Modeling “Equitable and Sustainable Well-being” (BES) Using Bayesian Networks: A Case Study of the Italian Regions

Abstract

Measurement of well-being has been a highly debated topic since the end of the last century. While some specific aspects are still open issues, a multidimensional approach as well as the construction of shared and well-rooted systems of indicators are now accepted as the main route to measure this complex phenomenon. A meaningful effort, in this direction, is that of the Italian “Equitable and Sustainable Well-being” (BES) system of indicators, developed by the Italian National Institute of Statistics (ISTAT) and the National Council for Economics and Labour (CNEL). The BES framework comprises a number of atomic indicators measured yearly at regional level and reflecting the different domains of well-being (e.g. Health, Education, Work & Life Balance, Environment,...). In this work we aim at dealing with the multidimensionality of the BES system of indicators and try to answer three main research questions: (I) What is the structure of the relationships among the BES atomic indicators; (II) What is the structure of the relationships among the BES domains; (III) To what extent the structure of the relationships reflects the current BES theoretical framework. We address these questions by implementing Bayesian Networks (BNs), a widely accepted class of multivariate statistical models, particularly suitable for handling reasoning with uncertainty. Implementation of a BN results in a set of nodes and a set of conditional independence statements that provide an effective tool to explore associations in a system of variables. In this work, we also suggest two strategies for encoding prior knowledge in the BN estimating algorithm so that the BES theoretical framework can be represented into the network.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Notes

  1. 1.

    According to this distance, given a set of continuous variable (or features) and two observations x and y, the contribution of each feature to a measure of closeness between x and y is set to 1 if the feature exhibits missing values in either x or y while, if values are not missing, it corresponds to their difference normalized by the feature range. To come up with a final distance between x and y, all features’ contributions are then aggregated by means of the euclidean distance.

References

  1. Blalock, H. M, Jr. (2018). Causal inferences in nonexperimental research. Chapel Hill: UNC Press Books.

    Google Scholar 

  2. Bollen, K. A., & Diamantopoulos, A. (2017). In defense of causal-formative indicators: A minority report. Psychological Methods, 22(3), 581.

    Article  Google Scholar 

  3. Ceriani, L., Gigliarano, C et al. (2016). Multidimensional well-being: A Bayesian Networks approach. Tech. rep.

  4. Checchi, D., & Peragine, V. (2010). Inequality of opportunity in Italy. The Journal of Economic Inequality, 8(4), 429–450.

    Article  Google Scholar 

  5. Chelli, F. M., Ciommi, M., Emili, A., Gigliarano, C., & Taralli, S. (2015). Comparing equitable and sustainable well-being (BES) across the Italian provinces. A factor analysis-based approach. Rivista Italiana di Economia Demografia e Statistica, 69(3), 61–72.

    Google Scholar 

  6. Chelli, F. M., Ciommi, M., Emili, A., Gigliarano, C., & Taralli, S. (2016). Assessing the equitable and sustainable well-being of the Italian provinces. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 24(Suppl. 1), 39–62.

    Article  Google Scholar 

  7. Claeskens, G., & Hjort, N. L. (2008). Model selection and model averaging. Cambridge: Cambridge University Press.

    Google Scholar 

  8. Cowell, R. G., Dawid, P., Lauritzen, S. L., & Spiegelhalter, D. J. (2006). Probabilistic networks and expert systems: Exact computational methods for Bayesian networks. New York: Springer Science & Business Media.

    Google Scholar 

  9. D’Agostino, R. B. (1986). Goodness-of-fit-techniques (Vol. 68). Boca Raton: CRC Press.

    Google Scholar 

  10. Davino, C., Dolce, P., & Taralli, S. (2017). Quantile composite-based model: A recent advance in PLS-PM. In M. Ronkko (Ed.), Partial least squares path modeling (pp. 81–108). New York: Springer.

    Google Scholar 

  11. De Muro, P., Mazziotta, M., Pareto, A. (2009). Composite indices for multidimensional development and poverty: An application to MDG indicators. In: Wye City Group Meeting.

  12. Diamantopoulos, A., & Siguaw, J. A. (2006). Formative versus reflective indicators in organizational measure development: A comparison and empirical illustration. British Journal of Management, 17(4), 263–282.

    Article  Google Scholar 

  13. Diamantopoulos, A., & Winklhofer, H. M. (2001). Index construction with formative indicators: An alternative to scale development. Journal of Marketing Research, 38(2), 269–277.

    Article  Google Scholar 

  14. Duda, R. O., Hart, P. E., & Stork, D. G. (2012). Pattern classification. Hoboken: Wiley.

    Google Scholar 

  15. Ebert-Uphoff, I., & Deng, Y. (2012a). A new type of climate network based on probabilistic graphical models: Results of boreal winter versus summer. Geophysical Research Letters, 39(19), 1–7.

    Article  Google Scholar 

  16. Ebert-Uphoff, I., & Deng, Y. (2012b). Causal discovery for climate research using graphical models. Journal of Climate, 25(17), 5648–5665.

    Article  Google Scholar 

  17. Ebert-Uphoff, I., & Deng, Y. (2015). Using causal discovery algorithms to learn about our planet’s climate. In V. Lakshmanan, E. Gilleland, A. McGovern, & M. Tingley (Eds.), Machine learning and data mining approaches to climate science (pp. 113–126). New York: Springer.

    Google Scholar 

  18. Ferrara, A.R., Nisticò, R. (2019). Does institutional quality matter for multidimensional well-being inequalities? Insights from Italy. Social Indicators Research pp. 1–43.

  19. Franzin, A., Sambo, F., & Di Camillo, B. (2016). bnstruct: An R package for Bayesian Network structure learning in the presence of missing data. Bioinformatics, 33(8), 1250–1252.

    Google Scholar 

  20. Friedman, N., Goldszmidt, M., Wyner, A. (1999a). Data analysis with Bayesian networks: A bootstrap approach. In: Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence, Morgan Kaufmann Publishers Inc., pp 196–205.

  21. Friedman, N., Nachma, I., Pe’er, D. (1999b). Learning Bayesian network structure from massive datasets: The “sparse candidate” algorithm. In: Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence, Morgan Kaufmann Publishers Inc., pp 206–215.

  22. Friedman, N., Linial, M., Nachman, I., & Pe’er, D. (2000). Using Bayesian networks to analyze expression data. Journal of Computational Biology, 7(3–4), 601–620.

    Article  Google Scholar 

  23. Frydenberg, M. (1990). The chain graph Markov property. Scandinavian Journal of Statistics, 17, 333–353.

    Google Scholar 

  24. Gardiner, S. M. (2011). A perfect moral storm: The ethical tragedy of climate change. Oxford: Oxford University Press.

    Google Scholar 

  25. Hall, J., Giovannini, E., Morrone, A., Ranuzzi, G. (2010). A framework to measure the progress of societies.

  26. Helldin, T., Riveiro, M. (2009). Explanation Methods for Bayesian Networks: review and application to a maritime scenario. In: Proceedings of the 3rd Annual Skövde Workshop on Information Fusion Topics (SWIFT 2009), pp 11–16.

  27. Howell, R. D., Breivik, E., & Wilcox, J. B. (2007). Reconsidering formative measurement. Psychological Methods, 12(2), 205.

    Article  Google Scholar 

  28. Hradsky, B. A., Penman, T. D., Ababei, D., Hanea, A., Ritchie, E. G., York, A., et al. (2017). Bayesian networks elucidate interactions between fire and other drivers of terrestrial fauna distributions. Ecosphere, 8(8), e01926.

    Article  Google Scholar 

  29. ISTAT. (2015). Il benessere equo e sostenibile in italia (2015). Retrieved from https://www.istatit/it/files//2015/12/Rapporto_BES_2015pdf.

  30. ISTAT. (2018). Il benessere equo e sostenibile in italia (2018). Retrieved from https://www.istatit/it/files//2018/12/Bes_2018pdf.

  31. Jordan, M. I. (1998). Learning in graphical models (Vol. 89). New York: Springer Science & Business Media.

    Google Scholar 

  32. Kitov, I., Kitov, O. (2011). Employment, unemployment and real economic growth. Unemployment and Real Economic Growth (July 24, 2011).

  33. Kolar, M. (2013). Uncovering structure in high-dimensions: Networks and multi-task learning problems. PhD thesis, figshare.

  34. Koller, D., Friedman, N., & Bach, F. (2009). Probabilistic graphical models: principles and techniques. London: MIT Press.

    Google Scholar 

  35. Kreyenfeld, M., & Hank, K. (2000). Does the availability of child care influence the employment of mothers? Findings from western germany. Population Research and Policy Review, 19(4), 317–337.

    Article  Google Scholar 

  36. Lappenschaar, M., Hommersom, A., Lucas, P. J., Lagro, J., & Visscher, S. (2013). Multilevel Bayesian networks for the analysis of hierarchical health care data. Artificial Intelligence in Medicine, 57(3), 171–183.

    Article  Google Scholar 

  37. Lauritzen, S. L. (1996). Graphical models (Vol. 17). Oxford: Clarendon Press.

    Google Scholar 

  38. Lauritzen, S. L., & Wermuth, N. (1989). Graphical models for associations between variables, some of which are qualitative and some quantitative. The Annals of Statistics, 17, 31–57.

    Article  Google Scholar 

  39. Maggino, F. (2017). Developing indicators and managing the complexity. In F. Maggino (Ed.), Complexity in society: From indicators construction to their synthesis (pp. 87–114). New York: Springer.

    Google Scholar 

  40. Maggino, F., & Zumbo, B. D. (2012). Measuring the quality of life and the construction of social indicators. In K. C. Land, A. C. Michalos, & M. J. Sirgy (Eds.), Handbook of social indicators and quality of life research (pp. 201–238). New York: Springer.

    Google Scholar 

  41. Maitah, M., Toth, D., & Kuzmenko, E. (2015). Exploring the relationship between economic growth and employment in the Czech Republic and Belgium. European Studies Review, 7, 115.

    Google Scholar 

  42. Mazziotta, M., & Pareto, A. (2016). On a generalized non-compensatory composite index for measuring socio-economic phenomena. Social Indicators Research, 127(3), 983–1003.

    Article  Google Scholar 

  43. Mazziotta, M., & Pareto, A. (2019). Use and misuse of PCA for measuring well-being. Social Indicators Research, 142(2), 451–476.

    Article  Google Scholar 

  44. Milns, I., Beale, C. M., & Smith, V. A. (2010). Revealing ecological networks using Bayesian network inference algorithms. Ecology, 91(7), 1892–1899.

    Article  Google Scholar 

  45. Molina, J. L., Pulido-Velázquez, D., García-Aróstegui, J. L., & Manuel, P. V. (2013). Dynamic Bayesian networks as a decision support tool for assessing climate change impacts on highly stressed groundwater systems. Journal of Hydrology, 479, 113–129.

    Article  Google Scholar 

  46. Monte, A., Schoier, G. (2017). Il benessere economico e la sua evoluzione nelle regioni italiane: un’analisi attraverso indicatori.

  47. Neapolitan, R. E., et al. (2004). Learning bayesian networks (Vol. 38). Upper Saddle River, NJ: Pearson Prentice Hall.

    Google Scholar 

  48. Oposa, A. A. (1994). In defense of future generations. Phil LJ, 69, 164.

    Google Scholar 

  49. Panzera, D., & Postiglione, P. (2019). Measuring the spatial dimension of regional inequality: An approach based on the gini correlation measure. Social Indicators Research, 148, 379–394.

    Article  Google Scholar 

  50. Pearl, J. (2014). Probabilistic reasoning in intelligent systems: Networks of plausible inference. Amsterdam: Elsevier.

    Google Scholar 

  51. Penny, R.N., Reale, M. (2004). Using graphical modelling in official statistics.

  52. Peterson, R. (2018). bestNormalize: Normalizing transformation functions. R package version, 1(2).

  53. Peterson, R.A., Cavanaugh, J.E. (2019). Ordered quantile normalization: A semiparametric transformation built for the cross-validation era. Journal of Applied Statistics. https://doi.org/10.1080/02664763.2019.1630372.

  54. Rodin, A., Mosley, T. H, Jr., Clark, A. G., Sing, C. F., & Boerwinkle, E. (2005). Mining genetic epidemiology data with Bayesian networks application to APOE gene variation and plasma lipid levels. Journal of Computational Biology, 12(1), 1–11.

    Article  Google Scholar 

  55. Russell, S. J., & Norvig, P. (2016). Artificial intelligence: A modern approach. Malaysia: Pearson Education Limited.

    Google Scholar 

  56. Scutari, M., & Denis, J. B. (2014). Bayesian networks: With examples in R. Boca Raton: Chapman and Hall/CRC.

    Google Scholar 

  57. Scutari, M., Howell, P., Balding, D. J., & Mackay, I. (2014). Multiple quantitative trait analysis using Bayesian networks. Genetics, 198(1), 129–137.

    Article  Google Scholar 

  58. Scutari, M., Ness, R. (2012). bnlearn: Bayesian network structure learning, parameter learning and inference. R package version 3.

  59. Sebastiani, P., & Ramoni, M. (2001). On the use of Bayesian networks to analyze survey data. Research in Official Statistics, 4(1), 53–64.

    Google Scholar 

  60. Sen, A., et al. (1999). Commodities and capabilities. Oxford: OUP Catalogue.

    Google Scholar 

  61. Stiglitz, J.E., Sen, A., Fitoussi, J.P., on the Measurement of Economic Performance C, Progress S (2009). Report by the commission on the measurement of economic performance and social progress.

  62. Van der Heijden, M., Velikova, M., & Lucas, P. J. (2014). Learning Bayesian networks for clinical time series analysis. Journal of Biomedical Informatics, 48, 94–105.

    Article  Google Scholar 

  63. Verma, T., & Pearl, J. (1991). Equivalence and synthesis of causal models. Computer Science Department: UCLA.

  64. Vitolo, C., Scutari, M., Ghalaieny, M., Tucker, A., & Russell, A. (2018). Modeling air pollution, climate, and health data using Bayesian Networks: A case study of the English regions. Earth and Space Science, 5(4), 76–88.

    Article  Google Scholar 

  65. Wainwright, M. J., Jordan, M. I., et al. (2008). Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning, 1(1–2), 1–305.

    Article  Google Scholar 

  66. Wesselink, B., Bakkes, J., Best, A., Hinterberger, F., ten Brink, P. (2007). Measurement beyond GDP. Beyond GDP 304.

  67. Whittaker, J. (2009). Graphical models in applied multivariate statistics. Hoboken: Wiley Publishing.

    Google Scholar 

  68. Wilcox, J. B., Howell, R. D., & Breivik, E. (2008). Questions about formative measurement. Journal of Business Research, 61(12), 1219–1228.

    Article  Google Scholar 

  69. Wilson, D. R., & Martinez, T. R. (1997). Improved heterogeneous distance functions. Journal of Artificial Intelligence Research, 6, 1–34.

    Article  Google Scholar 

  70. Zhou, Y. (2011). Structure learning of probabilistic graphical models: a comprehensive survey. arXiv:11116925.

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Federica Onori.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

See Tables 2, 3, 4, 5, 6, 7, 8and 9.

Table 2 BES dataset: BES domains and corresponding atomic indicators (Outcome domains) (ISTAT 2018)
Table 3 BES dataset: BES domains and corresponding atomic indicators (Context domains) (ISTAT 2018)
Table 4 Pearson P test statistic for Gaussianity and the corresponding used transformation for each atomic indicator (Outcome domains)
Table 5 Pearson P test statistic for Gaussianity and the corresponding used transformation for each atomic indicator (Context domains)
Table 6 Prior blacklist: list of the edges \(X \rightarrow Y\) not allowed to be present in the network structure
Table 7 Network estimated by adopting prior Strategy 1 with NUTS 1 level areas (NW-NE-C-S-I): in-degree, out-degree and Markov blanket size of the nodes (Outcome domains)
Table 8 Network estimated by adopting prior Strategy 1 with NUTS 1 level areas (NW-NE-C-S-I): in-degree, out-degree and Markov blanket size of the nodes (Context domains)
Table 9 Network estimated by adopting prior Strategy 1 with NUTS 1 level areas (NW-NE-C-S-I): direct connections among domains

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Onori, F., Jona Lasinio, G. Modeling “Equitable and Sustainable Well-being” (BES) Using Bayesian Networks: A Case Study of the Italian Regions. Soc Indic Res (2020). https://doi.org/10.1007/s11205-020-02406-8

Download citation

Keywords

  • Well-being
  • Probabilistic graphical models
  • BES
  • Bayesian Networks
  • Italian regions