Semiparametric methods in nonlinear time series analysis: a selective review

Time series analysis is a tremendous research area in statistics and econometrics. In a previous review, the author was able to break down up 15 key areas of research interest in time series analysis. Nonetheless, the aim of the review in this current paper is not to cover a wide range of somewhat unrelated topics on the subject, but the key strategy of the review in this paper is to begin with a core the ‘curse of dimensionality’ in nonparametric time series analysis, and explore further in a metaphorical domino-effect fashion into other closely related areas in semiparametric methods in nonlinear time series analysis.     

Principal weighted logistic regression for sufficient dimension reduction in binary classification

Sufficient dimension reduction (SDR) is a popular supervised machine learning technique that reduces the predictor dimension and facilitates subsequent data analysis in practice. In this article, we propose principal weighted logistic regression (PWLR), an efficient SDR method in binary classification where inverse-regression-based SDR methods often suffer. We first develop linear PWLR for linear SDR and study its asymptotic properties. We then extend it to nonlinear SDR and propose the kernel PWLR. Evaluations with both simulated and real data show the promising performance of the PWLR for SDR in binary classification.     

Poverty affects access to regular source of primary care among the general population in Hong Kong

A territory‐wide two‐stage stratified random sample of 2,282 community‐dwelling Hong Kong adults were surveyed between 2014 and 2015 to investigate the association between poverty and regular source of primary care utilization. Poverty was operationalized by income‐poverty and deprivation. About 94% of our sample reported having regular source of primary care (Western and/or Chinese medical practitioner) and about 69% among them were in private sector. Multivariable logistic regression showed that people who were income‐poor and deprived were less likely to have regular source of primary care (income‐poor: OR = 0.523, p = .027; deprived: OR = 0.488, p = .007) and visit private primary care doctors (income‐poor: OR = 0.445, deprived: OR = 0.222, both p < .0001). Those who had chronic diseases were more likely to have regular source of primary care (multimorbid: OR = 10.709, p < .0001), but less likely to access care in the private sector (one chronic disease: OR = 0.690, p = .019; multimorbid: OR = 0.374, p < .0001) than those without. Further, being older and less skilled were significantly associated with less likelihood of visiting a private doctor. Path analysis showed that the number of chronic diseases had significant indirect effect on having regular source of primary care with being income‐poor and deprived as the mediators (β = ?.0183, p = .0016). Therefore, despite a public health‐care system that aims to deny no one from adequate health care for lack of means, regular source of primary care in Hong Kong is found to be pro‐rich. Future policies should tackle the problem of health‐care inequalities to meet the needs of the underprivileged.     

Welfare Reform and Asset Accumulation: Asset Limit Changes,Financial Assets,and Vehicle Ownership*

Objective. Over the past decade, federal and state governments have substantially liberalized asset limits in welfare. This article examines whether this policy change promotes asset accumulation among the target population of actual and potential welfare recipients. Methods. Utilizing household data from the Panel Study of Income Dynamics as well as state data, this study employs a difference‐in‐difference approach in order to determine whether state asset limits affect the target population's financial and vehicle asset accumulation. This study develops a new policy measure that considers the time period following the adoption of liberalized asset limits. Results. Analysis results suggest that increased asset limits may have successfully encouraged the target population's asset accumulation. The earlier a state raised its asset limit, the more likely welfare recipients were to accumulate financial assets and to possess bank accounts. Conclusion. It is recommended to liberalize asset eligibility rules to promote long‐term economic advancement of poor households.     

Comparing the Survival of Two Groups with an Intermediate Clinical Event

Consider a subject entered on a clinicaltrial in which the major endpoint is a time metric such as deathor time to reach a well defined event. During the observationalperiod the subject may experience an intermediate clinical event.The intermediate clinical event may induce a change in the survivaldistribution. We consider models for the one and two sample problem.The model for the one sample problem enables one to test if theoccurrence of the intermediate event changed the survival distribution.This models provides a way of carrying out non-randomized clinicaltrial to determine if a therapy has benefit. The two sample problemconsiders testing if the probability distributions, with andwithout an intermediate event, are the same. Statistical testsare derived using a semi-Markov or a time dependent mixture model.Simulation studies are carried out to compare these new procedureswith the log rank, stratified log rank and landmark tests. Thenew tests appear to have uniformly greater power than these competitortests. The methods are applied to a randomized clinical trialcarried out by the Aids Clinical Trial Group (ACTG) which comparedlow versus high doses of zidovudine (AZT).     

Households' Perceived Personal Risk and Responses in a Multihazard Environment

This study proposed and tested a multistage model of household response to three hazards—flood, hurricane, and toxic chemical release—in Harris County Texas. The model, which extends Lindell and Perry's (1992, 2004) Protective Action Decision Model, proposed a basic causal chain from hazard proximity through hazard experience and perceived personal risk to expectations of continued residence in the home and adoption of household hazard adjustments. Data from 321 households generally supported the model, but the mediating effects of hazard experience and perceived personal risk were partial rather than complete. In addition, the data suggested that four demographic variables—gender, age, income, and ethnicity—affect the basic causal chain at different points.     

Efficient method for identification of cyclic trends in incidence

Various methods for estimating the parameters of the simple harmonic curve and corresponding statistics for testing the significance of the sinusoidal trend are investigated. The locally reasonable method is almost fully efficient when the size of the trend is very small; however, the maximum likelihood method is preferred generally, especially when the trend is not very small. The log likelihood ratio test is more powerful than the R test which is based on locally reasonable estimates. The efficient method and the log likelihood ratio or equivalent tests are the best statistical techniques for identifying the cyclical trend. Thus they are the methods of choice when adequate computing facilities are available.     

Effects of Surface Material,Ventilation, and Human Behavior on Indirect Contact Transmission Risk of Respiratory Infection

Infectious particles can be deposited on surfaces. Susceptible persons who contacted these contaminated surfaces may transfer the pathogens to their mucous membranes via hands, leading to a risk of respiratory infection. The exposure and infection risk contributed by this transmission route depend on indoor surface material, ventilation, and human behavior. In this study, quantitative infection risk assessments were used to compare the significances of these factors. The risks of three pathogens, influenza A virus, respiratory syncytial virus (RSV), and rhinovirus, in an aircraft cabin and in a hospital ward were assessed. Results showed that reducing the contact rate is relatively more effective than increasing the ventilation rate to lower the infection risk. Nonfabric surface materials were found to be much more favorable in the indirect contact transmission for RSV and rhinovirus than fabric surface materials. In the cases considered in this study, halving the ventilation rate and doubling the hand contact rate to surfaces and the hand contact rate to mucous membranes would increase the risk by 3.7–16.2%, 34.4–94.2%, and 24.1–117.7%, respectively. Contacting contaminated nonfabric surfaces may pose an indirect contact risk up to three orders of magnitude higher than that of contacting contaminated fabric surfaces. These findings provide more consideration for infection control and building environmental design.