Do worker absences affect productivity? The case of teachers

This article studies the impact of teacher absences on education. Using data spanning three academic years about 285 teachers and 8,631 predominantly economically disadvantaged students from a United States urban school district, it tests assumptions that a substantial portion of teachers' absences is discretionary and that these absences reduce productivity – students' mathematics scores. Since absent teachers are typically replaced by less qualified substitutes, instructional intensity and consistency may decline: ten days of teacher absence reduce students' achievement score by about 3.3 per cent of a standard deviation – enough to lower some students' designation in the state proficiency system and, thus, their motivation to succeed.     

The foundations of econometrics-are there any

The conclusions of alogically consistent economic theory which strictly adheres to Aristotle's axioms of logic are factually true if its sufficient conditions are all factually true. Alternatively, if a conclusion of such a theory is false, then at- least one of its assumptions is false. Unfortunately, the factual truth of sufficient conditions cannot be established because the problem of induction i s impossible t o solve. It is algo true that the falsity of a conclusion cannot be established in the presence of uncertainty. While the philosophy of instrumentalism applied to sufficient and logically consistent explanations may provide useful solutions to immediate practical problems, the principles of simplicity, parsimony and profligacy--all of them requiring conditional deductive arguments--are useless as criteria for model choice.     

Retracted and replaced: Sodium cromoglicate: an ineffective drug or meta‐analysis misused?

The following article from Pharmaceutical Statistics, Sodium cromoglicate: an ineffective drug or meta‐analysis misused? by M. T. Stevens, A. M. Edwards, J. B. L. Howell published online on 15 March 2007 in Wiley InterScience ( www.interscience.wiley.com ), has been retracted by agreement between the author, the journal Editor in Chief, Steven Julious, and John Wiley & Sons, Ltd. The retraction has been agreed because the article is not yet ready for publication and an early version without revisions was published in error. Replacement article pending. Copyright © 2007 John Wiley & Sons, Ltd.     

A Longitudinal Study of Depressive Symptoms and Marijuana Use in a Sample of Inner‐City African Americans

The association between marijuana use and depressive symptoms was examined longitudinally in a sample of 622 African American youth, interviewed on six occasions, using hierarchical linear modeling (HLM). We considered whether depressive symptoms predicted changes in marijuana use and vice versa from high school through the transition into young adulthood. We also examined gender differences in these behaviors over time. The results indicated that depressive symptoms predicted later marijuana use only for males. Marijuana use did not predict later depressive symptoms for females or males. These findings are consistent with a unidirectional hypothesis indicating that marijuana use may play a role as mood regulator among young males, but not among females. Research findings also indicate that females with lower depressive symptoms use more marijuana than females who report high depressive symptoms. These findings did not change even after controlling for the effects of using other substances at previous stages, school achievement, and demographics factors. These results suggest that depressive symptoms may be an antecedent of marijuana use among African American males.     

Can Trade Help Poor People? The Role of Trade,Trade Policy and Market Access in Tanzania

Many development economists prescribe trade as a poverty‐reducing formula. But how is this elixir supposed to work? This article contributes to the lively debate on this topic with household evidence from Tanzania — a poor country even within sub‐Saharan Africa, the poorest region. About 81% of the poor work in agriculture, which accounts for 88% of the export bundle. The article describes existing poverty and then evaluates the poverty‐reduction potential of trade, trade policy and market access. The article extends the analysis by simulating tariff changes and four switching scenarios that swap some poor households into trade‐related sectors, such as cash cropping or tourism, to project national poverty reductions of up to 5.6% and household income increases of up to 21.5%.     

Feature significance in generalized additive models

This paper develops inference for the significance of features such as peaks and valleys observed in additive modeling through an extension of the SiZer-type methodology of Chaudhuri and Marron (1999) and Godtliebsen et al. (2002, 2004) to the case where the outcome is discrete. We consider the problem of determining the significance of features such as peaks or valleys in observed covariate effects both for the case of additive modeling where the main predictor of interest is univariate as well as the problem of studying the significance of features such as peaks, inclines, ridges and valleys when the main predictor of interest is geographical location. We work with low rank radial spline smoothers to allow to the handling of sparse designs and large sample sizes. Reducing the problem to a Generalised Linear Mixed Model (GLMM) framework enables derivation of simulation-based critical value approximations and guards against the problem of multiple inferences over a range of predictor values. Such a reduction also allows for easy adjustment for confounders including those which have an unknown or complex effect on the outcome. A simulation study indicates that our method has satisfactory power. Finally, we illustrate our methodology on several data sets.