Concentration behavior of the penalized least squares estimator

Consider the standard nonparametric regression model and take as estimator the penalized least squares function. In this article, we study the trade‐off between closeness to the true function and complexity penalization of the estimator, where complexity is described by a seminorm on a class of functions. First, we present an exponential concentration inequality revealing the concentration behavior of the trade‐off of the penalized least squares estimator around a nonrandom quantity, where such quantity depends on the problem under consideration. Then, under some conditions and for the proper choice of the tuning parameter, we obtain bounds for this nonrandom quantity. We illustrate our results with some examples that include the smoothing splines estimator.     

Do special issues offer something special? An overview of research trends in Telecommunications Policy special issues

This study explores the value of special issues by analyzing the characteristics of special issues of Telecommunications Policy (TP). Specifically, this study examines the status of special issue publications, the characteristics of their articles compared with those of general issues, and the factors affecting article citations. For the analysis, all information on TP articles published from 1976 to 2018 was collected from the Scopus database. A comparative analysis as well as a negative binomial regression were conducted on papers published after 1994, when the first special issue was published. The results show that special issues are distinguished from general issues by various characteristics, such as multinational author collaboration, number of references, keywords, and funding. While general issue papers are more frequently cited in academia, special issue papers show better performance in terms of online captures and social media sharing. Moreover, the smaller number of variables affects the frequency of citations in the case of special issues, revealing that content and format are more influential than author factors.     

Monetary policy and food inflation in South Africa: A quantile regression analysis

Although optimal monetary policy stabilizes food inflation theoretically, empirical studies remain limited not only in the context of volumes and the estimation approaches, but are focused on selected advanced and emerging countries to the neglect of Africa where poverty and dominance of food in the consumption basket are more pronounced. We provide empirical evidence in the context of South Africa using quantile regressions. Rising food prices are destabilized even further by restrictive monetary policy; a finding that has ramifications for inflation targeting, especially given that a quarter of the country’s population is food poor.     

Who benefits from partial tax coordination?

In this paper, we investigate whether partial tax coordination is beneficial to countries within and outside a tax union, in which countries are supposed to compete in taxes and infrastructure. Our results demonstrate that a subgroup of countries agreeing on a common tax rate can harm both member and nonmember states. This is in contrast to the classical findings that partial tax harmonisation is Pareto improving. When a minimum tax rate is imposed within a tax union, we demonstrate that it does not necessarily improve the welfare of the member countries. Moreover, both the high‐tax and low‐tax countries can be worse off. This conclusion is at odds with the classical result that a high‐tax country benefits from the imposition of a lower tax bound.     

A multivariate distance nonlinear causality test based on partial distance correlation: a machine learning application to energy futures

This paper proposes a multivariate distance nonlinear causality test (MDNC) using the partial distance correlation in a time series framework. Partial distance correlation as an extension of the Brownian distance correlation calculates the distance correlation between random vectors X and Y controlling for a random vector Z. Our test can detect nonlinear lagged relationships between time series, and when integrated with machine learning methods it can improve the forecasting power. We apply our method as a feature selection procedure and combine it with the support vector machine and random forests algorithms to study the forecast of the main energy financial time series (oil, coal, and natural gas futures). It shows substantial improvement in forecasting the fuel energy time series in comparison to the classical Granger causality method in time series.     

Reconciling Alternative Theories for the Safety of Owner–Operators

Motor carrier safety is an important concern of shippers, carriers, policy makers, consignees, insurance providers, and the motoring public. One aspect of carrier safety that has garnered substantial attention is whether carriers making greater use of owner–operators are more or less safe vis‐à‐vis carriers making greater use of employee drivers. Currently, conflicting theoretical predictions exist regarding the direction of this relationship. In this article, we offer a reconciliation of the alternative theoretical predictions by developing a coherent theory that merges sociological rational choice theory and theory regarding motor carrier safety. We subject our theory to empirical testing by fitting a series of seemingly unrelated regression models to a vector of safety measures tracked as part of the Federal Motor Carrier Safety Administration's Compliance, Safety, and Accountability program. Our results are consistent with our proposed theory of owner—operator safety and provide meaningful theoretical and managerial implications and directions for future research.     

Labor market analysis through transformations and robust multivariate models

The work presents a robust approach to labor share analysis. The estimate of labor share presents various complexities related to the nature of the data sets to be analyzed. Typically, labor share is evaluated by using discriminant analysis and linear or generalized linear models, that do not take into account the presence of possible outliers. Moreover, the variables to be considered are often characterized by a high dimensional structure. The proposed approach has the objective of improving the estimation of the model using robust multivariate regression techniques and data transformation.     

Aggregate Dividend Behavior and Permanent Earnings Hypothesis

The study examines the aggregate dividend behavior of U.S. corporations based on the permanent earnings hypothesis. Using annual data of aggregate earnings and dividends from 1871–1993, I find that although managers change dividends proportional to permanent earnings changes, they make revisions with a larger percentage change in dividends than in permanent earnings. The results from the post‐war data show that firms follow a partial adjustment policy with a long‐term dividend payout target in mind and make revisions with a delay. The quarterly data analysis yields results similar to those of the post‐war annual data.     

Estimating the Size of a Criminal Population from Police Records Using the Truncated Poisson Regression Model

The truncated Poisson regression model is used to arrive at point and interval estimates of the size of two offender populations, i.e. drunk drivers and persons who illegally possess firearms. The dependent capture–recapture variables are constructed from Dutch police records and are counts of individual arrests for both violations. The population size estimates are derived assuming that each count is a realization of a Poisson distribution, and that the Poisson parameters are related to covariates through the truncated Poisson regression model. These assumptions are discussed in detail, and the tenability of the second assumption is assessed by evaluating the marginal residuals and performing tests on overdispersion. For the firearms example, the second assumption seems to hold well, but for the drunk drivers example there is some overdispersion. It is concluded that the method is useful, provided it is used with care.