Band-limited component estimation in time-limited economic series

This paper tackles the issue of economic time-series modeling from a joint time and frequency-domain standpoint, with the objective of estimating the latent trend-cycle component. Since time-series records are data strings over a finite time span, they read as samples of contiguous data drawn from realizations of stochastic processes aligned with the time arrow. This accounts for the interpretation of time series as time-limited signals. Economic time series (up to a disturbance term) result from latent components known as trend, cycle, and seasonality, whose generating stochastic processes are harmonizable on a finite average-power argument. In addition, since trend is associated with long-run regular movements, and cycle with medium-term economic fluctuation, both of these turn out to be band-limited components. Recognizing such a frequency-domain location permits a filter-based approach to component estimation. This is accomplished through a Toeplitz matrix operator with sinc functions as entries, mirroring the ideal low-pass filter impulse response. The notion of virtual transfer function is developed and its closed-form expression derived in order to evaluate the filter features. The paper is completed by applying this filter to quarterly data from Italian industrial production, thus shedding light on the performance of the estimation procedure.     

Using activity sensitivity and network topology information to monitor project time performance

The interest in activity sensitivity from both the academics and the practitioners lies in the need to focus a project manager's attention on those activities that influence the performance of the project. When management has a certain feeling of the relative sensitivity of the various parts (activities) on the project objective, a better management's focus and a more accurate response during project tracking should positively contribute to the overall performance of the project.     

An Assessment of the Psychometric Properties of Italian Version of CPGI

The aim of this study was to adapt to the Italian context a very commonly used international instrument to detect problem gambling, the canadian problem gambling index (CPGI), and assess its psychometric properties. Cross-cultural adaptation of CPGI was performed in several steps and the questionnaire was administered as a survey among Italian general population (n = 5,292). Cronbach’s alpha reliability coefficient was 0.87 and can be considered to be highly reliable. Construct validity was assessed first by means of a principal component analysis and then by means of confirmatory factor analysis, showing that only one factor, problem gambling, was extracted from the CPGI questionnaire (an eigenvalues of 4,684 with percentage of variance 52 %). As far as convergent validity is concerned, CPGI was compared with Lie/Bet questionnaire, a two-item screening tool for detecting problem gamblers, and with both depression and stress scales. A short form DSM-IV CIDI questionnaire was used for depression and VRS scale, a rating scale, was used for rapid stress evaluation. A strong convergent validity with these instruments was found and these findings are consistent with past research on problem gambling, where another way to confirm the validity is to determine the extent to which it correlates with other qualities or measures known to be directly related to problem gambling. In sum, despite the lack of a direct comparison with a classic gold-standard such as DSM-IV, the Italian version of CPGI exhibits good psychometric properties and can be used among the Italian general population to identify at-risk problem gamblers.     

First-passage densities of controlled Gaussian processes

Whittle has proved a theorem that gives the optimal control of Gaussian processes in terms of the mathematical expectation of a function of the time and the place where the uncontrolled processes hit the boundary of the stopping region for the first time. In this paper we obtain formulae for the joint probability density function of the first hitting time and place and, in the time-invariant case, for the moment generating function of the first exit time of the optimally controlled processes. Two particular one-dimensional cases are considered.     

Bayesian dynamic network actor models with application to South Korean COVID-19 patient movement data

Statistical Methods & Applications - Motivated by the ongoing COVID-19 pandemic, this article introduces Bayesian dynamic network actor models for the analysis of infected individuals’...     

Nondifferentiable errors in beta-compliance integrated logistic models

In a classical measurement error model, true regressors. though unknown, vary stochastically around the true level. In inhalation toxicology, environmental epidemiology. and some other problems, the administered dose mav not be completely absorbed into the system, resulting, in a stochastic compliance where the actual dose intake is smaller in magnitude, so the classical measurement error models may not be tenable. We introduce some logistic models tor stochastic compliance of various types incorporating a Btfn compliance distribution The^e compliance-adjusted models are categorized into t hree types: (i) i.ow (or near zero) dose levels, (ii) moderate dose levels, and (iii) high dose levels, resulting in difTeient forms. The buul-T uin method is incorporated to draw statistical conclusions based on BAN estimatois.