Search

Purpose: There has been increased interest in using telepractice for involving more diverse children in research and clinical services, as well as when in-person assessment is challenging, such as during COVID-19. Little is known, however, about the feasibility, reliability, and validity of language samples when conducted via telepractice. Method: Child language samples from parent-child play were recorded either in person in the laboratory or via video chat at home, using parents' preferred commercially available software on their own device. Samples were transcribed and analyzed using Systematic Analysis of Language Transcripts software. Analyses compared measures between-subjects for 46 dyads who completed video chat language samples versus 16 who completed in-person samples; within-subjects analyses were conducted for a subset of 13 dyads who completed both types. Groups did not differ significantly on child age, sex, or socioeconomic status. Results: The number of usable samples and percent of utterances with intelligible audio signal did not differ significantly for in-person versus video chat language samples. Child speech and language characteristics (including mean length of utterance, type-token ratio, number of different words, grammatical errors/omissions, and child speech intelligibility) did not differ significantly between in-person and video chat methods. This was the case for between-group analyses and within-child comparisons. Furthermore, transcription reliability (conducted on a subset of samples) was high and did not differ between in-person and video chat methods. Conclusions: This study demonstrates that child language samples collected via video chat are largely comparable to in-person samples in terms of key speech and language measures. Best practices for maximizing data quality for using video chat language samples are provided., Language sampling is a common assessment tool speech-language pathologists (SLPs) and researchers use to evaluate children's spontaneous, expressive language (Costanza-Smith, 2010; Hux et al., 1993). Language samples are often elicited [...]

We introduce and analyze a framework and corresponding method for compressed sensing in infinite dimensions. This extends the existing theory from finite-dimensional vector spaces to the case of separable Hilbert spaces. We explain why such a new theory is necessary by demonstrating that existing finite-dimensional techniques are ill suited for solving a number of key problems. This work stems from recent developments in generalized sampling theorems for classical (Nyquist rate) sampling that allows for reconstructions in arbitrary bases. A conclusion of this paper is that one can extend these ideas to allow for significant subsampling of sparse or compressible signals. Central to this work is the introduction of two novel concepts in sampling theory, the stable sampling rate and the balancing property, which specify how to appropriately discretize an infinite-dimensional problem., Author(s): Ben Adcock[sup.1] , Anders C. Hansen[sup.2] Author Affiliations: (1) Department of Mathematics, Simon Fraser University, V5A 1S6, Burnaby, BCCanada (2) DAMTP, Centre for Mathematical Sciences, University of Cambridge, Wilberforce [...]

Characterizations of conifer crown biomass are important for assessing forest fuel loadings, bioenergy supplies, carbon stocks, and growth and yield. There is considerable variation in conifer crown mass, but to guide sampling programs, there is little quantitative information available concerning its structure or extent. This research examines several randomized branch sampling (RBS) strategies adapted for excurrent crown forms, as well as the impact of allometric relationships on their precision. The RBS strategies differ in terms of how primary branches (those attached directly to the bole) are aggregated into selection nodes and are evaluated using destructively sampled Douglas-fir (Pseudotsuga menziesii (Mirb.) Franco) and western larch (Larix occidentals Nutt.) trees. Strong linear relationships between branch mass and basal area improve the precision of RBS relative to simple random sampling. Yet because the sample trees exhibited area- increasing branching patterns, the RBS strategies could not achieve the same precision as two-pass probability proportional-to-size methods. For the same reason, aggregation of branches improved the precision of RBS. For practical reasons, we recommend aggregating branches by 1 m intervals along the stem. This strategy brought the relative standard errors for crown mass below 20% with sample sizes of four to eight branches, with smaller sample sizes yielding this result for more slender trees. We also report results on the variability of branch area and mass, as well as results that recommend against the practice of allocating equal numbers of sample branches to crown strata of equal length. Key words: randomized branch sampling, crown biomass, crown allometry, excurrent crown form, unequal probability sampling. Il est important de bien caracteriser la biomasse de la cime des coniferes pour evaluer la charge de combustibles, les reserves d' energie, les stocks de carbone ainsi que la croissance et la production dans les forets. La masse de la cime des coniferes varie considerablement mais il y a peu d' information quantitative disponible au sujet de la structure et de l' etendue de cette variation pour orienter les programmes d' echantillonnage. Cette etude examine plusieurs strategies d' echantillonnage aleatoire des branches (EAB) adaptees aux cimes de forme conique ainsi que l' impact des relations allometriques sur leur precision. Les strategies d'EAB different quant a la facon dont les branches primaires inferieures (celles qui partent directement du tronc) sont regroupees en noeuds de selection et sont evaluees par un echantillonnage destructif de tiges de douglas de Menzies (Pseudotsuga menziesii (Mirb.) Franco) et de meleze occidental (Larix occidentals Nutt.). D'etroites relations lineaires entre la masse des branches et la surface terriere ameliorent la precision de l' EAB comparativement a l' echantillonnage aleatoire simple. Par contre, parce que les arbres echantillonnes presentaient des patrons de branchement a surface croissante, les strategies d'EAB ne pouvaient pas fournir la meme precision que les methodes a double passage avec des probabilites proportionnelles a la taille. Pour la meme raison, le regroupement des branches a ameliore la precision de l' EAB. Pour des raisons pratiques, nous recommandons de regrouper les branches par intervalles de 1 m le long de la tige. Cette strategie a reduit les erreurs types relatives pour la masse de la cime au-dessous de 20 % avec des tailles d'echantillon de quatre a huit branches; de plus petites tailles d'echantillon produisaient ce resultat pour les arbres plus effiles. Nous presentons aussi des resultats sur la variabilite de la masse et de la surface des branches ainsi que des resultats qui remettent en question la pratique qui consiste a allouer des nombres egaux de branches echantillons a des strates de cime d' egale longueur. [Traduit par la Redaction] Mots-cles: echantillonnage aleatoire des branches, biomasse de la cime, allometrie de la cime, cime de forme conique, echantillonnage avec probabilites inegales., Introduction Tree canopies regulate many aspects of the structure and dynamics of coniferous forests, and information regarding the size and structure of individual crowns is important for a wide and [...]

INTRODUCTION I. AVERAGING II. SHRINKAGE III. NONRANDOM SAMPLING CONCLUSION INTRODUCTION In many mass tort cases, individual trials are simply impractical. Take, for example, Wal-Mart Stores, Inc. v. Dukes, (1) a [...]

Dissemination of ideas from theory to practice is a significant challenge in statistics. Quick identification of articles useful to practitioners would greatly assist in this dissemination, thereby improving science. This article uses the citation count history of articles to identify key papers from 1985 to 2002 from 12 statistics journals for applied biostalisticians. One feature requiring attention in order to appropriately rank an article's impact is assessment of the citation accrual patterns over time. Citation counts in statistics differ dramatically from fields such as medicine. In statistics, most articles receive few citations, with 15-year-old articles from live key journals receiving a median of 13 citations compared to 66 in the Journal of Clinical Oncology. However, statistics articles in the top 2%-3% continue to gain citations at a high rate past 15 years, exceeding those in JCO, whose counts slow dramatically around 8 years past publication. Articles with the highest expected applied uses 20 years post publication were identified using joinpoint regression. In this evaluation, the fraction of citations that represent applied use was defined and estimated. The false discovery rate, quantification of heterogeneity in meta-analysis, and generalized estimating equations rank as the ideas with the greatest estimated applied impact. KEY WORDS: Applied fraction; Citation count; Statistical practice.

Accurate simulation of scalar optical diffraction requires consideration of the sampling requirement for the phase chirp function that appears in the Fresnel diffraction expression. We describe three sampling regimes for FFT-based propagation approaches: ideally sampled, oversampled, and undersampled. Ideal sampling, where the chirp and its FFT both have values that match analytic chirp expressions, usually provides the most accurate results but can be difficult to realize in practical simulations. Under- or oversampling leads to a reduction in the available source plane support size, the available source bandwidth, or the available observation support size, depending on the approach and simulation scenario. We discuss three Fresnel propagation approaches: the impulse response/transfer function (angular spectrum) method, the single FFT (direct) method, and the two-step method. With illustrations and simulation examples we show the form of the sampled chirp functions and their discrete transforms, common relationships between the three methods under ideal sampling conditions, and define conditions and consequences to be considered when using nonideal sampling. The analysis is extended to describe the sampling limitations for the more exact Rayleigh-Sommerfeld diffraction solution. OCIS codes: 050.1755, 050.1940, 070.2580, 070.7345.

In two experiments with adults (N = 126), we examined the influence of sampling procedure on inductive generalization. In predicate sampling, participants learned the category identity of individuals known to possess some property. In subject sampling, individuals selected for category identity were discovered to possess a novel property. In both experiments, sampling procedure influenced induction. Predicate sampling resulted in very narrow generalization, whereas subject sampling yielded a fairly high and constant rate of projection. Differences in confidence of generalizations were also observed. Conditions in which evidence was described as randomly sampled from a collection of animals yielded a consistent decrease in projections as predicted by similarity-based models. The results are presented as support for an evidence-based view of induction.

Problem statement: Bootstrap approach had introduced new advancement in modeling and model evaluation. It was a computer intensive method that can replace theoretical formulation with extensive use of computer. The Ordinary Least Squares (OLS) method often used to estimate the parameters of the regression models in the bootstrap procedure. Unfortunately, many statistics practitioners are not aware of the fact that the OLS method can be adversely affected by the existence of outliers. As an alternative, a robust method was put forward to overcome this problem. The existence of outliers in the original sample may create problem to the classical bootstrapping estimates. There was possibility that the bootstrap samples may contain more outliers than the original dataset, since the bootstrap re-sampling is with replacement. Consequently, the outliers will have an unduly effect on the classical bootstrap mean and standard deviation. Approach: In this study, we proposed to use a robust bootstrapping method which was less sensitive to outliers. In the robust bootstrapping procedure, we proposed to replace the classical bootstrap mean and standard deviation with robust location and robust scale estimates. A number of numerical examples were carried out to assess the performance of the proposed method. Results: The results suggested that the robust bootstrap method was more efficient than the classical bootstrap. Conclusion/Recommendations: In the presence of outliers in the dataset, we recommend using the robust bootstrap procedure as its estimates are more reliable. Key words: Bootstrap, outliers, robust location, robust standard deviation, INTRODUCTION Model selection is an important subject in the areas of scientific research, especially in regression predictions. Riadh et al. (1) proposed utilizing the bootstrap techniques for model selection. Bootstrap [...]

In this technical note we present a novel sampled-data lowgain I-control algorithm for infinite-dimensional systems in the presence of input nonlinearity. The system is assumed to be exponentially stable with invertible steady-state gain. We use an integral controller with fixed integrator gain, chosen on the basis of state gain information and a time varying sampling period determined by the growth bound of the system. We compare this new algorithm with two other algorithms one with fixed gain and sampling period, the other with time-varying gain. Index Terms--Infinite dimensional systems, input nonlinearities, integral control, robust tracking, steady-state gain matrix, variable sampling.

Biodiversity sampling is labor intensive, and a substantial fraction of a biota is often represented by species of very low abundance, which typically remain undetected by biodiversity surveys. Statistical methods are widely used to estimate the asymptotic number of species present, including species not yet detected. Additional sampling is required to detect and identify these species, but richness estimators do not indicate how much sampling effort (additional individuals or samples) would be necessary to reach the asymptote of the species accumulation curve. Here we develop the first statistically rigorous nonparametric method for estimating the minimum number of additional individuals, samples, or sampling area required to detect any arbitrary proportion (including 100%) of the estimated asymptotic species richness. The method uses the Chao1 and Chao2 nonparametric estimators of asymptotic richness, which are based on the frequencies of rare species in the original sampling data. To evaluate the performance of the proposed method, we randomly subsampled individuals or quadrats from two large biodiversity inventories (light trap captures of Lepidoptera in Great Britain and censuses of woody plants on Barro Colorado Island [BCI], Panama). The simulation results suggest that the method performs well but is slightly conservative for small sample sizes. Analyses of the BCI results suggest that the method is robust to nonindependence arising from small-scale spatial aggregation of species occurrences. When the method was applied to seven published biodiversity data sets, the additional sampling effort necessary to capture all the estimated species ranged from 1.05 to 10.67 times the original sample (median [approximately equal to] 2.23). Substantially less effort is needed to detect 90% of the species (0.33-1.10 times the original effort; median [approximately equal to] 0.80). An Excel spreadsheet tool is provided for calculating necessary sampling effort for either abundance data or replicated incidence data. Key words: asymptotic species richness estimators; biodiversity sampling; sample size; Turing's frequency formula.

Participants were given information about three different vacation destinations to read before discussing them in a group. Some information was given to all three group members before the discussion (shared) and some information was only given to one participant (unshared). Participants were randomly assigned to discuss the issue in either unstructured groups or Judge-Advisor Systems (JASs). A JAS is a group in which one member has the role of decisionmaker and the other two members act as advisors to the decisionmaker. Participants in JASs discussed more information and repeated a higher percentage of both their own unshared information and others' unshared information than participants in unstructured groups. The hypothesis that others' unshared information would be rated as more important and valid in JASs than groups was not supported. Keywords: Unshared Information; Information Sampling; Common Information Bias; Group Decision Making; Advice

Stable isotope analysis of diet switching by fishes often is hampered by slow turnover rates of the tissues analyzed (usually muscle or fins). We examined epidermal mucus as a potentially faster turnover 'tissue' that might provide a more rapid assessment of diet switching. In a controlled hatchery experiment, we switched the diet of juvenile steelhead (sea-run rainbow trout, Oncorhynchus mykiss) from a plant-based feed with low [delta][sup.13]C and [delta][sup.15]N to a fish-meal-based diet with higher delta values. We found mucus to provide a significantly more rapid response to diet switching (half-life = 36 days for [delta][sup.15]N, 30 days for [delta][sup.13]C) than muscle tissue (half-life = 94 days for [delta][sup.15]N, 136 days for [delta][sup.13]C), even for growing juvenile fish. Mucus may provide a rapid turnover 'tissue' for analysis of diet (or habitat) switching by fish. It has the additional advantage that it may be sampled nonlethally in some fishes, thereby avoiding problems in studying threatened or endangered species. This is the first report of the use of fish mucus in stable isotope analyses of fish tissues. Les analyses de changements de regime alimentaire chez les poissons au moyen des isotopes stables sont souvent entravees par les faibles taux de remplacement des tissus analyses (generalement les muscles ou les branchies). Nous evaluons l'utilisation du mucus epidermique comme [much less than] tissu [much greater than] a taux de renouvellement potentiellement plus eleve qui pourrait fournir une appreciation plus hative des changements de regime. Dans une experience en conditions controlees de pisciculture, nous avons modifie l'alimentation de jeunes truites arc-en-ciel anadromes (Oncorhynchus mykiss) d'un regime a base de plantes a [delta][sup.13]C et [delta][sup.15]N bas, a un regime a base de farine de poisson avec des valeurs plus elevees des deltas. Le mucus reagit significativement plus rapidement au changement de regime (demi-vie = 36 jours pour [delta][sup.15]N et 30 jours pour [delta][sup.13]C) que le muscle (demi-vie = 94 jours pour [delta][sup.15]N et 136 jours pour [delta][sup.13]C), meme chez les jeunes poissons en croissance. Le mucus peut donc constituer un [much less than] tissu [much greater than] a taux de renouvellement rapide pour l'analyse des changements de regime (ou d'habitat) chez les poissons. Il presente, de plus, l'avantage de pouvoir etre echantillonne chez certains poissons sans devoir sacrifier l'animal, ce qui evite quelques-uns des problemes associes a l'etude des especes menaces ou en voie de disparition. C'est la premiere fois que le mucus de poisson est utilise pour l'analyse des isotopes stables dans les tissus de poisson. [Traduit par la Redaction], Introduction The analysis of stable isotope ratios in fish can be a powerful tool for studying fish ecology, including, for example, movement of fish from one habitat (and diet) to [...]

Variability, hypothesis testing, statistical interpretation, confidence intervals, and sample size are explained to give oral health care professionals the tools to properly interpret clinical results.

The article explains a newly developed noniterative, interpolation-based super-resolution (SR) technique, which uses the sampling theory for deriving the required SR algorithm. The approach is shown to be highly beneficial, as it minimizes the aliasing in the images and is also easily scalable.

Although many authors have proposed different approaches to the analysis of length-biased survival data, a number of issues have not been fully addressed. The most important among these issues is perhaps that regarding inclusion of covariates into the analysis of length-biased lifetime data collected through cross-sectional sampling of a population. One aspect of this problem, which appears to have been neglected in the literature, concerns the effect of length bias on the sampling distribution of the covariates. In most regression analyses, it is conventional to condition on the observed covariate values; however, certain covariate values could be preferentially selected into the sample, being linked to the long-term survivors, who themselves are favored by the sampling mechanism. This observation raises two questions: (1) Does the conditional analysis of covariates lead to biased estimators of regression coefficients'?; and (2) does inference through the joint I likelihood of covariates and failure times yield more efficient estimators of the regression parameters? We present a joint likelihood approach and study the large-sample behavior of the resulting maximum likelihood estimators (MLEs). We find that these MLEs are more efficient than their conditional counterparts even though the two MLEs are asymptotics equal. Our results are illustrated using data on survival with dementia, collected as part of the Canadian Study of Health and Aging. KEY WORDS: Asymptotic efficiency; Cross-sectional sampling; Left truncation; Length-biased sampling; Prevalent cohort; Right censoring.

A general sampling framework with a linear sampling operator and with signals from a known union of subspaces is presented. Results suggest that the proposed framework provides a geometrical approach to finite rate of innovation sampling.

The frame reconstruction of a function from its noisy samples is analyzed. Findings reveal an unbiased estimated reconstructed function from the sampled function belonging to a shift invariant space.

Orthogonal projection sampling mode was proposed to reconstruct the incomplete-data flow field in optical computerized tomography (OCT). With numerical simulation technique, a two-peak plane symmetric flow field was reconstructed in different sampling modes and discussed in simulated results is the reconstructive accuracy with error indexes, such as mean square error (MSE) and peak error (PE). The corresponding experiments were researched with a Fabry-Perot rotary interferometer. The results indicated that the errors were drastically reduced and the precision was improved when orthogonal projection sampling mode was adopted in the reconstruction of the incomplete data field. The MSE obtained with orthogonal sampling mode was decreased 72.81% from that of the sequential projection sampling mode (the difference between the MSE obtained with the orthogonal sampling mode and that with the sequential sampling mode divided by the MSE of the sequential sampling mode) and the PE was decreased by 73.97%. The precision obtained from the experimental results reached 10%, which showed the orthogonal projection sampling could be a practicable sampling mode for the incomplete data field reconstruction in OCT and could provide some guidance for the flow-field measurement and apparatus design in the practical situation. OCIS codes: 110.6960, 100.3010, 200.3050, 100.6950.

We consider the problem of creating a sample view of a database table. A sample view is an indexed materialized view that permits efficient sampling from an arbitrary range query over the view. Such 'sample views' are very useful in applications that require random samples from a database: Approximate query processing, online aggregation, data mining, and randomized algorithms are a few examples. Our core technical contribution is a new file organization called the Appendability, Combinability, and Exponentiafity (ACE) Tree that is suitable for organizing and indexing a sample view. One of the most important aspects of the ACE Tree is that it supports online random sampling from the view. That is, at atl times, the set of records returned by the ACE Tree constitutes a statistically random sample of the database records satisfying the relational selection predicate over the view. Our paper presents experimental results that demonstrate the utility of the ACE Tree. Index Terms--Indexing methods, query processing, sampling.

Although several efficacious treatments for posttraumatic stress disorder (PTSD) exist, these treatments are currently underutilized in clinical practice. To address this issue, research must better identify barriers to dissemination of these treatments. This study investigated patient preferences for PTSD treatment given a wide range of treatment options in an analog sample. One hundred and sixty individuals, with varying degrees of trauma history, were asked to imagine themselves undergoing a trauma, developing PTSD, and seeking treatment. Participants evaluated seven different treatment descriptions, which depicted treatment options that they might encounter in a clinical setting. Participants rated their most and least preferred treatments along with their personal reactions to and the perceived credibility of each treatment. Participants also completed a critical thinking skills questionnaire. Participants predominantly chose exposure or another variant of cognitive-behavioral therapy as their most preferred therapy, and those who chose exclusively empirically supported treatments evidenced higher critical thinking skills. The present study contributes to a growing literature indicating that patients may be more interested in these therapies than indicated by utilization rates. The problem of underutilization of empirically supported treatments for PTSD in clinical practice may be due to therapist factors. Keywords: PTSD, Exposure; Empirically supported treatment; Patient preference

Data from a variability study of loblolly pine (Pinus taeda L.) based on weighted core specific gravity (WCSG) were examined to show how costs and variance estimates are used in designing efficient sampling strategies. Increment cores for the determination of WCSG were taken from 3957 trees across six distinct physiographic regions in the southeastern United States. More variability was found to exist among stands than within stands. This indicates that reducing the variation of the mean of WCSG can be accomplished by sampling more stands and fewer trees in the region of interest. The number of stands and trees to sample is dictated by the maximum allowable cost and the precision required of the sample mean, and formulas are given for such calculations. The estimate of among-stand variability was found to be similar among the regions of interest, whereas larger within-stand variation was found to exist in the South Atlantic and Hilly regions. The standard error of the mean was found to increase with an increase in the age at which the stand was sampled. When sampling across multiple stands (at any age), little if any gain in the precision of the standard error of the mean is gained by sampling more than 15 trees. In the general case where one is interested only in the value of WCSG in one stand and precision or cost-time factors are not of consideration, it would suffice to sample between 45 and 55 trees at any age. Des donnees provenant d'une etude de variabilite basee sur le poids specifique pondere de carottes de pin a encens (Pinus taeda L.) ont ete examinees pour illustrer comment l'estimation des couts et de la variance est utilisee pour elaborer des strategies efficaces d'echantillonnage. Les carottes utilisees pour determiner le poids specifique pondere ont ete prelevees sur 3957 arbres repartis dans six regions physiographiques distinctes du sud-est des Etats-Unis d'Amerique. Une plus grande variabilite a ete observee entre les peuplements que dans les peuplements. Cela signifie qu'il est possible de reduire la variation de la moyenne du poids specifique pondere en echantillonnant plus de peuplements et moins d'arbres dans la region visee. Le nombre de peuplements et d'arbres a echantillonner est dicte par le cout maximal admissible et la precision de la moyenne de l'echantillon qui est requise; des formules servant a effectuer ces calculs sont fournies. L'estimation de la variabilite entre les peuplements etait semblable d'une region a l'autre tandis qu'une plus forte variabilite a ete observee dans les peuplements des regions de South Atlantic et de Hilly. L'erreur type de la moyenne augmente avec l'age auquel le peuplement a ete echantillonne. Lorsqu'on echantillonne plusieurs peuplements d'ages differents, on obtient peu sinon aucun gain de precision de l'erreur type de la moyenne en echantillonnant plus de 15 arbres. En general, lorsqu'on s'interesse seulement a la valeur du poids specifique pondere dans un peuplement et que la precision ou les facteurs de cout ou de temps ne sont pas importants, il serait suffisant d'echantillonner 45 a 55 arbres peu importe l'age. [Traduit par la Redaction], Introduction The southeastern United States produces 58% of the marketed timber in the United States and 16% of all marketed timber in the world (Wear and Greis 2002). Loblolly pine [...]

Double sampling involves combining information from inexpensive rapid counts with intensive complete counts to provide an efficient population estimate. This technique is a valuable approach for calibrating population indices based on incomplete counts and improving the precision of monitoring studies. Data collected through a double-sampling protocol can be analyzed with either a ratio or a regression estimator. The ratio estimator is recommended when the relationship of the actual count to the rapid count is a straight line through origin, which may not be valid when surveying populations that have a small number of individuals per site and a low detection probability. In such situations, the regression estimator may be more appropriate. I investigated the properties of these two different estimators through a simulation study and tabulated sample sizes to control bias of the population average and standard error. Further, I used the results to evaluate when double sampling is a cost-effective design and how to design surveys that meet precision requirements. The design process is illustrated with the Spring Eastern Waterfowl Survey, which shows that double sampling is not always appropriate. Key words: detection probability, double sampling, ratio estimator, regression estimator, simulation. Directives pour l'utilisation de l'echantillonnage double dans le suivi des populations d'oiseaux L'echantillonnage double implique la combinaison d'informations provenant de decomptes rapides et peu couteux et de decomptes intensifs complets afin de fournir un bon estime de population. Cette technique est une approche tres utile pour calibrer les indices de population bases sur des decomptes incomplets et ameliorer la precision des etudes de suivi. Les donnees recueillies a l'aide d'un protocole de double echantillonnage peuvent etre analysees soit par un rapport, soit par une regression. Le rapport est recommande lorsque la relation entre le decompte reel et le decompte rapide est une ligne droite passant par l'origine, ce qui peut ne pas etre valide lorsque l'on etudie des populations qui ont un petit nombre d'individus par site et une faible probabilite de detection. Dans de telles situations, la regression peut etre plus appropriee. J'ai etudie les proprietes de ces deux differents estimateurs par une simulation et j'ai calcule les tailles d'echantillon afin de controler les biais de la moyenne et de l'erreur-type de la population. De plus, j'ai utilise les resultats pour evaluer quand l'echantillonnage double est rentable et comment elaborer un suivi qui rencontre les besoins de precision. Ce processus de conception est illustre avec le Spring Eastern Waterfowl Survey, qui montre que l'echantillonnage double n'est pas toujours approprie.

A consistent sampling theorem for preserving certain preferential signals is discussed. Findings reveal that the theorem offers a unique and well-defined solution in the absence of one-to-one mapping between the measurements and the reconstructed signal.

Old-growth stands within the Tionesta Research Natural Area were sampled in 1977, 1990 and 2000. Sapling growth within 25 treefall gaps was sampled all three times. Canopy trees were measured using the point-centered quarter method, with 83 points sampled all three times. Gap regeneration increased significantly in density and basal area from 1977-1990. Beech (Fagus grandifolia) significantly increased its relative gap sapling density from 68% to 91% to 94% over the 3 y. Other species decreased in absolute numbers presumably due to deer browsing. Canopy tree density remained constant and basal area increased 1977-1990 but both decreased 1990-2000. Species relative density and basal area values did not change. Mortality rates almost doubled from 1977-1990 to 1990-2000, increasing especially for smaller canopy trees. Snag densities and formation rates also increased, though not significantly, from the first to the second time interval. Beech, in particular, showed large increases in mortality, probably due to the growing impact of beech bark disease, which reached the stand about 1990. The stand seems changing to a new state with less beech in the canopy and more in the understory. Which species will replace beech in the canopy is difficult to predict.

In observational studies of treatment effects, matched samples have traditionally been constructed using two tools, namely close matches on one or two key covariates and close matches on the propensity score to stochastically balance large numbers of covariates. Here we propose a third tool, fine balance, obtained using the assignment algorithm in a new way. We use all three tools to construct a matched sample for an ongoing study of provider specialty in the treatment of ovarian cancer. Fine balance refers to exact balance of a nominal covariate, often one with many categories, but it does not require individually matched treated and control subjects for this variable. In the example the nominal variable has 72 = 9 x 8 categories formed from 9 possible years of diagnosis and 8 geographic locations or SEER sites. We obtain exact balance on the 72 categories and close individual matches on clinical stage, grade, year of diagnosis, and other variables using a distance, and stochastically balance a total of 61 covariates using a propensity score. Our approach finds an optimal match that minimizes a suitable distance subject to the constraint that fine balance is achieved. This is done by defining a special patterned distance matrix and passing it to a subroutine that solves the optimal assignment problem, which optimally pairs the rows and columns of a matrix using a polynomial time algorithm. In the example we used the function Proc Assign in SAS. A new theorem shows that with our patterned distance matrix, the assignment algorithm returns an optimal, finely balanced matched sample whenever one exists, and otherwise returns an infinite distance, indicating that no such matched sample exists. KEY WORDS: Assignment algorithm; Matched sampling; Observational study; Optimal matching; Propensity score.

Two novel block-based algorithms are described for the reconstruction of uniform samples given the nonuniform samples, where the first algorithm has used a sinc interpolator and the second one has used a density functional theory (DFT)-based interpolator. The analysis has shown that the modified block-based algorithm has performed better than a group of alternative algorithms, including Yen's third algorithm, for a variety of signal, noise and sampling grids.

This paper describes the development of adaptive importance sampling (IS) techniques for estimating false alarm probabilities of detectors that use space-time adaptive processing (STAP) algorithms. Fast simulation using IS methods has been notably successful in the study of conventional constant false alarm rate (CFAR) radar detectors, and in several other applications. The principal objectives here are to examine the viability of using these methods for STAP detectors, develop them into powerful analysis and design algorithms and, in the long term, use them for synthesizing novel detection structures. The adaptive matched filter (AMF) detector has been analyzed successfully using fast simulation. Of two biasing methods considered, one is implemented and shown to yield good results. The important problem of detector threshold determination is also addressed, with matching outcome. As an illustration of the power of these methods, two variants of the square-law AMF detector that are thought to be robust under heterogeneous clutter conditions have also been successfully investigated. These are the envelope-law and geometric-mean STAP detectors. Their CFAR property is established and performance evaluated. It turns out the variants have detection performances better than those of the AMF detector for training data contaminated by interferers. In summary, the work reported here paves the way for development of advanced estimation techniques that can facilitate design of powerful and robust detection algorithms.