“Economic and Political Integration in Europe: A Time-Series Quasi-Experimental Analysis”

Changes in political decision-making outputs and trading activities in the European Economic Community are examined around three quasi-experimental events (formation of the EEC in 1958, first agricultural package in 1962, and the agricultural crisis in 1965–66). On the basis of a preliminary analysis, nine variables were selected for inclusion in the study (three political decision variables and six trade indicators); these were then subjected to “interrupted time-series analysis,” through which the quasi-experimental effects of the three events were assessed for statistical significance (t-tests and autocorrelation measures) and theoretical validity (through the elimination of plausible rival interpretations). Political integration in the EEC is viewed as (1) positive growth in system indicators, and (2) increased mutual responsiveness among the major components or subsystems of the EEC. Results of the quasi-experimental analyses suggest that despite high positive growth in the selected variables, mutual responsiveness among system parts remains quite low; therefore, the principal conclusion drawn is that the EEC is a “weakly” integrating system—a collection of structures growing rapidly in many directions, with each structure very imperfectly responsive to the behavior of others. The paper urges and attempts to demonstrate the methodological usefulness of applying the logic of experimentation to ex-post-facto research. This approach entails the demonstration that non-random variation in independent and dependent variables has occurred, that these variables are related in some way, and that the relationship is nonspurious—that is, that the important confounding variables have been controlled by eliminating plausible rival hypotheses through statistical and analytical procedures.