Journal of Economic and Social Measurement

Timely estimates of employment in nonprofit organizations can be created by matching information collected directly from the sector to other databases. Coverage of employment reported by nonprofit entities is established for 2003 by matching IRS Forms 990/990-EZ and a Registry of nonprofits to the BLS Quarterly Census of Employment and Wages (QCEW). The match reveals nonresponse and match errors that are overcome by imputation, editing, and modeling. Estimates of employment in nonprofit charitable organizations are substantially larger than prior reports. As many nonprofits and some nonprofit employees are excluded from the QCEW universe, an alternative approach to estimating employment would match the Form 990/990-EZ and the Registry to IRS Forms 941 and W-2. This alternative became available in 2005 and may be more timely and complete than the QCEW match.

Both demographers and economists evaluate the accuracy of their respective forecasts with measures like mean square error, root mean square error, mean absolute percent error, and mean algebraic percent error. However, demographers tend to approach the issue of forecasting very differently than do economists. Two of the distinctive features of the demographic tradition are the use of the cohort-component method (instead of time-series models) and an emphasis on cross-sectional forecasts (instead of forecasts aggregated over time). From the perspective of this demographic tradition, we examine "MAPE-R" (Mean Absolute Percent Error-Rescaled), a recently developed measure of accuracy designed to overcome shortcomings noted in "MAPE" (Mean Absolute Percent Error), a measure commonly used to evaluate the accuracy of population estimates and forecasts. We show that MAPE-R can be calculated simply, thus overcoming the cumbersome calculation procedure used in its introduction and noted as a feature needing correction. We find this closed form expression for MAPE-R to be a member of the family of power mean-based accuracy measures. This enables it to be placed in relation to other members of this family, which includes HMAPE (Harmonic Mean Absolute Percent Error), GMAPE (Geometric Mean Absolute Percent Error), and MAPE. Given that MAPE-R was designed to be robust in the face of outliers, it is not surprising to find that it is a valid estimator of the median of the distribution(s) generating the absolute percent errors. Simulation studies suggest that MAPE-R is a far more efficient estimator of this median than MEDAPE(Median Absolute Percent Error). Because the Box-Cox transformation on which MAPE-R depends is known to be unstable, we suggest that this represents a line of further research into GMAPE, which, like MAPE-R, is subject neither to the shortcomings observed for MAPE nor to the instability of the Box-Cox transformation. While further lines of research are called for, nothing in our examination of MAPE-R here rules out its use. It also meets the National Research Council's major criteria as a summary measure of accuracy. It is subject to some cautions, but these are no more restrictive than those affecting other accuracy measures, many of which are widely used and have been for some years.

This study provides a summary of the capacity of the Medical Expenditure Panel Survey (MEPS) to produce national estimates of the continuously uninsured population over a four year time frame and the adopted estimation strategy. The paper reports on the employed methodology that permits more accurate estimates of the long term uninsured than heretofore derived. This is accomplished through the linkage of the survey to the National Health Interview Survey, allowing for a reconciliation of insurance coverage responses covering overlapping time periods. The production of national estimates of the long term uninsured for a four year interval is a new MEPS output, and this study identifies the characteristics of the uninsured. The utility of this information to improve behavioral models of health care expenditure patterns is also described.

This paper reports on a failed attempt to replicate work by Son (2004) on the measurement of the pro-poorness of growth. Son promotes a new "poverty growth curve" methodology for measuring the pro-poorness of growth, in part because of its ability to conclusively categorize 82% of the growth spells she examines as either unambiguously pro-poor, not pro-poor, or immiserizing, regardless of the chosen poverty level. Further analysis of her original data set reveals numerous errors in the classifications of the growth spells, such that the proposed methodology can only conclusively categorize the pro-poorness of 62% of the growth spells examined. This brings into question Son's assertions that her method is "powerful" and "conclusive". The poverty growth curve method is nevertheless found to have a high degree of conclusive results when it is extended to measure separately the impacts of growth on poverty and on income inequality, something that Son does not test, and yet which can still be of interest to development economists.