c t to S w e d i s h expor ts . T h e t r a d e n e t w o r k b e i n g h i g h l y a g g r e g a t e d m ea n s , h o w e v e r , t ha t the 1) F o r a t h e o r e t i c a l d i s c u s s i o n of a g g r e g a t i o n p r o b l e m s in input - o u t p u t a n a l y s i s , see Moriraoto (1970). H ö g l u n d (1966) p r e s e n t s a n e m p i r i c a l s t u d y of r e l a t e d inte re s t.
s i g n i f i c a n c e of this r e s u l t is u n c l e a r a n d that the m o d e l p r i m a r i l y s er v e s a n i l l u s t r a t i v e purpo s e. A l s o the t h i r d p a p e r (III), s t u d y i n g S w e d i s h e m p l o y m e n t c h a n g e s I960 - 1980 b y d e c o m p o s i t i o n a n a l y s i s , is d r a w i n g on i n f o r m a t i o n theory. A n e n t r o p y m o d e l is u s e d to d e c o m p o s e e m p l o y m e n t c h a n g e s i nto e f f e c t s of r e g io n, i n d u s tr y, o c c u p a t i o n a n d i n t e r a c t i o n eff ec ts . By a d d i n g a n o c c u p a t i o n e f f e c t to the t r a d i t i o n a l e f f e c t s of r e g i o n a n d i n du st r y, the d e c o m p o s i t i o n p r o v i d e s i m p o r t a n t i n f o r m a t i o n that o t h e r w i s e w o u l d not be a v a i l a b l e , e v e n at a v e r y d e t a i l e d d i s a g g r e g a t i o n of ind u st ri e s.
T h e r e is o n e issue that is of s p e c i f i c i n t e r e s t to p e r f o r m this
a n a l y s i s , viz. the s p a t i a l i m p l i c a t i o n s of the p r o d u c t c y c l e theory.
H e r e e m p l o y m e n t f i g u r e s a r e u s e d to d i f f e r e n t i a t e b e t w e e n v a r i o u s e c o n o m i c a c t i v i t i e s , i n c l u d i n g d i f f e r e n t p h a s e s in the p r o d u c t cycle. In this c o n t e x t d e f i n i n g a c t i v i t i e s b y i n d u s t r y is i n a d e q u a t e si n c e a n industry' is a n a g g r e g a t e o v e r al l k i n ds of e s t a b l i s h m e n t s a n d a c t i v i t i e s , w h e t h e r , e.g., m a n u f a c t u r i n g in b r a n c h p l a n t s or R & D in c o r p o r a t e h e a d q u a r t e r s . D e f i n i n g a c t i v i t i e s b y o c c u p a t i o n m a k e s it p o s s i b l e , h o w e v e r , to d i f f e r e n t i a t e b e t w e e n , e.g., k n o w l e d g e i n t e n s i v e a n d g o o d s h a n d l i n g o c c u p a t i o n s , c a t e g o r i e s that c a n b e c o n c e i v e d as c o u n t e r p a r t s to
p h a s e s in the p r o d u c t cycle. As f o r the s p a t i a l d i m e n s i o n , r e g i o n s
h av e b e e n c o n s t r u c t e d a c c o r d i n g to the level of i n t r a r e g i o n a l
a c c e s s i b i l i t y , a p r i n c i p l e d e r i v e d f r o m p r o d u c t c y c l e th e ory.
In g e n e r a l , region s , i n d u s t r i e s a n d o c c u p a t i o n s h a v e b e e n c o n s t r u c t e d
on the b a s i s of h o m o g e n e i t y p r i n c i p l e s , a c c o r d i n g to c h a r a c t e r i s t i c s
8
A s m e n t i o n e d a b o v e th e f o u r t h p a p e r (IV), p r e s e n t i n g a n a n a l y s i s of h o u s i n g c h o i c e , is a m i c r o - o r i e n t e d a p p r o a c h , b a s e d on d a t a for i n d i v i d u a l h o u s e h o l d s , a n d the a n a l y s i s is p e r f o r m e d b y e s t i m a t i n g a p r o b a b i l i s t i c c h o i c e model . A c c o r d i n g t o M c F a d d e n (1981), t h r e e m a j o r f a m i l i e s of c o n c r e t e f u n c t i o n a l f o r m s fo r p r o b a b i l i s t i c c h o i c e m o d e l s h a v e b e e n d e v e l o p e d : L o g i t m o d e l s b a s e d o n the w o r k of L u c e (1959), p r o b l t m o d e l s b a s e d on the w o r k of T h u r s t o n e (1927), a n d e l i m i n a t i o n m o d e l s b a s e d o n th e w o r k of T v e r s k y (1972). In the p r e s e n t c a s e a (nested) m u l t i n o m i a l lo g it m o d e l is a p p l i e d . T h i s m od e l , d e v e l o p e d b y M c F a d d e n (1973), is u s e d to e s t i m a t e the joint c h o i c e of l o c a t i o n , t e n u r e a n d s e c o n d a r y d w e l l i n g , w h e r e s e p a r a t e m o d e l s a r e e s t i m a t e d fo r th r e e h o u s e h o l d c a t e g o r i e s , d e f i n e d m a i n l y b y l i f e - c y c l e f a ctors. T h i s k i n d of m o d e l i n g is d i s a g g r e g a t i v e in s e v e r a l r e s pe c ts . F i r s t , the c o n s u m e r c h o i c e is r e g a r d e d as a c o m p l e x c h o i c e f r o m a f i n i t e set of d i s c r e t e a l t e r n a t i v e s . D e c i s i o n s o n h o u s e t y pe s a n d r e s i d e n t i a l l o c a t i o n a r e o b v i o u s e x a m p l e s of c h o i c e s a m o n g d i s c r e t e a l t e r n a t i v e s . T h e r e are, h o w e v e r , m a n y o t h e r i m p o r t a n t e c o n o m i c d e c i s i o n s th a t l i k e w i s e i n v o l v e d i s c r e t e a l t e r n a t i v e s , e.g. l a bo r f o r c e p a r t i c i p a t i o n , o c c u p a t i o n , e d u c a t i o n a l lev e l - s i t u a t i o n s w h e r e the I n d i v i s i b i l i t y p r o b l e m m a k e s th e u s e of c o n v e n t i o n a l m a r g i n a l i s t c o n s u m e r t h e o r y i n a de qu a te . S e c o n d , it is p o s t u l a t e d t hat u t i l i t y is d e r i v e d f r o m the b u n d l e of a t t r i b u t e s th at the a l t e r n a t i v e s p o s s e s s , f o l l o w i n g L a n c a s t e r (1966b). T h i r d , it is a s s u m e d t ha t a t t r i b u t e s a r e v a l u e d d i f f e r e n t l y b y d i f f e r e n t h o u s e h o l d c at e g o r i e s .i l l u s t r a t i o n , i m p l y a m o d e l of h o u s i n g d e m a n d w h e r e a ll h o u s i n g a t t r i b u t e s a r e l u m p e d t o g e t h e r i nt o o n e s i n g l e - v a l u e d c o m m o d i t y , h o u s i n g s e r v i c e s ' , a n d w h e r e h o u s e h o l d s a r e n o t g r o u p e d at all. G i v e n th e s e a l t e r n a t i v e s , w e m a y w i t h o u t f u r t h e r e l a b o r a t i o n c o n c l u d e t ha t the d i s a g g r e g a t e d a p p r o a c h g i v e s a b e t t e r u n d e r s t a n d i n g of the d e m a n d f or h o u s i n g a n d the b e h a v i o u r of a h o u s i n g m a rk e t. Now, it s h o u l d b e a d m i t t e d t ha t th is e x t r e m e l y a g g r e g a t i v e a p p r o a c h in f act h a s no r e l a t i o n w i t h m o d e r n re s e a r c h , n o r w i t h m o d e r n m a c r o m o d e l i n g in c o n n e c t i o n w i t h r e g i o n a l a n d lo cal p l a nn in g . S i n c e the s e v e n t i e s a c o n s i d e r a b l e p ar t of the r e s e a r c h in h o u s i n g e c o n o m i c s h a s b e e n f o c u s e d o n d i s a g g r e g a t e d i s c r e t e c h o i c e m o d e l s , the r e s e a r c h s t r e a m to w h i c h the p r e s e n t p a p e r b e l o n g s . E v e n m a c r o level a p p r o a c h e s , in r e s e a r c h as w e l l as in p l a n n i n g a n d p o l i c y c o n t e x t s , a r e c o u c h e d in t e r m s p a r t l y r e f l e c t i n g th e h e t e r o g e n e i t y 1) of h o u s i n g a n d the i n f l u e n c e of li fe c y c l e f a ct or s . B e i n g a p o l i c y f i e l d of g r e a t i m p o r t a n c e , a n d g i v e n the i n c r e a s i n g l y
s o p h i s t i c a t e d r e s e a r c h a t the m i c r o level, the m o s t r e c e n t h o u s i n g
r e s e a r c h is c o n c e r n i n g the li nk b e t w e e n m i c r o a n d m a c r o p e r s p e c t i v e s F or e x a m p l e , A n a s et al. (1987) h a v e d e v e l o p e d a p r o t o t y p e m o d e l of the S w e d i s h h o u s i n g m a r k e t , d r a w i n g o n a s i m i l a r m o d e l in US, A n a s (1982), w h e r e the li nk b e t w e e n m i c r o a n d m a c r o b e h a v i o u r s is d i s c u s s e d . In t h e s e s t u d i e s it is a r g u e d that lo gi t m o d e l s , b a s e d on I n d i v i d u a l c h o i c e th eory, ca n b e m e a n i n g f u l l y a n d a c c u r a t e l y e s t i m a t e d u s i n g sma ll a g g r e g a t i o n u n i t s a n d r e l a t i v e f r e q u e n c y d a t a of ch oices. 1) Cf. H å r s m a n (1981) 2) A r e v i e w is f o u n d in C l a r k a n d V a n L i e r o p (1986)
10
T h e f i f t h a n d la s t p a p e r (V), p r e s e n t i n g a s p e c t r a l a n a l y s i s of S w e d i s h e x p o r t s of f o r e s t p r o d u c t s , w a s w r i t t e n in c o n n e c t i o n w i t h the s am e r e s e a r c h p r o j e c t a s p a p e r II. T h i s p a p e r m a y e v e n f r o m a m e t h o d o l o g i c a l p o i n t of v i e w s e e m to b e of a d i f f e r e n t k i n d t h a n o t h e r pa p er s. Yet th er e a r e c o n n e c t i o n s , m o s t e a s i l y s e e n w i t h r e s p e c t to the m e t h o d u s e d in the d e c o m p o s i t i o n a n a l y s i s in p a p e r III. T h e r e a n e n t r o p y m o d e l is u s e d to e s t i m a t e e m p l o y m e n t c h a n g e s , d e c o m p o s e d i nt o a n a t i o n a l e f f e c t , e f f e c t s of r e g i o n , i n d u s t r y , o c c u p a t i o n a n d i n t e r a c t i o n e ff e ct s . T h e s e e f f e c t s a r e q u i t e a n a l o g o u s to the o v e r a l l m e a n term, the m a i n a n d i n t e r a c t i o n e f f e c t s in a n a n a l y s i s 1) of v a r i a n c e m od e l. An d , as e x p l a i n e d b y T u k e y (1961), t u r n i n g f r o m i n d i v i d u a l e f f e c t s to v a r i a n c e c o m p o n e n t s , t h e r e is a cl e a r a n a l o g u e b e t w e e n a n a l y s i s of v a r i a n c e a n d s p e c t r a l a n a l y s i s . J u s t as a n a l y s i s of v a r i a n c e c a n b e r e g a r d e d as a d e c o m p o s i t i o n in to v a r i a n c e c o m p o n e n t s , the s p e c t r u m of a t i m e s e r i e s is a d e c o m p o s i t i o n of the o v e r - a l l v a r i a n c e i n t o c y c l e c o m p o n e n t s of v a r i o u s f r e q u e n c i e s . T h e s p e c t r u m thus p r o v i d e s i n f o r m a t i o n of the r e l a t i v e s t r e n g t h of c y c l e s w i t h v a r i o u s f r e q u e n c i e s . S p e c t r a l a n a l y s i s is t h e r e f o r e a u s e f u l m e t h o d fo r i d e n t i f y i n g the s i g n i f i c a n t c o m p o n e n t s of c y c l eb e h a v i o u r in ti m e series. In the p r e s e n t e x p l o r a t i v e pap e r, the
e s t i m a t e d s p e c t r a a r e b a s e d o n q u a r t e r l y d a ta , 1961 - 1979, for
S w e d i s h e x p o r t s of 158 f o r e s t p r od u c t s . T h i s m e a n s t h a t m o s t
p r o d u c t s a r e r e a s o n a b l y h o m o g e n e o u s w i t h r e s p e c t to p r o d u c t i o n ,
u s e s a n d t r a n s p o r t a t i o n c h a r a c t e r i s t i c s . A n d a f i n e c l a s s i f i c a t i o n
of p r o d u c t s m a y b e ju s ti fi e d, as d i f f e r e n t q u a l i t i e s w i t h i n a g g r e
g a t e s as 's a wnwood', 'pulp' etc. e x h i b i t m a r k e d l y d i f f e r e n t sp ectra.
1) O v e r v i e w s of r e l a t e d s t a t i s t i c a l m o d e l s in thi s f i e l d a r e f o u n d in e.g. W r i g l e y a n d B r o u w e r (1986) a n d W r i g l e y (1985).
3. I N F O R M A T I O N M I N I M I Z A T I O N A N D R A N D O M U T I L I T Y M A X I M I Z A T I O N
T h e d i s c u s s i o n a b o v e w a s c l o s e d b y p o i n t i n g at the the analogue,, in
a s t a t i s t i c a l d e c o m p o s i t i o n c o n t e x t , b e t w e e n s p e c t r a l a n a l y s i s a n d e n t r o p y m o d e l i n g . A m o r e i n t e r e s t i n g q u e s t i o n c o n c e r n s the c o n n e c ti on b e t w e e n m o d e l s u s e d in p a p e r s I - IV. A c t u a l l y , w h e n p r o j e c t i n g t r a de f l o w s (II), d e c o m p o s i n g e m p l o y m e n t (III) a n d a n a l y z i n g h o u s i n g c h o i c e (IV), the t h e o r e t i c a l p e r s p e c t i v e s d i f f e r b u t th e m o d e l f o r m s ar e q u i t e or a l m o s t i d e n ti c al . F u r t h e r m o r e , s o m e m o d e l s a r e of g e n e r a l i n t e r e s t in e s t i m a t i n g a n d p r o j e c t i n g i n p u t - o u t p u t c o e f f i
cient s , a l t h o u g h n o t u s e d in this case.
First, the i n f o r m a t i o n t heory, or e n t r o p y m o d e l a p p r o a c h e s u s e d in
p a p e r s II a n d III a r e q u i t e i de nt i c a l . In a n o v e r v i e w b y B a t t e n a n d
B o y c e (1986) this a p p r o a c h is r e l a t e d to a l a r g e r f a m i l y of s p a t i a l
i n t e r a c t i o n models. E v e n if t h is c o n n e c t i o n d o e s not i m p l y that
e n t r o p y m o d e l s a r e i n a p p l i c a b l e in o t h e r f i e l d s of e c o n o m i c s , the
mo st f r e q u e n t a p p l i c a t i o n s d o r e l a t e to r e g i o n a l s c i e nc e , e.g. in
sp a t i a l f o re c a s t i n g .
In this c o n t e x t R o y (1987) p o i n t s out that tw o a l t e r n a t i v e a p p r o a c h e s
ar e a v a i l a b l e , k n o w n as the S h a n n o n a n d the K u l l b a c k a p p r o a c h e s . It is 1)
the latter, a l s o k n o w n as the m i n i m u m i n f o r m a t i o n p r i n c i p l e , or e n t r o p y
m a x i m i z a t i o n w i t h n o n - u n i f o r m p r i o r p r o b a b i l i t i e s , th at is u s e d in p a p e r s II a n d III. T h us , in p r o j e c t i n g tr a d e f l o w s (II) a n d e s t i m a t i n g e m p l o y m e n t c h a n g e s (III), a r e v i s e d d i s t r i b u t i o n (of i n t e r r e g i o n a l t r a d e f l o w s a n d e m p l o y m e n t b y regi on , i n d u s t r y a n d o c c u p a t i o n , r e s p e c t i v e l y ) is i n f e r r e d f r o m a p r i o r d i s t r i b u t i o n u p o n the i n t r o d u c t i o n of n e w e x o g e n e o u s d a t a (t otal r e g i o n a l e x p o r t s a n d im p o r t s a n d t o t a l n u m b e r of e m p l o y e d in r eg i on s, i n d u s t r i e s , o c c u p a t i o n s etc ., r e s p e c t i v e l y ) . I) See S n i c k a r s a n d W e i b u l l (1977), W e b b e r (1979)
12
T h e e s t i m a t e s of a n y e n t r o p y m o d e l m a y he c h a r a c t e r i z e d as a t ype of
s t a t i s t i c a l i n f e r e n c e , see e.g. B a t t e n a n d B o y c e (1986). O n e may, h o w
e ver, m a k e a f u r t h e r d i s t i n c t i o n b e t w e e n the t w o a p p r o a c h e s in this
respect. T h e S h a n n o n a p p r o a c h d i f f e r s f r o m the K u l l b a c k p r o c e d u r e b y a s s u m i n g u n i f o r m p r i o r p r o b a b i l i t i e s , e . g., a s s u m i n g tha t i n t e r r e g i o n a l t r a d e f l o w s a r e e q u a l l y p r o b a b l e . Now , t h e r e is e m p i r i c a l e v i d e n c e t h a t the K u l l b a c k p r o c e d u r e h a s s u p e r i o r p r e d i c t i v e c a p a b i l i t y , a t l e ast w i t h r e s p e c t to h i s t o r i c a l data. A c c o r d i n g to R o y (1987), thi s a p p r o a c h m a y (thus) b e c l a s s i f i e d a (the) s t a t i s t i c a l I n f e r e n c e ap p r o a c h .
On the o t h e r han d , the S h a n n o n a p p r o a c h is a l l e g e d to h a v e a l a r ge r
e x p l a n a t o r y powe r , b y the f o l l o w i n g reason. U s i n g the S h a n n o n a p p r o a c h ,
the e s t i m a t e d m o d e l is b a s e d on a set of e x p l a n a t o r y c h a r a c t e r i s t i c s
and, h e n c e , the p a r a m e t e r s c a n b e u s e d at the f o r e c a s t i n g stage,
a c c o u n t i n g fo r the e f f e c t s of c h a n g e d c h a r a c t e r i s t i c s . A p p l i e d to,
e .g ., i n t e r r e g i o n a l t r a d e fl o ws , the e s t i m a t e d f l o w p a t t e r n c o u l d be
b a s e d on i n f o r m a t i o n s u c h as t r a n s p o r t a t i o n co s t s a n d o t h e r t r a d e
i m p e d i m e n t s / a f f i n i t i e s , as in the c l a s s i c a l g r a v i t y m odel. A f l o w
p a t t e r n f o r e c a s t c o u l d thus r e f l e c t the e f f e c t s of a l t e r e d t r a n s p o r
t a t i o n c osts, ta ri f f b a r r i e r s et c., p r o v i d e d t hat t his i n f o r m a t i o n
is a v a i l a b l e . A s to the e x p l a n a t o r y p o w e r of the K u l l b a c k p r o c e d u r e , R o y a r g u e s t ha t it “s u b s t i t u t e s d i r e c t p r o j e c t i o n f r o m the p r i o r d i s t r i b u t i o n f o r the e s t i m a t i o n p h a s e of the S h a n n o n m o d e l . . ( a n d is t h e r e f o r e ) ..i n c a p a b l e of c o n s i d e r i n g a n y c h a n g e s in the c o n f i g u r a t i o n of c h a r a c t e r i s t i c s i n f o r m a t i o n b e t w e e n the e s t i m a t i o n (prior) ti m e p e r i o d a n d the f o r e c a s t i n g p e ri o d " . T h u s , s t a r t i n g f r o m the c o n c e p t i o n of the K u l l b a c k a n d S h a n n o n a p p r o a c h es h a v i n g c o m p l e m e n t a r y m e r i t s , R o y p r e s e n t s a n e w f o r e c a s t i n g a p p r o a c h , a t t e m p t i n g to c o m b i n e t h e s e m e ri t s. A s r e g a r d s o ur d i s c u s s i o n ,
R o y
' 3paper la of interest primarily by the discussion of the
advan-1)
tages and disadvantages associated with respective approach.
The Kullback procedure discussed so far may in fact be seen as a
special case of the minimum information principle, as presented in
Snickars and Weibull (1977). There, e.g., the 'new gravity model'
makes use of explanatory characteristics (travel time) information
as well, in addition to the information of a prior probability
distribution and the probability sum information. Thus it seems as
If the difference between a Shannon approach (the classical gravity
model) and a Kullback approach (the new gravity model) is not a
matter of explanatory power, as the same characteristics are used
In both approaches, but a matter of the amount of information used,
being less in the Shannon approach.
Now, turning to the connection between information theory approaches
and the multinomial logit model (MNL) approach used in paper IV, Anas
(1983) gives one proof that the Shannon approach and the (simple) MNL
may yield identical estimates. It may therefore be instructive to
draw on parts of Anas' paper. Assume the problem of deriving the
h
choice probabilities P
, where h =l—
H denotes choosers and j=l...J
J
denotes the discrete alternatives forming the choice set (as in, e.g.,
a housing choice problem). The information available makes it possible
to formulate the following information minimizing problem, using the
Shannon approach:
h
h
Min 1 1 P In P
(1)
h 1
J
j
I ;
The problem resembles the traditional forecasting problem, as
discussed, from a users perspective, by e.g. Chambers et al. (1971);
'The superior short term accuracy of techniques based on stochastic
models of time series, while causal ('explanatory') methods are to
prefer in long term forecasting.
14
s u b j e c t to h I P * 1 ; h = l . . . H (2) j j h h V P * I A ; j = l. . .J (3) hJ
h j h h h h V V P X = I I A X ? k = l . . . K (4) h jJ
jk h i j jk T h e p r o b a b i l i t y s u m i n f o r m a t i o n is u s e d in c o n s t r a i n t (2), s t a t i n g that the c h o i c e p r o b a b i l i t i e s f o r e a c h c h o o s e r s h o u l d su m to u n i t y , a n d in c o n s t r a i n t (3), s t a t i n g t hat the e x p e c t e d n u m b e r of c h o o s e r s c h o o s i n g a p a r t i c u l a r a l t e r n a t i v e s h o u l d eq u a l the a c t u a l n u m b e r of ch o i c e s , w h e r e h h A =1 if h c h o o s e s j a n d A =0 if h d o e s no t c h o o s e j. T h e e x p l a n a t o r y j j h c h a r a c t e r i s t i c s i n f o r m a t i o n is r e p r e s e n t e d in X , the v a l u e of the k i t h jk a t t r i b u t e f o r a l t e r n a t i v e j a n d c h o o s e r h, a n d c o n s t r a i n t (4) s t at e s th at the e x p e c t e d a n d the o b s e r v e d a g g r e g a t e v a l u e of e a c h a t t r i b u t e s h o u l d b e equal. T h e L a g r a n g i a n of (1) - (4) is h h h h L = I I P In P - £ 8 ( £ P - 1) - I .1 ( I P - N ) hJ
j j h h j J j oj h j j h h • I A ( I I P X - X ) (5) k k h j j jk k w h e r e 8 , ,\ a n d A a r e the L a g r a n g e m u l t i p l i e r s a n d h oj k h h h N * I A , X = I I A X . J h j k j h j jk A f t e r d e v e l o p i n g the f i r s t - o r d e r c o n d i t i o n s the s o l u t i o n o b t a i n e d g i v e s h h h P = exp( A + I À X ) / I exp( .\ + I A X ). i oi k k ik j oj k k jk (6
)G i v e n e q u i v a l e n t i n f o r m a t i o n , a c h a n g e f r o m the i n f o r m a t i o n - m i n i m i -
z a t i o n a p p r o a c h to a r a n d o m u t i l i t y m a x i m i z a t i o n a p p r o a c h m e a n s t h a t
the c ho i ce p r o b a b i l i t i e s , c o r r e s p o n d i n g to (6), c o u l d b e d e r i v e d as
f o l l o w s .
It is assumed that the choosers have similar preferences and that
the random utility function is linear in parameters and additive in
variables :
h
h
h
U =
«1+ I'
X
+
i
(7)
j
oj
k
k jk
J
h
where U
is the perceived utility of alternative j for chooser h;
3
n is a vector of utility coefficients, among which a
are alter
ed
native specific constants, measuring the unspecified part of utility,
h
and
*
is the vector of random utility. The random component (
is
3
assumed to be statistically independent and identically distributed
according to the extreme value distribution
h
-<
Prob( (
<= < ) = expl-exp
).
(8)
3
by this assumption the utllity-maximization choice probabilities will
have the form
h
h
h
P
* Prob( U
> U
;
V
3 i i)
i
i
3
h
h
= exp( (i
+ - u X
) / £ exp( (\
+ £ <r X
)
(9)
oi
k k ik
3
o3
k k 3k
16
T h u s , the c h o i c e p r o b a b i l i t i e s d e r i v e d b y the i n f o r m a t i o n - m i n i m i z a t i o n a p p r o a c h (6) a r e i d e n t i c a l in f o r m to t h o s e d e r i v e d b y the r a n d o m uti li t y- ma x ir a iz at i on a p p r o a c h (9). T h e r e f o r e A n a s c o n c l u d e s that it is n ot r e a s o n a b l e to c l a i m that m o d e l s b a s e d on i n f o r m a t i o n t h e o r y a r e i n h e r e n t l y less “b e h a v i o u r a l " t h a n r a n d o m u t i l i t y m o d e l s of d i s c r e t e ch o ice. O n e c a u s e f o r the o p p o s i t e o p i n i o n m a y be the f act, that
a p p l i e d r a n d o m u t i l i t y - m a x l m i z a t i o n m o d e l s a r e t r a d i t i o n a l l y d i s a g g r e
g a t e d , w h i l e i n f o r m a t i o n - m i n i m i z a t i o n m o d e l s a r e g e n e r a l l y e s t i m a t e d
f r o m a g g r e g a t e data. T h i s f a c t d o e s not, h o w e v e r , p r o v i d e a s o u n d b a s i s
f o r c o m p a r i n g the two a p p r o a c h e s .
O n e i m p o r t a n t p r o p e r t y of the M N L m o d e l is t e r m e d ' i n d e p e n d e n c e f r o m
i r r e l e v a n t a l t e r n a t i v e s ' (IIA). T h i s p r o p e r t y , i m p l y i n g that the r e l a
t ive od d s for the c h o i c e of a n y two a l t e r n a t i v e s is i n d e p e n d e n t of the
a t t r i b u t e s of a n y o t h e r a l t e r n a t i v e , is a d i r e c t c o n s e q u e n c e of the
a s s u m p t i o n of I n d e p e n d e n t l y d i s t r i b u t e d r a n d o m terms. T hus, in c a se s
w h e r e the u n o b s e r v e d a t t r i b u t e s of a l t e r n a t i v e s (the r a n d o m terms) a r e
c o r r e l a t e d , the a s s u m p t i o n of the M N L m o d e l is v i o l a t e d . In t hese
c a s e s a n e s t e d l ogit m o de l , as in p a p e r IV, m a y p r o v i d e a p r a c t i c a l w a y
of d e a l i n g w i t h the II A p ro b le m. M a y it h e r e s u f f i c e to s a y th at the
n e s t e d logit m o d e l is a n a p p r o a c h that m a k e s it p o s s i b l e to a c c o m o d a t e
v a r y i n g d e g r e e s of s i m i l a r i t y b e t w e e n a l t e r n a t i v e s .
S i n c e the (simple) M N L m o d e l a n d the S h a n n o n a p p r o a c h m od el , a c c o r
d i n g to t h e p r e s e n t a t i o n a b o v e le a ds to the s a m e f o r m a l r e p r e s e n t a t i o n
of the b e h a v i o u r , the I I A p r o b l e m is i m p l i e d a l s o w i t h r e s p e c t to the
i n f o r m a t i o n - m i n i m i z a t i o n a p p r o a c h . In t h is c o n t e x t it is i n t e r e s t i n g
to n o t e th e d e v e l o p m e n t of m o d e l s u s i n g the S h a n n o n a p p r o a c h w h e r e
the s t r u c t u r e of the m o d e l s ha r e s th e f r e e d o m f r o m the II A r e s
t r i c t i o n in t h e sam e w a y as t h e n e s t e d log i t mo d e l , see e.g. B o y c e
Now, it s h o u l d b e c l e a r f r o m a b o v e th at i n f o r m a t i o n - m i n i m i z a t i o n is a
m o r e g e n e r a l p r i n c i p l e t h a n t h e S h a n n o n a p p r o a c h u s e d in (1) - (4).
Li ke w i s e , the M N L m o d e l is Just a s p e c i a l ca s e of d i s c r e t e c h o i c e
models. T h i s b r i n g s A n a s (1983) to c l o s e his p a p e r b y s t a t i n g the
c o n v i c t i o n that the e q u i v a l e n c e b e t w e e n i n f o r m a t i o n - m i n i m i z a t i o n a n d
d i s c r e t e c h o i c e t h e o r y d o e s n o t e n d w i t h the M N L model.
R e f r a i n i n g f r o m a n y a t t e m p t s in th i s respe ct , t h e r e is, h o w e v e r , o n e
q u e s t i o n th a t s ho u ld , at least, b e r a i s e d in th i s c o n t e x t , viz. the
c o r r e s p o n d e n c e to the K u l l b a c k a p p r o a c h (the m i n i m u m i n f o r m a t i o n p r i n ciple) in a d i s c r e t e c h o i c e t h e o r y f ra me w o r k . A l t h o u g h a p r i o r p r o b a b i l i t y d i s t r i b u t i o n c a n be d e r i v e d b y m o d e l i n g e f f o r t s , see S n i c k a r s a n d W e i b u l l (1977), the d i r e c t u s e of h i s t o r i c a l d a t a is the c o m m o n p r o c e d u r e , as in p a p e r s II a n d III. A3 d i s c u s s e d b y F i s c h e r a n d N i j k a m p (1987) in a r e c e n t 'State of the Art' r e view, s ev e r a l i m p o r t a n t m e t h o d o l o g i c a l is su e s a r e r a i s e d w h e n c h o i c e b e h a v i o u r o v e r t ime is i n c o r p o r a t e d in d i s c r e t e c h o i c e m o d e l l
ing. O n e k e y issue is the p r o b l e m of d i s t i n g u i s h i n g b e t w e e n the i n f l u
en ce of tr ue ( st ru c tu r al ) s t a t e d e p e n d e n c e a n d s p u r i o u s s t a t e d e p e n
d e n c e in the m o de l i n g . F o l l o w i n g H e c k m a n (1981), th e s e i n f l u e n c e s a re
r e l a t e d to two d i s t i n c t e x p l a n a t i o n s fo r the e m p i r i c a l r e g u l a r i t y of
c u r r e n t b e h a v i o u r b e i n g d e p e n d e n t on pa st b e h a v i o u r .
One e x p l a n a t i o n is t h a t the p r e v i o u s c h o i c e h a s a g e n u i n e b e h a v i o u r a l
e f f e c t on the c u r r e n t ch o ice, as a c o n s e q u e n c e of, e. g., a l t e r e d p r e
ferenc e s. In this c a s e t h e r e is a tr ue st a t e d e p e n d e n c e of c u r r e n t on
past b eh a v i o u r . A s e c o n d e x p l a n a t i o n for the p h e n o m e n o n is t ha t the
p r e v i o u s c h o i c e m a y a p p e a r to i n f l u e n c e the c u r r e n t c h o i c e o n l y
18
d e t e r m i n e c h oi ce s . In t hi s c ase, the d e p e n d e n c e of c u r r e n t o n p a s t b e h a v i o u r is d u e to s e r i a l c o r r e l a t i o n in t h e u n o b s e r v a b l e s , a n d t his d e p e n d e n c e is th us t e r m e d s p u r i o u s s t a t e d e p e n d e n c e . A c o n v e n i e n t i l l u s t r a t i o n to t hi s i s s u e is g i v e n b y T a r d l f f (1980), s u g g e s t i n g t h at th e u t i l i t y f u n c t i o n (7) c o u l d b e r e p l a c e d b y a s p e c i f i c a t i o n t hat t a k es t he i n t e r t e m p o r a l n a t u r e of t he c h o i c e p r o c e s s int o a c c o u n t : h h h h * h Ü *£ a
X +X Y
C # + f + € (10)j t
k k Jkt
3* 33' 3 <t-l>
3
3t
w h e r e U is the u t i l i t y of a l t e r n a t i v e J for c h o o s e r h at t ime p e r i o d h jt t; X is the v a l u e of th e k : t h a t t r i b u t e for a l t e r n a t i v e j a n d c h o o s e r jkt h h, w h i c h m a y v a r y in time, C * 1 if c h o o s e r h c h o o s e s a l t e r n a t i v e j (t-1) ^ h J in the p r e v i o u s p e r i o d (t-1) a n d 0 o t h e r w i s e , t is an e r r o r c o m p o -j * h n e n t that v a r i e s a m o n g c h o o s e r s b u t is t i m e - i n v a r i a n t a n d < is an Jt e r r o r c o m p o n e n t tha t v a r i e s a m o n g b o t h c h o o s e r s a n d t i m e p e r i od s . T h e i n c l u s i o n of the s e c o n d t e r m in (10) a l l o w s c h o i c e in a p r e v i o u s p e r i o d to i n f l u e n c e c h o i c e in the c u r r e n t pe r iod. If t h e e s t i m a t e of the p a r a m e t e r
V
is p o s i t i v e ( n e g a t iv e ), it i n d i c a t e s a n i n c r e a s e d33
(d ec re a se d) c h o i c e p r o b a b i l i t y in t h e c u r r e n t pe ri o d. Now, b y s e t t i n g v a r i o u s t e rm s in (10) to zero, T a r d l f f c o n s i d e r s t h r e e s p e c i a l c a s es of t h e g e n e r a l d i s c r e t e c h o i c e model. F i r s t , if th e a s s u m p t i o n s tha tV
■ 0 a n d(
* 0 fo r a l l h, j a n d JJJ
J
a r e va l i d , the i n t e r t e m p o r a l c h o i c e b e h a v i o u r c a n b e t r e a t e d as i n d e p en d e n t . In th is c a se a s t a t i c d i s c r e t e c h o i c e m o d e l c a n be a p p l i e dd i r e c t l y to the d y n a m i c c h o i c e p r o b l e m ; e . g ., o n the a s s u m p t i o n that * h
(
is d i s t r i b u t e d as in (8), a M N L m o d e l c a n b e a p p li e d. Jt^ h
Second, if it can be assumed that
7
= 0 for all h and J but that
3
some
Ì
f 0, we have a true state dependence model. In this case
3 3
previous choices are explicitly considered but, since the error terms
are assumed to be independent across time periods, the usual type of
discrete choice models can still be applied directly.
„h
Third, turning the assumptions the other way round, i.e.
<
f 0 for
3
some h and 3, and
)’
* 0 for all h,3 and 3, we have a spurious state
33
dependence model. In this case previous choices are not considered,
but, since some unobservables are assumed to remain constant across
time pericds, the error terms are serially correlated and, hence,
current and previous choices are statistically dependent.
Consequently, the usual estimation procedures are no longer valid.
In these circumstances there are two approaches available to deal
with the error terms; The 'fixed effects' approach, in which the
^ h
t
terms are specified as alternative-specific constants for each
3
chooser, or the 'random effects' approach, in which the complex error
1)
variable structure is dealt with directly.
To conclude, by raising the question of the correspondence to the
Kuliback approach in a discrete choice theory framework, the discussion
has been carried to a generalization of the discrete choice model in a
dynamic context. Whether there is a meaningful answer to the opening
question has not been considered, but there is one specific reason for
2 )