Screening policies in health impact assessment: easier decision making through cluster analysis

Autor: Bacelar-Nicolau, Leonor, Pereira Miguel, José, Saporta, Gilbert
Přispěvatelé: Universidade de Lisboa (ULISBOA), CEDRIC. Méthodes statistiques de data-mining et apprentissage (CEDRIC - MSDMA), Centre d'études et de recherche en informatique et communications (CEDRIC), Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), International Epidemiological Association, Esther Bols, Luc Smits, Matty Weijenberg
Jazyk: angličtina
Rok vydání: 2015
Předmět:
Zdroj: European Journal of Public Health
European Journal of Epidemiology
8th European Congress of Epidemiology
8th European Congress of Epidemiology, International Epidemiological Association, Jun 2015, Maastricht, Netherlands. pp.852, ⟨10.1007/s10654-015-0072-z⟩
ISSN: 1101-1262
1464-360X
DOI: 10.1007/s10654-015-0072-z⟩
Popis: International audience; Background: Screening policies to identify candidates for applying Health Impact Assessment (HIA) is generally a qualitative process. Our aim is to show how the use of multivariate exploratory statistical methods such as cluster analysis may help the screening step of HIA in getting a shortlist of policies as HIA candidates quickly and reliably. Methods: A panel of 7 international renowned public health experts from Nova University in 2011 rated 76 policies proposed by the Technical Group planning the Portuguese hospital reform on a 10-point scale (1-Very low to 10-Very high) regarding Potential Impact, Ease of implementation and Implementation costs. Hierarchical cluster analysis is used to identify groups of similar policies regarding these 3 dimensions and prioritize those more pertinent of being considered for HIA according to chosen priority criteria, given different scenarios. Results: The analysis identified 7 groups of policies and showed that Ease of implementation was not as relevant to differentiate these groups as were Potential impact and Implementation costs: 3 groups present higher mean levels of potential impact (one with also higher mean levels of implementation costs, another with intermediate costs and a last one with lower costs): 2 groups present intermediate mean levels of potential impact (one with higher mean costs and another with lower ones): 2 groups present lower mean levels of potential impact (one with higher mean costs and another with lower ones). The groups of policies were then re-ranked according to different priority criteria, but Group 1 lead all possible scenarios being the group of most obvious candidates for HIA. Conclusion: Although multivariate statistical methodologies may be complex, decision-makers may thus obtain more evidence-based knowledge and not necessarily in a harder way to grasp. Applying multivariate statistical methods such as hierarchical cluster analysis as early as the screening step of HIA may be very helpful towards obtaining evidence based, reliable, participatory, flexible and more efficient ways of selecting policies for HIA.
Databáze: OpenAIRE
Externí odkaz: