Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: Propensity score matching provides an estimate of the effect of a “treatment” variable on an outcome variable that is largely free of bias arising from an association between treatment status and observable variables. However, matching methods are not robust against “hidden bias” arising from unobserved variables that simultaneously affect assignment to treatment and the outcome variable. One strategy for addressing this problem is the Rosenbaum bounds approach, which allows the analyst to determine how strongly an unmeasured confounding variable must affect selection into treatment in order to undermine the conclusions about causal effects from a matching analysis. Instrumental variables (IV) estimation provides an alternative strategy for the estimation of causal effects, but the method typically reduces the precision of the estimate and has an additional source of uncertainty that derives from the untestable nature of the assumptions of the IV approach. A method of assessing this additional uncertainty is proposed so that the total uncertainty of the IV approach can be compared with the Rosenbaum bounds approach to uncertainty using matching methods. Because the approaches rely on different information and different assumptions, they provide complementary information about causal relationships. The approach is illustrated via an analysis of the impact of unemployment insurance on the timing of reemployment, the post-unemployment wage, and the probability of relocation, using data from several panels of the Survey of Income and Program Participation (SIPP).

Publication Type: Conference Paper/Unpublished Manuscript
Abstract: This project will examine the use of words of estimative probability (WEP) in National Intelligence Estimates (NIE) for the past 50 years. NIE’s deal with capabilities, vulnerabilities, and probable courses of action of foreign nations and key developments relative to the vital interests of the United States. The study aims to determine whether there is a disparity in the use of WEP’s during times of peace and crisis. Sherman Kent, a pioneer in intelligence analysis methods during WWII, attempted to quantify the qualitative judgments used by intelligence analysts and therefore created a list of WEP’s expressing percentages. These original words in order of descending certainty include almost certain, probable, chances about even, probably not, almost certainly not, and impossibility. He later added a number of synonyms for each of the five orders of probability. This study will use Hermetic Word Frequency Software to examine the NIE’s by analyzing a text file and creating a ranked list of these words. Individual word list files will eventually produce a master list which will allow analysis of word trends by parameters that include year, decade, specific crisis, etc.

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: Many states are conducting surveys to estimate rates of uninsurance, as well as to examine the characteristics of their uninsured populations. Yet, state generated estimates are likely to differ from the annual estimates of uninsurance rates based on the Census Bureau’s Current Population Survey (CPS). In our analyses from seven states using a similar instrument we show that the state surveys conducted produced anywhere from 15 percent to 50 percent lower uninsruance estimates than the CPS. Because the CPS estimates are widely cited by the media and in the health policy literature, they can create potential confusion when states use their own survey data for policy development. Our paper examines key reasons for the differences and discusses their relevance for state health policy. We focus on sample design, weighting adjustments for non-coverage, survey administration, definitions of the uninsured, survey design, and imputation/editing procedures. Although we are able to explain portions of the differences between the CPS and state survey estimates there is still several outstanding issues for both the CPS and state surveys.

Publication Type: Conference Paper/Unpublished Manuscript
Abstract: Party effects on legislative behavior are difficult to isolate due to multiple forms of party influence and non-party influences on legislators.

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: In this paper a parametric framework for estimation and
inference in cointegrated panel data models is considered that is
based on a cointegrated VAR(p) model. A convenient two-step
estimator is suggested where in the first step all individual
specific parameters are estimated and in the second step the
long-run parameters are estimated from a pooled least-squares
regression. The two-step estimator and related test procedures can
easily be modified to account for contemporaneously correlated
errors, a feature that is often encountered in multi-country
studies. Monte Carlo simulations suggest that the two-step
estimator and related test procedures outperform semiparametric
alternatives such as the fully modified OLS (FMOLS) approach,
especially if the number of time periods is small.