Filomena Maggino
filomena.maggino@unifi.it
Towards more participative
Towards more participative
methods in the construction of
methods in the construction of
composite indicators
composite indicators
.
.
The case of
1.Introduction
3.Obtaining weights:
objective ad subjective approaches
2.Obtaining weights:
general principles
4.Conclusions
1.Introduction
3.Obtaining weights:
objective ad subjective approaches
2.Obtaining weights:
general principles
4.Conclusions
How to obtain this ?
How to obtain this ?
How to obtain this ?
How to obtain this ?
By involving
By involving
By involving
By involving
individuals
individuals
individuals
individuals
in the process of
in the process of
in the process of
in the process of
social indicators construction
social indicators construction
social indicators construction
social indicators construction
GOAL
Methodology aimed
Methodology aimed
Methodology aimed
Methodology aimed at
at
at constructing
at
constructing
constructing
constructing
indicators
indicators
indicators
indicators
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
“
technology
technology”
technology
technology
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
need
need
need
need to have specialistic
to have specialistic
to have specialistic
to have specialistic training in
training in
training in
training in order to
order to
order to
order to
apply
apply
apply
apply the procedure in a
the procedure in a
the procedure in a
the procedure in a
scientific
scientific
scientific
scientific
and
and
and
and
objective
objective
objective
Actually
Actually
Actually
Actually
the procedure,
the procedure,
the procedure,
the procedure,
the procedure,
the procedure,
the procedure,
the procedure,
even though scientifically
even though scientifically
even though scientifically
even though scientifically
defined
defined
defined
defined, , , ,
is
is
is
is
far
far
far
far
far
far
far
far
from being
from being
from being
from being
from being
from being
from being
from being
objective
objective
objective
objective
objective
objective
objective
Indicators construction
Indicators construction
Indicators construction
Indicators construction
is developed
is developed
is developed
is developed through
through
through
through different
different
different
different
stages
stages
stages
stages. . . .
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
Each
Each
Each
Each stage
stage
stage
stage requires
requires
requires
requires
a
a
a
a
decision
decision
decision / / / / choice
decision
choice
choice
choice
((((methodological
methodological or
methodological
methodological
or
or
or not
not
not
not) ) ) )
to
to
to
to be taken
be taken
be taken
be taken....
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
Some decisions are quite technical
others may involve value judgments
It is quite difficult to make these decisions
It is quite difficult to make these decisions
It is quite difficult to make these decisions
It is quite difficult to make these decisions
objective
objective
objective
objective
Generally
Generally
Generally
Generally
they are taken through a process accepted and
they are taken through a process accepted and
they are taken through a process accepted and
they are taken through a process accepted and
shared by the
shared by the
shared by the
shared by the
scientific community
scientific community
scientific community
scientific community
But
But
But
But
can we share methodological decisions /choices
can we share methodological decisions /choices
can we share methodological decisions /choices
can we share methodological decisions /choices
by
by
by
1.
1.
1.
1. choosing
choosing
choosing
choosing analytical approach
analytical approach
analytical approach
analytical approach
2.
2.
2.
2. choosing
choosing
choosing
choosing and
and
and obtaining weights
and
obtaining weights
obtaining weights
obtaining weights
3.
3.
3.
3. choosing
choosing
choosing
choosing
and
and
and
and identifying the
identifying the
identifying the
identifying the
aggregating
aggregating
aggregating
aggregating technique
technique
technique
technique
4.
4.
4.
4. choosing
choosing
choosing
choosing models
models
models
models and
and
and
and conceptual
conceptual
conceptual
conceptual
approaches
approaches
approaches
approaches in
in
in
in order to assess
order to assess
order to assess
order to assess
(i)
(i)
(i)
(i) robustness
robustness
robustness
robustness
((((iiiiiiii) ) ) ) discriminant capacity
discriminant capacity
discriminant capacity
discriminant capacity
In
Weights
Weights
Weights
Weights
in indicators construction aim at
assigning differential
importance
importance
importance
importance
to the indicators
to be aggregated.
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
this process does not represent simply a
technical problem
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
weights judgment values
weights judgment values
weights judgment values
weights judgment values
Weights
Weights
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
differential subjective
differential subjective
weights
weights
How to obtain subjective weights
How to obtain subjective weights
How to obtain subjective weights
How to obtain subjective weights????
Determining
Determining
and
and
applying differential
applying differential
subjective
subjective
weights
weights
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
solid
conceptual
conceptual
framework
framework
helping in clarifying how
to
obtain
obtain
obtain
obtain
weights
to
assign
assign
assign
assign
weights
1.Introduction
3.Obtaining weights:
objective ad subjective approaches
2.Obtaining weights:
general principles
4.Conclusions
General basic conditions concerning weights
The identified weights
are
non negative
numbers
add up to unity
are
related
in
some
way
to
the
corresponding
score
may require to be rescaled in order to have
an
identical range
(0; 1)
Reproducing each sub-score’s contribution to CI
a criterion has to be adopted
a criterion has to be adopted
a criterion has to be adopted
a criterion has to be adopted
weighting system
weighting system
weighting system
weighting system
improvement and refinement of the adopted
improvement and refinement of the adopted
improvement and refinement of the adopted
improvement and refinement of the adopted
model of measurement
model of measurement
model of measurement
model of measurement.
Identification of a generic weighting system needs to take into accounttake into accounttake into accounttake into account :
rationale and theoretical framework
rationale and theoretical framework
rationale and theoretical framework
rationale and theoretical framework
on which themeasurement of the complex characteristics is founded and that will consequently regard the synthetic score
meaning and contribution of each sub
meaning and contribution of each sub----score
meaning and contribution of each sub
meaning and contribution of each sub
score
score
score
to thesynthesis
quality of data and statistical adequacy of
quality of data and statistical adequacy of
quality of data and statistical adequacy of
quality of data and statistical adequacy of
indicators
indicators
indicators
indicators
proportional size of weightsproportional size of weightsproportional size of weightsproportional size of weights
a.
a.
a.
a.
a.
a.
a.
a.
equal
equal
equal
equal or
equal
equal
equal
equal
differential
differential
differential
differential weighting
differential
differential
differential
differential
aggregation technique to be adopted aggregation technique to be adopted aggregation technique to be adopted aggregation technique to be adoptedb.
b.
b.
b.
b.
b.
b.
b.
compensatory
compensatory
compensatory
compensatory or
compensatory
compensatory
compensatory
compensatory
non
non
non
non
non
non
non
non
----
----
compensatory
compensatory
compensatory
compensatory
compensatory
compensatory
compensatory
compensatory
Identification of a generic weighting system needs decisions to be taken
N.B.
AAAA
whole set of weights
whole set of weights
whole set of weights
whole set of weights
whole set of weights
whole set of weights
whole set of weights
whole set of weights
able to express in
a
a
a
a
perfect
perfect
perfect
perfect way
perfect
perfect
perfect
perfect
way
way
way
the contribution of each indicator
General statements
does not exist
does not exist
does not exist
does not exist
does not exist
does not exist
does not exist
does not exist
Equal vs. differential weighting
Equal vs. differential weighting
Equal vs. differential weighting
Equal vs. differential weighting
First decision
First decision
First decision
First decision
Equal Weighting
Equal Weighting
Equal Weighting
Equal Weighting
Equal Weighting
Equal Weighting
Equal Weighting
Equal Weighting
Different Weighting
Different Weighting
Different Weighting
Different Weighting
Different Weighting
Different Weighting
Different Weighting
Different Weighting
The choice will strongly influence
The choice will strongly influence
The choice will strongly influence
The choice will strongly influence
the final results
the final results
the final results
the final results
• different components different components different components different components have tohave tohave tohave to bebebebe aggregatedaggregatedaggregatedaggregated by by by by different numbers of indicators
different numbers of indicators different numbers of indicators
different numbers of indicators ( synthetic score = unbalanced structure);
• indicators exist measuring the same componentindicators exist measuring the same componentindicators exist measuring the same componentindicators exist measuring the same component (
double weighted
odouble counting
).Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
procedure mainlywhen
when
when
when
when
when
when
when
Equal weighting
Equal weighting
Equal weighting
Equal weighting
Differential weighting
Differential weighting
Differential weighting
Differential weighting
•
• theoretical reflectionstheoretical reflectionstheoretical reflectionstheoretical reflectionstheoretical reflectionstheoretical reflectionstheoretical reflectionstheoretical reflections •
• methodological concernsmethodological concernsmethodological concernsmethodological concernsmethodological concernsmethodological concernsmethodological concernsmethodological concerns
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
Doubtful
procedure mainlywhen
when
when
when
when
when
when
when
not supported bynot supported bynot supported bynot supported byCompensatory and
Compensatory and
Compensatory and
Compensatory and
Non
Non
Non
Non----compensatory
compensatory
compensatory
compensatory
aggregation techniques
aggregation techniques
aggregation techniques
aggregation techniques
In order to avoid incoherencies between
theoretical meaning actual application
of weights of weights
a consistent aggregating technique is needed
by considering
compensability
compensability
compensability
compensability
among
the elementary indicators
Compensatory
Compensatory
Compensatory
Compensatory
Compensatory
Compensatory
Compensatory
Compensatory
aggregating approach- additive approachadditive approachadditive approachadditive approach (simple addition)
- geometrical approachgeometrical approachgeometrical approachgeometrical approach (multiplicative technique)
low values compensated by high values
low values compensated by high values
low values compensated by high values
low values compensated by high values
synthetic score does not allow us to return to the original individual profiles
problems of interpretation
problems of interpretation
problems of interpretation
problems of interpretation
In obtaining
ssss
ssss
ubjective
ubjective
ubjective
ubjective
ubjective
ubjective
ubjective
ubjective
weights
weights
weights
weights
weights
weights
weights
weights
the decisions / choices
do not rely on experts.
Statements in obtaining
subjective weights
“importance” is a distinct construct?
psychometric properties of importance ratingspsychometric properties of importance ratingspsychometric properties of importance ratingspsychometric properties of importance ratingsinternal consistency and test-retest reliability Identification of a subjective weighting system
needs to take into accounttake into accounttake into accounttake into account :
Statements in obtaining
subjective weights
the criterion the level
the techniques the approach
Identification of a subjective weighting system: a modelmodelmodelmodel should be chosen by considering
Statements in obtaining
subjective weights
1.Introduction
3.Obtaining weights:
objective ad subjective approaches
2.Obtaining weights:
general principles
4.Conclusions
Approaches for obtaining weights
Approaches for obtaining weights
Approaches for obtaining weights
Approaches for obtaining weights
Approaches for obtaining weights
Approaches for obtaining weights
Approaches for obtaining weights
Approaches for obtaining weights
can produce:
can produce:
can produce:
can produce:
can produce:
can produce:
can produce:
can produce:
a.
a.
a.
a.
statistical statistical statistical statistical methodsmethodsmethodsmethodsb.
b.
b.
b.
multimultimultimulti----attribute attribute attribute approachesattribute approachesapproachesapproachesc.
c.
c.
c.
scaling approachesscaling approachesscaling approachesscaling approachesApproaches for obtaining
weights
““““objectiveobjectiveobjectiveobjective weightsweightsweights””””weights
⇒
⇒
⇒
⇒
a.
a.
a.
a. Statistical methods
Statistical methods
Statistical methods
Statistical methods
Approaches for obtaining
weights
b.
b.
b.
b. Multi
Multi
Multi----attributes approaches
Multi
attributes approaches
attributes approaches
attributes approaches
Approaches for obtaining
weights
Multi
Multi
Multi
Multi----Attribute Models
Attribute Models
Attribute Models
Attribute Models
allow
subjective importance weights to be identified at
subjective level
through an indirect approach
by
Multi-attributes
approaches
• managing a certain number of combined comparisons
• applying methods aimed at making decision among different available alternatives
1. 1. 1.
1. MultiMultiMulti----Attribute Decision MakingMulti Attribute Decision MakingAttribute Decision MakingAttribute Decision Making:
Analytic Hierarchy Process Analytic Hierarchy Process Analytic Hierarchy Process Analytic Hierarchy Process (AHP) (pairwisecomparison)
Among these models we can distinguish:
Among these models we can distinguish:
Among these models we can distinguish:
Among these models we can distinguish:
2. 2. 2.
2. MultiMultiMulti----Attribute Compositional ModelMulti Attribute Compositional ModelAttribute Compositional ModelAttribute Compositional Modelssss:
Conjoint Analysis Conjoint Analysis (CA)Conjoint Analysis Conjoint AnalysisMulti-attributes
approaches
c.
c.
c.
c. Scaling approaches
Scaling approaches
Scaling approaches
Scaling approaches
Approaches for obtaining
weights
DimensionalityDimensionalityDimensionalityDimensionality Nature of dataNature of dataNature of dataNature of data
Scaling techniqueScaling techniqueScaling techniqueScaling technique
Criterion for testing the modelCriterion for testing the modelCriterion for testing the modelCriterion for testing the model Standard of measurementStandard of measurementStandard of measurementStandard of measurement
Contribution to the measurement of each multiple Contribution to the measurement of each multiple Contribution to the measurement of each multiple Contribution to the measurement of each multiple measures measures measures measures
They
They
They
They can
can
can
can be
be
be
be classifi
classifi
classifi
classified through
ed through
ed through their features
ed through
their features
their features
their features::::
wh
wh
wh
whoooose nature is comparative or preferential
se nature is comparative or preferential
se nature is comparative or preferential
se nature is comparative or preferential
((((in in in in yellow in the previous table)yellow in the previous table)yellow in the previous table)yellow in the previous table)
produced by a comparative scaling technique
produced by a comparative scaling technique
produced by a comparative scaling technique
produced by a comparative scaling technique
(in pink in the previous table) (in pink in the previous table) (in pink in the previous table) (in pink in the previous table)
Among all these approaches we
Among all these approaches we
Among all these approaches we
Among all these approaches we
Among all these approaches we
Among all these approaches we
Among all these approaches we
Among all these approaches we
need
need
need
need
need
need
need
need
to
to
to
to
to
to
to
to
select those approaches that utilize data:
select those approaches that utilize data:
select those approaches that utilize data:
select those approaches that utilize data:
select those approaches that utilize data:
select those approaches that utilize data:
select those approaches that utilize data:
select those approaches that utilize data:
-- group weightinggroup weightinggroup weightinggroup weighting: group weightinggroup weightinggroup weightinggroup weighting
-
Thurstone model
(differential scale
) -Unfolding model
(perceptual mapping
)
-- individual weightingindividual weightingindividual weightingindividual weighting: individual weightingindividual weightingindividual weightingindividual weighting
-
Conjoint model
Scaling models allowing subjective
Scaling models allowing subjective
Scaling models allowing subjective
Scaling models allowing subjective
weights to be obtained
weights to be obtained
weights to be obtained
weights to be obtained are
are
are
are
1.Introduction
3.Obtaining weights:
objective ad subjective approaches
2.Obtaining weights:
general principles
4.Conclusions
This work aims at
systematically framing the issue and
showing the possible approaches in order to
obtaining weights in a subjective perspective
⇓
⇓
⇓
⇓
⇓
⇓
⇓
⇓
many technical issues should be clarified.
Difficulties
Obtaining subjective weights requires and relies
on the accomplishment of large survey projects
aimed at collecting “importance” data.
- Time
- Resources
- Sampling
- Field work
- …
Conclusions
«Constructing composite indicators should take
into account the agreement among citizens
concerning the importance to be assigned to each
indicator»
(Hagerty and Land, 2007)
Seen in this perspective, this topic can be placed
in the ambit of an improvement of democratic
participation to decisions (“res publica”).
Presentation designer: trapani.marco@gmail.com