Communications inspired linear discriminant analysis

We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label. By harnessing a recent theoretical result on the gradient of mutual information, the above optimization problem can be solved directly using gradient descent, without requiring simplification of the objective function. Theoretical analysis and empirical comparison are made between the proposed method and two closely related methods, and comparisons are also made with a method in which Rényi entropy is used to define the mutual information (in this case the gradient may be computed simply, under a special parameter setting). Relative to these alternative approaches, the proposed method achieves promising results on real datasets. Copyright 2012 by the author(s)/owner(s).

The empirical analysis of cigarette tax avoidance and illicit trade in Vietnam, 1998-2010.

Illicit trade carries the potential to magnify existing tobacco-related health care costs through increased availability of untaxed and inexpensive cigarettes. What is known with respect to the magnitude of illicit trade for Vietnam is produced primarily by the industry, and methodologies are typically opaque. Independent assessment of the illicit cigarette trade in Vietnam is vital to tobacco control policy. This paper measures the magnitude of illicit cigarette trade for Vietnam between 1998 and 2010 using two methods, discrepancies between legitimate domestic cigarette sales and domestic tobacco consumption estimated from surveys, and trade discrepancies as recorded by Vietnam and trade partners. The results indicate that Vietnam likely experienced net smuggling in during the period studied. With the inclusion of adjustments for survey respondent under-reporting, inward illicit trade likely occurred in three of the four years for which surveys were available. Discrepancies in trade records indicate that the value of smuggled cigarettes into Vietnam ranges from $100 million to $300 million between 2000 and 2010 and that these cigarettes primarily originate in Singapore, Hong Kong, Macao, Malaysia, and Australia. Notable differences in trends over time exist between the two methods, but by comparison, the industry estimates consistently place the magnitude of illicit trade at the upper bounds of what this study shows. The unavailability of annual, survey-based estimates of consumption may obscure the true, annual trend over time. Second, as surveys changed over time, estimates relying on them may be inconsistent with one another. Finally, these two methods measure different components of illicit trade, specifically consumption of illicit cigarettes regardless of origin and smuggling of cigarettes into a particular market. However, absent a gold standard, comparisons of different approaches to illicit trade measurement serve efforts to refine and improve measurement approaches and estimates.

Comparing the model-simulated global warming signal to observations using empirical estimates of unforced noise.

The comparison of observed global mean surface air temperature (GMT) change to the mean change simulated by climate models has received much public and scientific attention. For a given global warming signal produced by a climate model ensemble, there exists an envelope of GMT values representing the range of possible unforced states of the climate system (the Envelope of Unforced Noise; EUN). Typically, the EUN is derived from climate models themselves, but climate models might not accurately simulate the correct characteristics of unforced GMT variability. Here, we simulate a new, empirical, EUN that is based on instrumental and reconstructed surface temperature records. We compare the forced GMT signal produced by climate models to observations while noting the range of GMT values provided by the empirical EUN. We find that the empirical EUN is wide enough so that the interdecadal variability in the rate of global warming over the 20(th) century does not necessarily require corresponding variability in the rate-of-increase of the forced signal. The empirical EUN also indicates that the reduced GMT warming over the past decade or so is still consistent with a middle emission scenario's forced signal, but is likely inconsistent with the steepest emission scenario's forced signal.

Empirical measurement of illicit tobacco trade in the Philippines.

Cigarette smuggling reduces the price of cigarettes, thwarts youth access restrictions, reduces government revenue, and undercuts the ability of taxes to reduce consumption. The tobacco industry often opposes increases to tobacco taxes on the claim that greater taxes induce more smuggling. To date, little is known about the magnitude of smuggling in the Philippines. his information is necessary to effectively address illicit trade and to measure the impacts of tax changes and the introduction of secure tax markings on illicit trade. This study employs two gap discrepancy methods to estimate the magnitude of illicit trade in cigarettes for the Philippines between 1994 and 2009. First, domestic consumption is compared with tax-paid sales to measure the consumption of illicit cigarettes. Second, imports recorded by the Philippines are compared with exports to the Philippines by trade partners to measure smuggling. Domestic consumption fell short of tax-paid sales for all survey years. The magnitude of these differences and a comparison with a prevalence survey for 2009 suggest a high level of survey under-reporting of smoking. In the late 1990s and the mid 2000s, the Philippines experienced two sharp declines in trade discrepancies, from a high of $750 million in 1995 to a low of $133.7 million in 2008. Discrepancies composed more than one-third of the domestic market in 1995, but only 10 percent in 2009. Hong Kong, Singapore, and China together account for more than 80 percent of the cumulative discrepancies over the period and 74 percent of the discrepancy in 2009. The presence of large discrepancies supports the need to implement an effective tax marking and tobacco track and trace system to reduce illicit trade and support tax collection. The absence of a relation between tax changes and smuggling suggests that potential increases in the excise tax should not be discouraged by illicit trade. Finally, the identification of specific trade partners as primary sources for illicit trade may facilitate targeted efforts in cooperation with these governments to reduce illicit trade.