Mazziotta–Pareto index explained

The Mazziotta–Pareto index (MPI) is a composite index^[1] (OECD, 2008^[2]) for summarizing a set of individual indicators that are assumed to be not fully substitutable.^[3] It is based on a non-linear function which, starting from the arithmetic mean of the normalized indicators, introduces a penalty for the units with unbalanced values of the indicators (De Muro et al., 2011^[4]).Two version of the index have been proposed: (a) MPI, and (b) adjusted MPI (AMPI). The first version is the best solution for a 'static' analysis (e.g., a single-year analysis), whereas the second one is the best solution for a 'dynamic' analysis (e.g., a multi-year analysis). For a comparison between the two versions, see Mazziotta and Pareto (2015).^[5]

MPI

Y = y _{ij} with n rows (statistical units) and m columns (individual indicators), we calculate the normalized matrix Z = z _{ij} as follows:z _{ij} =100 \pm[(y _{ij} - M _{y _{j}} )S ^{-1} _{y _{j}} ] 10

where

M _{y _{j}} and S _{y _{j}} are, respectively, the mean and standard deviation of the indicator j and the sign \pm is the 'polarity' of the indicator j , i.e., the sign of the relation between the indicator j and the phenomenon to be measured (+ if the individual indicator represents a dimension considered positive and - if it represents a dimension considered negative).Denoting with M _{z _{j}} ,S _{z _{j}} ,cv _{z _{j}} , respectively, the mean, standard deviation, and coefficient of variation of the normalized values for unit i , the composite index is given byMPI ^{\pm} _{i} = M _{z _{i}} ( 1 \pm cv ^{2 ) = M} _{z _{i}} \pm S _{z _{i}} cv _{z _{i}}

where the sign

\pm depends on the kind of phenomenon to be measured. If the composite index is 'increasing' or 'positive', i.e., increasing values of the index correspond to positive variations of the phenomenon (e.g., socio-economic development), then MPI ^{-} is used. On the contrary, if the composite index is 'decreasing' or 'negative', i.e., increasing values of the index correspond to negative variations of the phenomenon (e.g., poverty), then MPI ^{+} is used. In any cases, an unbalance among indicators will have a negative effect on the value of the index.

AMPI

Given the matrix

Y = y _{ij} , we calculate the matrix R = \{r _{ij} \} as follows:r _{ij} = \left[\left(y _{ij} -min _{i} y _{i\right)\left(max} _{i} y _{i} - min _{i} y _{i} \right) ^{-1} \right] 60+70

where

min _{i} y _{i} and max _{i} y _{i} are the 'goalposts' for the indicator j , i.e., a minimum and a maximum value that represent the possible range of the indicator j for all time periods considered. If the indicator j has negative 'polarity', the complement of (1) with respect to 200 is calculated.

To facilitate the interpretation of results, the 'goalposts' can be chosen so that 100 represents a reference value (e.g., the average in a given year). Let

inf _{j} y _{j} and \sup _{j} y _{j} be the minimum and maximum of indicator j across all time periods considered, and \operatorname{Ref} _{y _{j}} be the reference value for indicator j . Then the 'goalposts' are defined as: {\operatorname{Ref} _{y _{j}} }\pm \Delta, where \Delta = (\sup _{j} y _{j-inf} _{j} y _{j)} 2 ^{-1}

Denoting with

M _{r _{i}} ,S _{r _{i}} ,cv _{r _{i}} , respectively, the mean, standard deviation, and coefficient of variation of the normalized values for unit i , the composite index is given byAMPI ^{\pm} _{i} = M _{r _{i}} ( 1 \pm cv ^{2 ) = M} _{r _{i}} \pm S _{r _{i}} cv _{r _{i}}

where the sign

\pm depends on the kind of phenomenon to be measured.

Applications

The methodology is usually applied to the calculation of both composite indices of “positive” multidimensional phenomena (the higher the value the better the performance), such as well-being (Istat, 2015^[6]), quality of life (Mazziotta and Pareto, 2012^[7]), development (De Muro et al., 2011) and infrastructural endowment (Mazziotta and Pareto, 2009^[8]), and for “negative” multidimensional phenomena (the higher the value the worse the performance), such as poverty (De Muro et al., 2011).

Notes and References

1. A composite index is a mathematical combination (or aggregation as it is termed) of a set of indicators that represent the different dimensions of a phenomenon to be measured
2. OECD (2008). Handbook on Constructing Composite Indicators. Methodology and user guide. OECD Publications, Paris.
3. The components of a composite index are called 'substitutable' if a deficit in one component may be compensated by a surplus in another (e.g., a low value of “Proportion of people who have participated in religious or spiritual activities” can be offset by a high value of “Proportion of people who have participated in meetings of cultural or recreational associations” and vice versa). Similarly, the components of a composite index are called 'non-substitutable' if a compensation among them is not allowed (e.g., a low value of “Life expectancy at birth” cannot be offset by a high value of “GDP per capita” and vice versa).
4. De Muro, P., Mazziotta, M., Pareto, A. (2011). Composite Indices of Development and Poverty: An Application to MDGs. Social Indicators Research, 104, 1–18.
5. Mazziotta, M., Pareto, A. (2015). On a Generalized Non-compensatory Composite Index for Measuring Socio-economic Phenomena. Social Indicators Research, DOI 10.1007/s11205-015-0998-2
6. Istat (2015). Terzo Rapporto sul Benessere Equo e Sostenibile in Italia (BES). http://www.istat.it/it/files/2015/12/Rapporto_BES_2015.pdf
7. Mazziotta M., Pareto A. (2012). “A non-Compensatory Approach for the Measurement of the Quality of Life”, in “Quality of life in Italy: researches and reflections” (Maggino F. and Nuvolati P. eds.), Social Indicators Research Series. Springer.
8. Mazziotta M., Pareto A. (2009). “Il Metodo per la Sintesi degli Indicatori” in “La Dotazione di Infrastrutture e Servizi nella Sanità, Collana Informazioni Istat. Volume n.8.