Suchergebnisse

In spite of the fact that political eras in the United States are widely (and often ambiguously) defined in terms of a general policy sentiment or mood, political scientists have done little in the way of rigorous analysis regarding this subject. I argue that shifts in domestic policy sentiment along a liberal–conservative continuum may be understood in part as responses to changing economic expectations. Specifically, expectations of a strong economy result in greater support for liberal domestic policies, whereas anticipation of declining economic conditions pushes the national policy mood to the right. Using quarterly data for the period 1968–88, I present a multiple-time-series error correction model that lends considerable support to the hypothesis.

My aim in this note is not to rejoin the useful comments of Beck and Williams (in this volume) in this symposium, but rather to speculate about the future place of cointegration and error correction in the discipline of political science. Stopping somewhere short of the pejorative "hegemony" Williams anticipates for the ECM framework, I agree that this modeling approach is likely to enjoy wide play in a variety of substantive arenas. As such, I believe it is critical that analysts concerned with advancing cointegration methodology do so with an eye toward not just technical issues, but also questions regarding the theory of cointegration, error correction, and time-series stationarity. Furthermore, if methodological advancements are to be of any real value, they must be accessible to political scientists who, for inexplicable reasons, care not to make econometrics the center of their beings. In short, I am concerned
that we will produce a method (1) dominated by questions of measurement and measurement strategy (at the expense of theory) and (2) inaccessible to (and therefore ignored by) most analysts. Such an evolution would be tantamount to losing the error correction forest for its trees.

For political scientists who engage in longitudinal analyses, the question of how best to deal with nonstationary time-series is anything but settled. While many believe that little is lost when the focus of empirical models shifts from the nonstationary levels to the stationary changes of a series, others argue that such an approach erases any evidence of a long-term relationship among the variables of interest. But the pitfalls of working directly with integrated series are well known, and post-hoc corrections for serially correlated errors often seem inadequate. Compounding (or perhaps alleviating, if one believes in the power of selective perception) the difficult question of whether to difference a time-series is the fact that analysts have been forced to rely on subjective diagnoses of the stationarity of their data. Thus, even if one felt strongly about the superiority of one modeling approach over another, the procedure for determining whether that approach is even applicable can be frustrating.

We examine the degree to which aggregate-level support for the Supreme Court is a function of its divergence from the ideological mood of the country. We first overcome the problem of irregular & infrequent measurement of attitudes toward the Supreme Court by employing an approach developed by Stimson (1991), which allows us to pool seventeen similar survey items administered a total of ninety-three times to produce a single, semiannual time series of support for the Supreme Court, extending from 1973 through 1993. We then consider the effect of the Court's ideological position on the level of support that it enjoys. In contrast to previous research, we take into account that both the Court's & the public's ideological preferences vary over time. Our analysis indicates that the public's appraisal of the Supreme Court responds not to the Court's ideological position per se, but rather to the extent to which the Court's position diverges from the ideological preferences of the citizenry; when the Court deviates from the public mood, its support erodes. 1 Table, 2 Figures, 1 Appendix, 32 References. Adapted from the source document.