Stratford Douglas

The hazard of starting smoking: Estimates from a split population duration model

Understanding the determinants of the hazard of starting smoking is of great importance in developing policy to reduce the number of smokers. This paper develops a split population duration model of the decision to start smoking. Using data from the 1978 and 1979 Smoking Supplements to the National Health Interview Survey, we find some evidence that lifetime educational attainment, gender, and race are important determinants of both whether and when the smoking habit is initiated. The study finds no evidence that higher cigarette prices would have a significant impact on teenage decisions to pick up the smoking habit.

Depression in Patients with Type 2 Diabetes: Impact on Adherence to Oral Hypoglycemic Agents

Background: Adherence to oral hypoglycemic agents (OHAs) is important for adequate glycemic control and prevention of future complications in patients with type 2 diabetes. Objective: To examine the impact of depression on adherence to OHAs in patients newly diagnosed with type 2 diabetes. Methods: Patients newly diagnosed with type 2 diabetes during a 4 year period were identified from a Medicaid claims database. Presence of preexisting depression was determined on the basis of ICD-9-CM codes. Adherence to OHAs was computed using prescription refill data for a 12 month follow-up period from the date of the index OHA prescription. Two separate adherence indices (Medication Possession Ratio-1 [MPR-1], Medication Possession Ratio-2 [MPR-2]) were computed. The impact of depression on adherence was assessed after controlling for confounders such as demographics, comorbidity, provider interaction, complexity of regimen, and diabetes severity. Results: A total of 1326 newly diagnosed patients with type 2 diabetes were identified (depressed = 471; nondepressed = 855). Results of the study indicated that patients with depression had significantly lower adherence (MPR-1 86%; MPR-2 66%) to OHAs compared with patients without depression (MPR-1 89%; MPR-2 73%). Multivariate results indicated that depression was a significant predictor of adherence, with depressed patients being 3–6% less adherent to OHAs than nondepressed patients, after controlling for confounding factors. Conclusions: Depression significantly impacts adherence to OHAs in patients with type 2 diabetes. The study results imply that depression screening and treatment need to be included in the protocol for management of patients with type 2 diabetes.

Estimating Educational Production Functions with Correction for Drops.

Problems or sample selection in explaining student performance in economics classes are identified, and Heckmans two-step method is used to correct the implied bias in both Cobb-Douglas and translog-type learning functions. The effects of gender and other explanatory variables are then examined.

Estimating Relative Standard of Living in the United States Using Cross‐Migration Data

A new estimator links migration data to a random utility “voting with your feet” model to compare the relative living standards of pairs of regions. It is argued that this estimator has a firmer theoretical basis and uses migration information more efficiently than previous methods. An algorithm converts pairwise comparisons into rankings of the U.S. states for 1970, 1980, and 1990. The rankings indicate living standards were highest in the Northwest (1970, 1980) and the south Atlantic coast (1990). A nonparametric test suggests that the system was in disequilibrium in 1980 (probably due to energy price shocks), but near equilibrium in 1970 and 1990.

‘Voting with your feet’ and the quality of life index: A simple non-parametric approach applied to Canada

Abstract This paper develops a new technique that uses the utility-maximizing migration decisions of rational voters/consumers to construct QOL rankings. We apply our technique to Canadian inter-provincial migration data for 1970–1990.

Coal Mining and the Resource Curse in the Eastern United States

We measure the effect of coal resource sector dependence on long run income growth using the natural experiment of coal mining in 409 U.S. counties that are selected for homogeneity. Using a panel data set (1970-2010), we find a one standard deviation increase in resource dependence is associated with an estimated 0.6 percentage point drop in annual growth rates of per capita personal income. We also measure the extent to which the resource curse operates through disincentives to education, and find significant effects, but results indicate that this education channel explains only perhaps 25% of the curse.

Measuring relative quality of life from a cross-migration regression, with an application to Canadian provinces

We discuss specification of regression models for using migration data to infer the living standards of different regions, and for observing how much of the standard of living is determined by income opportunities versus non-pecuniary amenities. We estimate a regression using Canadian data from 1976-95, which results in rankings of the provinces with respect to overall living standards and amenities, with different rankings for different age groups. We also uncovers some interesting evidence as to the accuracy of the assumption of equilibrium.

Bootstrap confidence intervals in a switching regressions model

Traditional switching regression methods produce slope and intercept estimates conditional on the change point estimate, with confidence intervals that overstate their precision. This paper describes the problem and a bootstrap alternative. Extensive sampling experiments confirm that the traditional methods overstate precision, and that bootstrap confidence intervals are far more accurate.

COAL MINING AND THE RESOURCE CURSE IN THE EASTERN UNITED STATES: COAL MINING AND THE RESOURCE CURSE

We measure the effect of resource‐sector dependence on long‐run income growth using the natural experiment of coal mining in 409 Appalachian counties selected for homogeneity. Using a panel data set (1970–2010), we find a one standard deviation increase in resource dependence is associated with 0.5–1 percentage point long‐run and a 0.2 percentage point short‐run decline in the annual growth rate of per capita personal income. We also measure the extent to which the resource curse operates through disincentives to education, and find significant effects, but this “education channel” explains less than 15 percent of the apparent curse.

A Replication of “The Political Determinants of Federal Expenditure at the State Level” (Public Choice, 2005)

This article replicates and analyzes a study by Hoover and Pecorino (H&P) on federal spending in US states. H&P followed on pathbreaking research by Atlas et al. in which evidence was claimed in favor of the “small state effect”; namely, that since every state is represented by two senators, small states have a disproportionate influence on federal spending relative to their population size. Using H&P’s data, we both replicate their results and demonstrate strong support for the small-state effect when we formally test their predictions. The contribution of this study is that we demonstrate that this empirical support vanishes when we (i) employ cluster robust standard errors rather than conventional ordinary least squares (OLS) standard errors and (ii) include a variable for population growth as suggested in a recent study by Larcinese, Rizzo, and Testa. We conclude that there is insufficient evidence to support the hypothesis of a “small-state effect.”