The use of auxiliary variables in capture-recapture modelling: An overview

I review the use of auxiliary variables in capture-recapture models for estimation of demographic parameters (e.g. capture probability, population size, survival probability, and recruitment, emigration and immigration numbers). I focus on what has been done in current research and what still needs to be done. Typically in the literature, covariate modelling has made capture and survival probabilities functions of covariates, but there are good reasons also to make other parameters functions of covariates as well. The types of covariates considered include environmental covariates that may vary by occasion but are constant over animals, and individual animal covariates that are usually assumed constant over time. I also discuss the difficulties of using time-dependent individual animal covariates and some possible solutions. Covariates are usually assumed to be measured without error, and that may not be realistic. For closed populations, one approach to modelling heterogeneity in capture probabilities uses observable individual covariates and is thus related to the primary purpose of this paper. The now standard Huggins-Alho approach conditions on the captured animals and then uses a generalized Horvitz-Thompson estimator to estimate population size. This approach has the advantage of simplicity in that one does not have to specify a distribution for the covariates, and the disadvantage is that it does not use the full likelihood to estimate population size. Alternately one could specify a distribution for the covariates and implement a full likelihood approach to inference to estimate the capture function, the covariate probability distribution, and the population size. The general Jolly-Seber open model enables one to estimate capture probability, population sizes, survival rates, and birth numbers. Much of the focus on modelling covariates in program MARK has been for survival and capture probability in the Cormack-Jolly-Seber model and its generalizations (including tag-return models). These models condition on the number of animals marked and released. A related, but distinct, topic is radio telemetry survival modelling that typically uses a modified Kaplan-Meier method and Cox proportional hazards model for auxiliary variables. Recently there has been an emphasis on integration of recruitment in the likelihood, and research on how to implement covariate modelling for recruitment and perhaps population size is needed. The combined open and closed 'robust' design model can also benefit from covariate modelling and some important options have already been implemented into MARK. Many models are usually fitted to one data set. This has necessitated development of model selection criteria based on the AIC (Akaike Information Criteria) and the alternative of averaging over reasonable models. The special problems of estimating over-dispersion when covariates are included in the model and then adjusting for over-dispersion in model selection could benefit from further research.     

Non-parametric estimation of population size from capture–recapture data when the capture probability depends on a covariate

Summary.  In capture–recapture experiments the capture probabilities may depend on individual covariates such as an individual's weight or age. Typically this dependence is modelled through simple parametric functions of the covariates. Here we first demonstrate that misspecification of the model can produce biased estimates and subsequently develop a non-parametric procedure to estimate the functional relationship between the probability of capture and a single covariate. This estimator is then incorporated in a Horvitz–Thompson estimator to estimate the size of the population. The resulting estimators are evaluated in a simulation study and applied to a data set on captures of the Mountain Pygmy Possum.     

Inferential properties of an individual-based survival model using release-recapture data: Sample size,validity and power

A model for analyzing release-recapture data is presented that generalizes a previously existing individual covariate model to include multiple groups of animals. As in the previous model, the generalized version includes selection parameters that relate individual covariates to survival potential. Significance of the selection parameters was equivalent to significance of the individual covariates. Simulation studies were conducted to investigate three inferential properties with respect to the selection parameters: (1) sample size requirements, (2) validity of the likelihood ratio test (LRT) and (3) power of the LRT. When the survival and capture probabilities ranged from 0.5 to 1.0, a total sample size of 300 was necessary to achieve a power of 0.80 at a significance level of 0.1 when testing the significance of the selection parameters. However, only half that (a total of 150) was necessary for the distribution of the maximum likelihood estimators of the selection parameters to approximate their asymptotic distributions. In general, as the survival and capture probabilities decreased, the sample size requirements increased. The validity of the LRT for testing the significance of the selection parameters was confirmed because the LRT statistic was distributed as theoretically expected under the null hypothesis, i.e. like a chi 2 random variable. When the baseline survival model was fully parameterized with population and interval effects, the LRT was also valid in the presence of unaccounted for random variation. The power of the LRT for testing the selection parameters was unaffected by over-parameterization of the baseline survival and capture models. The simulation studies showed that for testing the significance of individual covariates to survival the LRT was remarkably robust to assumption violations.     

Inferential properties of an individual-based survival model using release-recapture data: sample size, validity and power

A model for analyzing release-recapture data is presented that generalizes a previously existing individual covariate model to include multiple groups of animals. As in the previous model, the generalized version includes selection parameters that relate individual covariates to survival potential. Significance of the selection parameters was equivalent to significance of the individual covariates. Simulation studies were conducted to investigate three inferential properties with respect to the selection parameters: (1) sample size requirements, (2) validity of the likelihood ratio test (LRT) and (3) power of the LRT. When the survival and capture probabilities ranged from 0.5 to 1.0, a total sample size of 300 was necessary to achieve a power of 0.80 at a significance level of 0.1 when testing the significance of the selection parameters. However, only half that (a total of 150) was necessary for the distribution of the maximum likelihood estimators of the selection parameters to approximate their asymptotic distributions. In general, as the survival and capture probabilities decreased, the sample size requirements increased. The validity of the LRT for testing the significance of the selection parameters was confirmed because the LRT statistic was distributed as theoretically expected under the null hypothesis, i.e. like a chi 2 random variable. When the baseline survival model was fully parameterized with population and interval effects, the LRT was also valid in the presence of unaccounted for random variation. The power of the LRT for testing the selection parameters was unaffected by over-parameterization of the baseline survival and capture models. The simulation studies showed that for testing the significance of individual covariates to survival the LRT was remarkably robust to assumption violations.     

A comparison of two approaches for power and sample size calculations in logistic regression models

Whittemore (1981) proposed an approach for calculating the sample size needed to test hypotheses with specified significance and power against a given alternative for logistic regression with small response probability. Based on the distribution of covariate, which could be either discrete or continuous, this approach first provides a simple closed-form approximation to the asymptotic covariance matrix of the maximum likelihood estimates, and then uses it to calculate the sample size needed to test a hypothesis about the parameter. Self et al. (1992) described a general approach for power and sample size calculations within the framework of generalized linear models, which include logistic regression as a special case. Their approach is based on an approximation to the distribution of the likelihood ratio statistic. Unlike the Whittemore approach, their approach is not limited to situations of small response probability. However, it is restricted to models with a finite number of covariate configurations. This study compares these two approaches to see how accurate they would be for the calculations of power and sample size in logistic regression models with various response probabilities and covariate distributions. The results indicate that the Whittemore approach has a slight advantage in achieving the nominal power only for one case with small response probability. It is outperformed for all other cases with larger response probabilities. In general, the approach proposed in Self et al. (1992) is recommended for all values of the response probability. However, its extension for logistic regression models with an infinite number of covariate configurations involves an arbitrary decision for categorization and leads to a discrete approximation. As shown in this paper, the examined discrete approximations appear to be sufficiently accurate for practical purpose.     

Modelling Survival Events with Longitudinal Covariates Measured with Error

In survival analysis, time-dependent covariates are usually present as longitudinal data collected periodically and measured with error. The longitudinal data can be assumed to follow a linear mixed effect model and Cox regression models may be used for modelling of survival events. The hazard rate of survival times depends on the underlying time-dependent covariate measured with error, which may be described by random effects. Most existing methods proposed for such models assume a parametric distribution assumption on the random effects and specify a normally distributed error term for the linear mixed effect model. These assumptions may not be always valid in practice. In this article, we propose a new likelihood method for Cox regression models with error-contaminated time-dependent covariates. The proposed method does not require any parametric distribution assumption on random effects and random errors. Asymptotic properties for parameter estimators are provided. Simulation results show that under certain situations the proposed methods are more efficient than the existing methods.     

The proportional hazards model with covariate measurement error

The proportional hazards regression model is commonly used to evaluate the relationship between survival and covariates. Covariates are frequently measured with error. Substituting mismeasured values for the true covariates leads to biased estimation. Hu et al. (Biometrics 88 (1998) 447) have proposed to base estimation in the proportional hazards model with covariate measurement error on a joint likelihood for survival and the covariate variable. Nonparametric maximum likelihood estimation (NPMLE) was used and simulations were conducted to assess the asymptotic validity of this approach. In this paper, we derive a rigorous proof of asymptotic normality of the NPML estimators.     

Use of the Barker model in an experiment examining covariate effects on first-year survival in Ross's Geese ( Chen rossii ): A case study

The Barker model provides researchers with an opportunity to use three types of data for mark-recapture analyses - recaptures, recoveries, and resightings. This model structure maximizes use of encounter data and increases the precision of parameter estimates, provided the researcher has large amounts of resighting data. However, to our knowledge, this model has not been used for any published ringing studies. Our objective here is to report our use of the Barker model in covariate-dependent analyses that we conducted in Program MARK. In particular, we wanted to describe our experimental study design and discuss our analytical approach plus some logistical constraints we encountered while conducting a study of the effects of growth and parasites on survival of juvenile Ross's Geese. Birds were marked just before fledging, alternately injected with antiparasite drugs or a control, and then were re-encountered during migration and breeding in following years. Although the Barker model estimates seven parameters, our objectives focused on annual survival only, thus we considered all other parameters as nuisance terms. Therefore, we simplified our model structures by maintaining biological complexity on survival, while retaining a very basic structure on nuisance parameters. These analyses were conducted in a two-step approach where we used the most parsimonious model from nuisance parameter analyses as our starting model for analyses of covariate effects. This analytical approach also allowed us to minimize the long CPU times associated with the use of covariates in earlier versions of Program MARK. Resightings made up about 80% of our encounter history data, and simulations demonstrated that precision and bias of parameter estimates were minimally affected by this distribution. Overall, the main source of bias was that smaller goslings were too small to retain neckbands, yet were the birds that we predicted would have the lowest survival probability and highest probability for parasite effects. Consequently, we considered our results conservative. The largest constraint of our study design was the inability to partition survival into biologically meaningful periods to provide insight into the timing and mechanisms of mortality.     

A Profile Conditional Likelihood Approach for the Semiparametric Transformation Regression Model with Missing Covariates

We propose a profile conditional likelihood approach to handle missing covariates in the general semiparametric transformation regression model. The method estimates the marginal survival function by the Kaplan-Meier estimator, and then estimates the parameters of the survival model and the covariate distribution from a conditional likelihood, substituting the Kaplan-Meier estimator for the marginal survival function in the conditional likelihood. This method is simpler than full maximum likelihood approaches, and yields consistent and asymptotically normally distributed estimator of the regression parameter when censoring is independent of the covariates. The estimator demonstrates very high relative efficiency in simulations. When compared with complete-case analysis, the proposed estimator can be more efficient when the missing data are missing completely at random and can correct bias when the missing data are missing at random. The potential application of the proposed method to the generalized probit model with missing continuous covariates is also outlined.     

Methods for missing covariates in logistic regression

Various methods have been suggested in the literature to handle a missing covariate in the presence of surrogate covariates. These methods belong to one of two paradigms. In the imputation paradigm, Pepe and Fleming (1991) and Reilly and Pepe (1995) suggested filling in missing covariates using the empirical distribution of the covariate obtained from the observed data. We can proceed one step further by imputing the missing covariate using nonparametric maximum likelihood estimates (NPMLE) of the density of the covariate. Recently Murphy and Van der Vaart (1998a) showed that such an approach yields a consistent, asymptotically normal, and semiparametric efficient estimate for the logistic regression coefficient. In the weighting paradigm, Zhao and Lipsitz (1992) suggested an estimating function using completely observed records after weighting inversely by the probability of observation. An extension of this weighting approach designed to achieve semiparametric efficient bound is considered by Robins, Hsieh and Newey (RHN) (1995). The two ends of each paradigm (NPMLE and RHN) attain the efficiency bound and are asymptotically equivalent. However, both require a substantial amount of computation. A question arises whether and when, in practical situations, this extensive computation is worthwhile. In this paper we investigate the performance of single and multiple imputation estimates, weighting estimates, semiparametric efficient estimates, and two new imputation estimates. Simulation studies suggest that the sample size should be substantially large (e.g. n=2000) for NPMLE and RHN to be more efficient than simpler imputation estimates. When the sample size is moderately large (n≤ 1500), simpler imputation estimates have as small a variance as semiparametric efficient estimates.     

Analyzing dependence in incidence of diabetes and heart problem using generalized bivariate geometric models with covariates

For analyzing incidence data on diabetes and health problems, the bivariate geometric probability distribution is a natural choice but remained unexplored largely due to lack of models linking covariates with the probabilities of bivariate incidence of correlated outcomes. In this paper, bivariate geometric models are proposed for two correlated incidence outcomes. The extended generalized linear models are developed to take into account covariate dependence of the bivariate probabilities of correlated incidence outcomes for diabetes and heart diseases for the elderly population. The estimation and test procedures are illustrated using the Health and Retirement Study data. Two models are shown in this paper, one based on conditional-marginal approach and the other one based on the joint probability distribution with an association parameter. The joint model with association parameter appears to be a very good choice for analyzing the covariate dependence of the joint incidence of diabetes and heart diseases. Bootstrapping is performed to measure the accuracy of estimates and the results indicate very small bias.     

Parametric regression models for continuous time removal and recapture studies

We use a class of parametric counting process regression models that are commonly employed in the analysis of failure time data to formulate the subject-specific capture probabilities for removal and recapture studies conducted in continuous time. We estimate the regression parameters by modifying the conventional likelihood score function for left-truncated and right-censored data to accommodate an unknown population size and missing covariates on uncaptured subjects, and we subsequently estimate the population size by a martingale-based estimating function. The resultant estimators for the regression parameters and population size are consistent and asymptotically normal under appropriate regularity conditions. We assess the small sample properties of the proposed estimators through Monte Carlo simulation and we present an application to a bird banding exercise.     

Multistate recapture models: Modelling incomplete individual histories

Multistate capture-recapture models are a natural generalization of the usual one-site recapture models. Similarly, individuals are sampled on discrete occasions, at which they may be captured or not. However, contrary to the one-site case, the individuals can move within a finite set of states between occasions. The growing interest in spatial aspects of population dynamics presently contributes to making multistate models a very promising tool for population biology. We review first the interest and the potential of multistate models, in particular when they are used with individual states as well as geographical sites. Multistate models indeed constitute canonical capture-recapture models for individual categorical covariates changing over time, and can be linked to longitudinal studies with missing data and models such as hidden Markov chains. Multistate models also provide a promising tool for handling heterogeneity of capture, provided states related to capturability can be defined and used. Such an approach could be relevant for population size estimation in closed populations. Multistate models also constitute a natural framework for mixtures of information in individual history data. Presently, most models can be fit using program MARK. As an example, we present a canonical model for multisite accession to reproduction, which fully generalizes a classical one-site model. In the generalization proposed, one can estimate simultaneously age-dependent rates of accession to reproduction, natal and breeding dispersal. Finally, we discuss further generalizations - such as a multistate generalization of growth rate models and models for data where the state in which an individual is detected is known with uncertainty - and prospects for software development.     

Improved inference on capture recapture models with behavioural effects

In the context of capture-recapture modeling for estimating the unknown size of a finite population it is often required a flexible framework for dealing with a behavioural response to trapping. Many alternative settings have been proposed in the literature to account for the variation of capture probability at each occasion depending on the previous capture history. Inference is typically carried out relying on the so-called conditional likelihood approach. We highlight that such approach may, with positive probability, lead to inferential pathologies such as unbounded estimates for the finite size of the population. The occurrence of such likelihood failures is characterized within a very general class of behavioural effect models. It is also pointed out that a fully Bayesian analysis overcomes the likelihood failure phenomenon. The overall improved performance of alternative Bayesian estimators is investigated under different non-informative prior distributions verifying their comparative merits with both simulated and real data.     

Multistate recapture models: modelling incomplete individual histories

Multistate capture-recapture models are a natural generalization of the usual one-site recapture models. Similarly, individuals are sampled on discrete occasions, at which they may be captured or not. However, contrary to the one-site case, the individuals can move within a finite set of states between occasions. The growing interest in spatial aspects of population dynamics presently contributes to making multistate models a very promising tool for population biology. We review first the interest and the potential of multistate models, in particular when they are used with individual states as well as geographical sites. Multistate models indeed constitute canonical capture-recapture models for individual categorical covariates changing over time, and can be linked to longitudinal studies with missing data and models such as hidden Markov chains. Multistate models also provide a promising tool for handling heterogeneity of capture, provided states related to capturability can be defined and used. Such an approach could be relevant for population size estimation in closed populations. Multistate models also constitute a natural framework for mixtures of information in individual history data. Presently, most models can be fit using program MARK. As an example, we present a canonical model for multisite accession to reproduction, which fully generalizes a classical one-site model. In the generalization proposed, one can estimate simultaneously age-dependent rates of accession to reproduction, natal and breeding dispersal. Finally, we discuss further generalizations - such as a multistate generalization of growth rate models and models for data where the state in which an individual is detected is known with uncertainty - and prospects for software development.     

Sample‐size calculations for multi‐group comparison in population pharmacokinetic experiments

This paper describes an approach for calculating sample size for population pharmacokinetic experiments that involve hypothesis testing based on multi‐group comparison detecting the difference in parameters between groups under mixed‐effects modelling. This approach extends what has been described for generalized linear models and nonlinear population pharmacokinetic models that involve only binary covariates to more complex nonlinear population pharmacokinetic models. The structural nonlinear model is linearized around the random effects to obtain the marginal model and the hypothesis testing involving model parameters is based on Wald's test. This approach provides an efficient and fast method for calculating sample size for hypothesis testing in population pharmacokinetic models. The approach can also handle different design problems such as unequal allocation of subjects to groups and unbalanced sampling times between and within groups. The results obtained following application to a one compartment intravenous bolus dose model that involved three different hypotheses under different scenarios showed good agreement between the power obtained from NONMEM simulations and nominal power. Copyright © 2009 John Wiley & Sons, Ltd.     

APPLICATION OF SEMIPARAMETRIC REGRESSION MODELS IN THE ANALYSIS OF CAPTURE-RECAPTURE EXPERIMENTS

If the capture probabilities in a capture‐recapture experiment depend on covariates, parametric models may be fitted and the population size may then be estimated. Here a semiparametric model for the capture probabilities that allows both continuous and categorical covariates is developed. Kernel smoothing and profile estimating equations are used to estimate the nonparametric and parametric components. Analytic forms of the standard errors are derived, which allows an empirical bias bandwidth selection procedure to be used to estimate the bandwidth. The method is evaluated in simulations and is applied to a real data set concerning captures of Prinia flaviventris, which is a common bird species in Southeast Asia.     

Multiple imputation of a randomly censored covariate improves logistic regression analysis

Randomly censored covariates arise frequently in epidemiologic studies. The most commonly used methods, including complete case and single imputation or substitution, suffer from inefficiency and bias. They make strong parametric assumptions or they consider limit of detection censoring only. We employ multiple imputation, in conjunction with semi-parametric modeling of the censored covariate, to overcome these shortcomings and to facilitate robust estimation. We develop a multiple imputation approach for randomly censored covariates within the framework of a logistic regression model. We use the non-parametric estimate of the covariate distribution or the semi-parametric Cox model estimate in the presence of additional covariates in the model. We evaluate this procedure in simulations, and compare its operating characteristics to those from the complete case analysis and a survival regression approach. We apply the procedures to an Alzheimer's study of the association between amyloid positivity and maternal age of onset of dementia. Multiple imputation achieves lower standard errors and higher power than the complete case approach under heavy and moderate censoring and is comparable under light censoring. The survival regression approach achieves the highest power among all procedures, but does not produce interpretable estimates of association. Multiple imputation offers a favorable alternative to complete case analysis and ad hoc substitution methods in the presence of randomly censored covariates within the framework of logistic regression.     

Cox regression with missing covariate data using a modified partial likelihood method

Missing covariate values is a common problem in survival analysis. In this paper we propose a novel method for the Cox regression model that is close to maximum likelihood but avoids the use of the EM-algorithm. It exploits that the observed hazard function is multiplicative in the baseline hazard function with the idea being to profile out this function before carrying out the estimation of the parameter of interest. In this step one uses a Breslow type estimator to estimate the cumulative baseline hazard function. We focus on the situation where the observed covariates are categorical which allows us to calculate estimators without having to assume anything about the distribution of the covariates. We show that the proposed estimator is consistent and asymptotically normal, and derive a consistent estimator of the variance–covariance matrix that does not involve any choice of a perturbation parameter. Moderate sample size performance of the estimators is investigated via simulation and by application to a real data example.