Naihua Duan

A Comparison of Alternative Models for the Demand for Medical Care

We have tested alternative models of the demand for medical care using experimental data. The estimated response of demand to insurance plan is sensitive to the model used. We therefore use a split-sample analysis and find that a model that more closely approximates distributional assumptions and uses a nonparametric retransformation factor performs better in terms of mean squared forecast error. Simpler models are inferior either because they are not robust to outliers (e.g., ANOVA, ANOCOVA), or because they are inconsistent when strong distributional assumptions are violated (e.g., a two-parameter Box-Cox transformation).

Monte Carlo evidence on the choice between sample selection and two-part models

Abstract This Monte Carlo study examines the relative performance of sample selection and two-part models for data with a cluster at zero. The data are drawn from a bivariate normal distribution with a positive correlation. The alternative estimators are examined in terms of means squared error, mean bias and pointwise bias. The sample selection estimators include LIML and FIML. The two-part estimators include a naive (the true specification, omitting the correlation coefficient) and a data-analytic (testimator) variant. In the absence of exclusion restrictions, the two-part models are no worse, and often appreciably better than selection models in terms of mean behavior, but can behave poorly for extreme values of the independent variable. LIML had the worst performance of all four models. Empirically, selection effects are difficult to distinguish from a non-linear (e.g., quadratic) response. With exclusion restrictions, simple selection models were significantly better behaved than a naive two-part model over subranges of the data, but were negligibly better than the data-analytic version.

Choosing Between the Sample-Selection Model and the Multi-Part Model

Hay and Olsen (1984) incorrectly argue that a multi-part model, the two-part model used in Duan et al. (1982,1983), is nested within the sample-selection model. Their proof relies on an unmentioned restrictive assumption that cannot be satisfied. We provide a counterexample to show that the propensity to use medical care and the level of expense can be positively associated in the two-part model, contrary to their assertion. The conditional specification in the multi-part model is preferable to the unconditional specification in the selection model for modeling actual (v. potential) outcomes. The selection model also has poor statistical and numerical properties and relies on untestable assumptions. Empirically the multi-part estimators perform as well as or better than the sample selection estimator for the data set analyzed in Duan et al. (1982, 1983).

An English and Spanish Pediatric Asthma Symptom Scale

BACKGROUNDnPediatric asthma survey measures have not been adequately tested in non-English-speaking populations.nnnOBJECTIVESnTo test the reliability and validity of an English and Spanish symptom scale to measure asthma control in children.nnnSUBJECTSnParents (54% Spanish-speaking; 61% not high school graduates) of 234 children seen in the emergency department for an asthma exacerbation.nnnMEASURESnParent report of frequency and perceived severity of child asthma symptoms during the beginning and after resolution of the exacerbation.nnnRESULTSnAn 8-item scale composed of reports of cough, wheezing, shortness of breath, asthma attacks, chest pain, night symptoms, and overall perceived severity had very good psychometric properties in both English and Spanish. The reliability (Cronbachs alpha) of the scale ranged from 0.81 to 0.87 for both languages and time frames. In both languages, the validity of the scale was supported by responsiveness to changes in clinical status (lower symptom score after resolution of the exacerbation, P < 0.001) and by moderate to strong correlations (P < 0.001) with other asthma morbidity measures (parent report of child bother: r = 0.59-0.65; school days lost: r = 0.38-0.67; and activity days lost: r = 0.41-0.59). There were no statistically significant differences in the reliability or construct validity of the summary symptom scale by language, although Spanish speakers reported a lower frequency of some symptoms than did English speakers.nnnCONCLUSIONSnA reliable and valid 8-item scale can be used to measure control of asthma symptoms in Spanish-speaking populations of low literacy. Additional research to evaluate language equivalency of asthma measures is necessary.

The Findings of the Rand Health Insurance Experiment??? A Response to Welch et al

penditures and hospitalization between health insurance plans claimed by Rand have, in fact, been shown. Fortunately, it is easy to demonstrate that these differences exist without becoming mired in a morass of detail. The simplest possible data-per-person use and expenditure in the various insurance plans-provide overwhelming evidence that the differences among plans that we have elsewhere described are real and substantial (Tables 1 and 2).-10 In general, we can reject the null hypotheses that there are no differences in use and expenditure with extremely high confidence; in three of the measures the chances are less than one in a trillion that