Annex C. Detailed results of the econometric analyses
To test the relationship between trust in public institutions, its main drivers and the impact of other contextual variables, the study carried out an analysis based on logistic regressions. In all regressions, independent variables are normalised, meaning that the coefficients reported represent the change in the dependent variable as a result of one standard deviation increase in the explanatory variable. Results from logistic regressions are presented as average marginal effects for trust in the civil service, the parliament and the local government (local government councillors)
The policy and contextual drivers of trust in the local government, the civil service, the Parliament and the local civil service are presented respectively in Table A C.1, Table A C.2, and Table A C.3. The four instances are regressed using the three broad categories presented in the conceptual framework: 1) sociodemographic characteristics and interpersonal drivers; 2) policy drivers (i.e. competences and values); and 3) sustainability and perception of government actions in key societal trends. Each of the individual categories is first regressed on the dependent variable, first including the full set of variables, and in the following using a selection determined by a stepwise regression (except for the first category). In the final columns, all three categories are grouped together, and the significant variables are retained (using the same methodology). The full models have the higher explanatory power and are those retained for subsequent policy analysis (see Chapters 2-4).