A comparison of design-based and model-based approaches for finite population spatial sampling and inference.

The design-based and model-based approaches to frequentist statistical inference rest on fundamentally different foundations. In the design-based approach, inference relies on random sampling. In the model-based approach, inference relies on distributional assumptions. We compare the approaches in a finite population spatial context.We provide relevant background for the design-based and model-based approaches and then study their performance using simulated data and real data. The real data is from the United States Environmental Protection Agency's 2012 National Lakes Assessment. A variety of sample sizes, location layouts, dependence structures, and response types are considered. The population mean is the parameter of interest, and performance is measured using statistics like bias, squared error, and interval coverage.When studying the simulated and real data, we found that regardless of the strength of spatial dependence in the data, the generalized random tessellation stratified (GRTS) algorithm, which explicitly incorporates spatial locations into sampling, tends to outperform the simple random sampling (SRS) algorithm, which does not explicitly incorporate spatial locations into sampling. We also found that model-based inference tends to outperform design-based inference, even for skewed data where the model-based distributional assumptions are violated. The performance gap between design-based inference and model-based inference is small when GRTS samples are used but large when SRS samples are used, suggesting that the sampling choice (whether to use GRTS or SRS) is most important when performing design-based inference.There are many benefits and drawbacks to the design-based and model-based approaches for finite population spatial sampling and inference that practitioners must consider when choosing between them. We provide relevant background contextualizing each approach and study their properties in a variety of scenarios, making recommendations for use based on the practitioner's goals.

An asymptotic approximation to the N-mixture model for the estimation of disease prevalence.

N-mixture models are probability models that estimate abundance using replicate observed counts while accounting for imperfect detection. In this article, we propose an asymptotic approximation to the N-mixture model which efficiently estimates large abundances without the computational limitations of the generalized N-mixture model introduced by Dail and Madsen in 2011. It has been suggested in the literature that N-mixture models do not perform well when counts from the same sites show weak patterns of population dynamics. Our proposed model addresses this issue by using the asymptotic information matrix to diagnose model parameter estimability and to derive parameter standard errors. A simulation study show that this model performs almost as well as the Dail-Madsen Generalized N-mixture model at low abundances and improves on it at higher abundances. We illustrate the procedure using two data sets: the American robin data from Dail and Madsen (2011), and counts of chlamydia cases in the state of Oregon from 2007-2016. The chlamydia data exhibit very large abundances and demonstrate the potential usefulness of the proposed model for disease surveillance data.

Estimating wind-turbine-caused bird and bat fatality when zero carcasses are observed.

Many wind-power facilities in the United States have established effective monitoring programs to determine turbine-caused fatality rates of birds and bats, but estimating the number of fatalities of rare species poses special difficulties. The loss of even small numbers of individuals may adversely affect fragile populations, but typically, few (if any) carcasses are observed during monitoring. If monitoring design results in only a small proportion of carcasses detected, then finding zero carcasses may give little assurance that the number of actual fatalities is small. Fatality monitoring at wind-power facilities commonly involves conducting experiments to estimate the probability (g) an individual will be observed, accounting for the possibilities that it falls in an unsearched area, is scavenged prior to detection, or remains undetected even when present. When g < 1, the total carcass count (X) underestimates the total number of fatalities (M). Total counts can be 0 when M is small or when M is large and g << 1. Distinguishing these two cases is critical when estimating fatality of a rare species. Observing no individuals during searches may erroneously be interpreted as evidence of absence. We present an approach that uses Bayes' theorem to construct a posterior distribution for M, i.e., P(M \ X, g), reflecting the observed carcass count and previously estimated g. From this distribution, we calculate two values important to conservation: the probability that M is below a predetermined limit and the upper bound (M*) of the 100(1 - α)% credible interval for M. We investigate the dependence of M* on α, g, and the prior distribution of M, asking what value of g is required to attain a desired M for a given α. We found that when g < -0.15, M* was clearly influenced by the mean and variance of g and the choice of prior distribution for M, but the influence of these factors is minimal when g > -0.45. Further, we develop extensions for temporal replication that can inform prior distributions of M and methods for combining information across several areas or time periods. We apply the method to data collected at a wind-power facility where scheduled searches yielded X = 0 raptor carcasses.

The Relationship Quality Interview: evidence of reliability, convergent and divergent validity, and incremental utility.

Relationship satisfaction and adjustment have been the target outcome variables for almost all couple research and therapies. In contrast, far less attention has been paid to the assessment of relationship quality. The present study introduces the Relationship Quality Interview (RQI), a semistructured, behaviorally anchored individual interview. The RQI was designed to provide a more objective assessment of relationship quality as a dynamic, dyadic construct across 5 dimensions: (a) quality of emotional intimacy in the relationship, (b) quality of the couple's sexual relationship, (c) quality of support transactions in the relationship, (d) quality of the couple's ability to share power in the relationship, and (e) quality of conflict/problem-solving interactions in the relationship. Psychometric properties of RQI ratings were examined through scores obtained from self-report questionnaires and behavioral observation data collected cross-sectionally from a sample of 91 dating participants and longitudinally from a sample of 101 married couples. RQI ratings demonstrated strong reliability (internal consistency, interrater agreement, interpartner agreement, and correlations among scales), convergent validity (correlations between RQI scale ratings and questionnaire scores assessing similar domains of relationship quality), and divergent validity (correlations between RQI scale ratings and (a) behavioral observation codes assessing related constructs, (b) global relationship satisfaction scores, and (c) scores on individual difference measures of related constructs). Clinical implications of the RQI for improving couple assessment and interventions are discussed.

Objective Ratings of Relationship Skills across Multiple Domains as Predictors of Marital Satisfaction Trajectories.

Expanding upon social-learning and vulnerability-stress-adaptation approaches to marriage, the impact of multiple dyadic behaviors on marital satisfaction trajectories was examined in 101 couples. Semi-structured interviews were administered separately to husbands and wives at 3 months of marriage. Interviewers generated objective ratings for five domains: emotional closeness/intimacy, sexual intimacy/sensuality, interspousal support, decision-making/relational control, and communication/conflict management. Marital satisfaction was assessed four times over three years. Dyadic behaviors were associated with initial levels and rates of change in satisfaction, demonstrating the unique contributions of each relational skill on marital development. For husbands, sexual intimacy was the strongest predictor of change whereas for wives, communication/conflict management was the strongest predictor of change compared to other domains. Theoretical, methodological and clinical implications are discussed.