Suchergebnisse

AbstractMany purposes can be served by using multiple dependent variables in a study, and the application of path analysis to multiple measures can increase both conceptual and statistical power.

Decision analysts use sensitivity analysis to identify influential variables, to determine which input variables to model stochastically, and to characterize scenarios that could affect a change in the rank ordering of the alternatives. A frequently recommended sensitivity analysis technique is "one‐way" sensitivity analysis, which determines a variable's influence by the degree to which the objective function changes as that variable is varied while all other variables are held fixed. Disadvantages of one‐way analysis are that it measures the influence of only one variable at a time and it assumes independence among the input variables. Clearly, however, there are situations when dependencies exist among the input variables that could possibly affect the sensitivity analysis results. This research develops a strategy that incorporates dependence relations among the input variables into the sensitivity analysis using rank correlations. Only decision problems with a finite number of alternatives and continuous state variables are considered.

Um die strukturellen Beziehungen zwischen mehreren Größen aufdecken oder entsprechende Hypothesen testen zu können, bedarf es multivariater Analysemethoden, mit denen man eine Vielzahl von Variablen unter Berücksichtigung von (zufälligen) Fehlereinflüssen bzw. Störgrößen simultan betrachten kann. Eine Gruppe von Modellen, die speziell auf die Analyse qualitativer abhängiger Variablen zugeschnitten sind, wird in dem Beitrag vorgestellt. Dabei handelt es sich um Regressionsmodelle, mit denen sich mehrdimensionale Kontingenztabellen analysieren lassen. (pmb)

Empirical analyses of deterrence have paid insufficient attention to the validity and reliability of the data used to test the central propositions of theories of deterrence. This article examines two prominent studies of immediate extended deterrence that do not deal adequately with the problems inherent in constructing a valid data set for quantitative analysis. The problems are particularly acute in the testing of theories of deterrence because of the difficulties in identifying cases of deterrence success and of inferring the intentions of would-be challengers. Our analysis explores these problems and suggests ways of testing theories of deterrence that can reduce the threats to valid inference.

Examines two prominent studies and suggests improved ways of testing theories of deterrence.

A method is suggested for determining the direction of influence between two variables in the absence of any basis for specifying the time sequence of their occurence. The method is a special application of Lazarsfeld's scheme for testing the validity of interpretations by means of cross-tabulations, & requires only that the two variables in question have a common antecedent variable. If each of the 2 variables is held constant, while comparing the other one with the common antecedent variable, the independent variable will be the one in which the partial r's tend to diminish or disappear. Conversely, when the partial r's persist or increase in magnitude, the variable being controlled is then seen as that of the 2 which is dependent. The method is exemplified in terms of 2 variables: R's self-image of his age status, & R's notion of significant others' view of his age status. Both of these are related to an antecedent variable, age, & on the basis of the method described it can be determined that of the 2, self-image is independent & conception of others' views is a dependent variable. K. Geiger.

AbstractA distinction between diplomacy as independent variable, impacting upon other developments, and diplomacy as dependent variable, adapting to other causes, is employed to underpin focused case analysis of negotiation between states. To dramatize diplomacy as dependent variable, it is hypothesized that allies with convergent interests would find negotiations between themselves more difficult when domestic constraints such as political ideology and pressure group activity intrude. To highlight diplomacy as independent variable, it is hypothesized that adversaries with divergent interests employ diplomatic statecraft to reduce the chances of war in periods of confrontation. Using a relatively small case sample, this study confirms these hypotheses, but reveals similarities as well as differences between the case categories. It is argued that the focused case approach is a fruitful way to yield much-needed generalizations about diplomatic statecraft.

Many political science research articles that use limited dependent variable models report estimated quantities, in particular, fitted probabilities, predicted probabilities, and functions of such probabilities, without indicating that such estimates are subject to uncertainty. This practice, along with the reporting of "percentage correctly predicted," can overstate the precision of reported results. In light of this, the present article describes a variety of measures of uncertainty that authors can include alongside estimates generated by limited dependent variable models. It also proposes an alternative to "percentage correctly predicted" and illustrates its calculations with congressional cosponsorship data from Krehbiel (1995).