Small Local Samples Research Articles

Communication-efficient estimation and inference for high-dimensional quantile regression based on smoothed decorrelated score.

Distributed estimation based on different sources of observations has drawn attention in the modern statistical learning. In practice, due to the expensive cost or time-consuming process to collect data in some cases, the sample size on each local site can be small, but the dimension of covariates is large and may be far larger than the sample size on each site. In this article, we focus on the distributed estimation and inference for a preconceived low-dimensional parameter vector in the high-dimensional quantile regression model with small local sample size. Specifically, we consider that the data are inherently distributed and propose two communication-efficient estimators by generalizing the decorrelated score approach to conquer the slow convergence rate of nuisance parameter estimation and adopting the smoothing technique based on multiround algorithms. The risk bounds and limiting distributions of the proposed estimators are given. The finite sample performance of the proposed estimators is studied through simulations and an application to a gene expression dataset is also presented.

Sightings trends and behaviour of manta rays in Fernando de Noronha Archipelago, Brazil

Despite substantial progress in mobulid research over the past decade, knowledge gaps in manta ray ecology and behaviour remain, particularly in the South Atlantic Ocean. Opportunistic photographic and video records of manta rays collected between 2002 and 2019 at Fernando de Noronha Archipelago (FNA) in northeast Brazil provide evidence to support the year-round use of the region by manta rays (believed to be Mobula cf. birostris). From a total of 130 sighting records, manta rays exhibited feeding behaviour in 36.9% (n = 48) of sightings, indicating that the shallow waters surrounding the archipelago are used as feeding grounds. Approximately half of the records (53.8%) corresponded to identified individuals that were re-sighted repeatedly, using the area in different seasons and for several years. Of the compiled records, 69.2% of sightings were of small individuals (≤3 m disc width). All identified males had undeveloped claspers and females had no visible mating scars, suggesting a juvenile population. Despite being limited to a small local sample, here we present the first report of manta rays at FNA and provide preliminary evidence of feeding behaviour by juvenile manta rays in Brazil. This information contributes to our understanding of the regional distribution and habitat use of manta rays in Brazilian waters.

Deeper Spatial Statistical Insights into Small Geographic Area Data Uncertainty.

Small areas refer to small geographic areas, a more literal meaning of the phrase, as well as small domains (e.g., small sub-populations), a more figurative meaning of the phrase. With post-stratification, even with big data, either case can encounter the problem of small local sample sizes, which tend to inflate local uncertainty and undermine otherwise sound statistical analyses. This condition is the opposite of that afflicting statistical significance in the context of big data. These two definitions can also occur jointly, such as during the standardization of data: small geographic units may contain small populations, which in turn have small counts in various age cohorts. Accordingly, big spatial data can become not-so-big spatial data after post-stratification by geography and, for example, by age cohorts. This situation can be ameliorated to some degree by the large volume of and high velocity of big spatial data. However, the variety of any big spatial data may well exacerbate this situation, compromising veracity in terms of bias, noise, and abnormalities in these data. The purpose of this paper is to establish deeper insights into big spatial data with regard to their uncertainty through one of the hallmarks of georeferenced data, namely spatial autocorrelation, coupled with small geographic areas. Impacts of interest concern the nature, degree, and mixture of spatial autocorrelation. The cancer data employed (from Florida for 2001–2010) represent a data category that is beginning to enter the realm of big spatial data; its volume, velocity, and variety are increasing through the widespread use of digital medical records.

Allometric Biomass Models for European Beech and Silver Fir: Testing Approaches to Minimize the Demand for Site-Specific Biomass Observations

In this paper, site-specific allometric biomass models were developed for European beech (Fagus sylvatica L.) and silver fir (Abies alba Mill.) to estimate the aboveground biomass in Șinca virgin forest, Romania. Several approaches to minimize the demand for site-specific observations in allometric biomass model development were also investigated. Developing site-specific allometric biomass models requires new measurements of biomass for a sample of trees from that specific site. Yet, measuring biomass is laborious, time consuming, and requires extensive logistics, especially for very large trees. The allometric biomass models were developed for a wide range of diameters at breast height, D (6–86 cm for European beech and 6–93 cm for silver fir) using a logarithmic transformation approach. Two alternative approaches were applied, i.e., random intercept model (RIM) and a Bayesian model with strong informative priors, to enhance the information of the site-specific sample (of biomass observations) by supplementing with a generic biomass sample. The appropriateness of each model was evaluated based on the aboveground biomass prediction of a 1 ha sample plot in Șinca forest. The results showed that models based on both D and tree height (H) to predict tree aboveground biomass (AGB) were more accurate predictors of AGB and produced plot-level estimates with better precision, than models based on D only. Furthermore, both RIM and Bayesian approach performed similarly well when a small local sample (of seven smallest trees) was used to calibrate the allometric model. Therefore, the generic biomass observations may effectively be combined with a small local sample (of just a few small trees) to calibrate an allometric model to a certain site and to minimize the demand for site-specific biomass measurements. However, special attention should be given to the H-D ratio, since it can affect the allometry and the performance of the reduced local sample approach.

Are Suicide Note Writers Representative of All Suicides? Analysis of the National Violent Death Reporting System.

While suicide notes can offer insights into the causes of suicide and clues for prevention, there is disagreement regarding the degree to which note leavers are representative of the general population of suicides. Previous relevant research on the United States is marked by a series of limitations: small local samples, an over focus on demographic constructs, and lack of multivariable analysis. This study uses a large national sample, a wide range of predictor variables, and multivariable statistical techniques to estimate more reliable similarities and differences between note leavers and other suicides. All data are taken from the National Violent Death Reporting System, which covers 17 states. A total of 9,048 note writers were compared to 21,522 other suicides in terms of 39 variables. In both bivariable (32/39 variables) and multivariable analyses (30/39 variables), note leavers differed from other suicides in most demographic variables, stressful life events, psychiatric issues, and methods of suicide. The national evidence suggests that caution be exercised in generalizing patterns found among writers of suicide notes to suicides in general. This is the first analysis of suicide notes using US data on the issue.

A contribution to the desmid flora of Southeastern Maine1

Abstract Eight peat bogs and wetlands near Steuben, ME were sampled in July 2005 to assess local diversity of freshwater algae. A surprising number of conjugating green algae, especially from the order Desmidiales, was seen even in this small local sample, summing up to 130 species and subspecific taxa. We present an overview of past floristic literature pertaining to desmid species distribution in New England and enrich the current checklist by 65 new records for the state of Maine. Additionally, eight taxa could not be confidently matched to known species, suggesting they may represent heretofore undescribed taxonomic entities. This, coupled with the fact that desmids can serve as water quality indicators, suggests that the desmid diversity in northern New England merits further attention and research.

Assessment of the validity of the English National Health Service Adult In-Patient Survey for use within individual specialties

BackgroundHealthcare improvement requires rigorous measurement. Patient experience is a key healthcare outcome and target for improvement. Its measurement requires psychometrically validated questionnaires. In England, the Adult In-Patient Survey (AIPS), which...

Effectiveness of Bayesian Updating Attributes in Data Transferability Applications

This paper presents the findings from an analysis of several Bayesian updating scenarios in the context of data transferability. Bayesian updating has been recognized as having great potential for use in the transportation field, especially in the simulation of travel demand and other transportation-related data. For local areas where comprehensive data collection is too costly and infeasible, Bayesian updating can be used to synthesize travel demand data in a process generally referred to as data transferability. Bayesian updating has been occasionally employed for transferring travel data; however, various aspects and disadvantages of its use have been insufficiently studied. This work addresses issues about Bayesian updating techniques in data transferability, including a comparison of the use of conjugate and nonconjugate formulations in the updating models, their relative effectiveness, and impacts of the quality of the prior information on final results. The study shows that, in general, updating small local samples of travel attribute data with prior information from national data sources provides an improved estimate of local travel attributes compared with using the local sample only. However, this study found that the inclusion of all available historical data in the prior distributions does not necessarily improve the quality of the updating results. Therefore, careful analysis of the applicability of the prior information to the desired context is necessary when a Bayesian updating formulation is used. The 2001 National Household Travel Survey and the 1995 Nationwide Personal Transportation Survey were used for the demonstration exercises in this study.

From plots to islands: species diversity at different scales

AbstractAim To investigate how plant diversity of whole islands (‘gamma’) is related to alpha and beta diversity patterns among sampling plots within each island, thus exploring aspects of diversity patterns across scales.Location Nineteen islands of the Aegean Sea, Greece.Methods Plant species were recorded at both the whole‐island scale and in small 100 m2 plots on each island. Mean plot species richness was considered as a measure of alpha diversity, and six indices of the ‘variation’‐type beta diversity were also applied. In addition, we partitioned beta diversity into a ‘nestedness’ and a ‘replacement’ component, using the total species richness recorded in all plots of each island as a measure of ‘gamma’ diversity. We also applied 10 species–area models to predict the total observed richness of each island from accumulated plot species richness.Results Mean alpha diversity was not significantly correlated with the overall island species richness or island area. The range of plot species richness for each island was significantly correlated with both overall species richness and area. Alpha diversity was not correlated with most indices of beta diversity. The majority of beta diversity indices were correlated with whole‐island species richness, and this was also true for the ‘replacement’ component of beta diversity. The rational function model provided the best prediction of observed island species richness, with Monod’s and the exponential models following closely. Inaccuracy of predictions was positively correlated with the number of plots and with most indices of beta diversity.Main conclusions Diversity at the broader scale (whole islands) is shaped mainly by variation among small local samples (beta diversity), while local alpha diversity is not a good predictor of species diversity at broader scales. In this system, all results support the crucial role of habitat diversity in determining the species–area relationship.

Multidimensional Predictors of Caregiver Strain among Older Persons Caring for Frail Spouses

Older persons caring for frail and disabled spouses in the community have special needs and concerns. When one spouse is incapacitated, the other spouse--if available and capable--will generally assume the role of primary caregiver (Mui, 1993; Stone, Cafferata, & Sangl, 1987). Even in , the face of their spouse's severe impairments, elderly spouse caregivers continue to provide the t bulk of care required by their disabled partners (Miller, 1990a; Pruchno & Resch, 1989). Spouses account for 36% of all caregivers of frail elderly persons (Stone et al., 1987). Most studies on the impact of caregiving on spouse caregivers have used small local samples with limited generalizability (e.g., Barusch & Spaid, 1989; Borden, 1991; Fitting, Rabins, Lucas, & Eastam, 1986; Pruchno & Resch, 1989; Zarit, Todd, Zarit, 1986). In the present study, the emotional, physical, and financial strain associated with caregiving among spouse caregivers was examined using data-from the 1982-84 National Long-Term Care Channeling Demonstration. The following research questions were studied: (a) Does emotional, physical, and financial strain associated with caregiving differ between wife and husband caregivers, and (b) what are the predictors of each domain of caregiver strain for the two spouse caregiver groups? CONCEPTUAL FRAMEWORK Older husband and wife caregivers seem to respond to the demands of their caregiving role differently because of differences in meaning attributed to caregiving and differences in ways of coping (Borden, 1991; Miller, 1990a). For example, Pruchno and Resch (1989) found that the caregiving burden of wife caregivers was associated with poorer health, less emotional involvement, higher spouse impairment, and more task help. Husband caregivers' sense of burden, however, was not easily explained by these variables, which suggested that husbands and wives may experience the distress of caregiving differently. In addition, compared with husband caregivers, wives have reported higher levels of emotional distress associated with caregiving (Barusch & Spaid, 1989; Fitting et al., 1986; Mui, 1993; Zarit et al., 1986). Gender differences in spouse caregiver strain may be due to differences in the following: meaning associated with the caregiver role, role preparedness, role satisfaction, and role expectations. For example, the caregiving experience of husband caregivers may be qualitatively different from that of wives because men define the context of caregiving differently than women do (Dwyer & Seccombe, 1991; Stoller, 1992). Husbands appear to be very involved in caregiving and, because of other role losses, may perceive caregiving as a meaningful retirement activity (Kaye Applegate, 1990; Stoller, 1990). Miller (1990a) has also suggested that husbands may derive positive feelings from caregiving because being in charge is an extension of men's traditional role of authority. Miller.(1990b) has suggested that researchers use role theory to study gender differences in spouse caregiving. The role theory perspective assumes that adults engage in continuous construction of social realities and that gender differences in caregiving occur because of current role demands. In this study, I have adopted the scarcity hypothesis of role theory (Marks, 1977) as a framework to conceptualize the experience of a caregiver who, along with many other competing role demands, cares for a frail elderly spouse. According to the scarcity hypothesis, caregivers do not have enough resources to adequately fulfill both the caregiving role and other social roles in their lives. This produces a strong tendency toward role strain as a consequence of role demand overload and role conflict (Goode, 1960; Mui, 1992). As prescribed by societal norms, a spouse caregiver typically will take on the caregiving role when the spouse becomes disabled. At the same time, the caregiver may have a variety of other social roles, such as parent, employee, and/or caregiver of another disabled relative, in addition to the caregiving role. …