Semiparametric Latent Variable Regression Models for Spatio-temporal Modeling of Mobile Source Particles in the Greater Boston Area

Traffic particle concentrations show considerable spatial variability within a metropolitan area. We consider latent variable semiparametric regression models for modeling the spatial and temporal variability of black carbon and elemental carbon concentrations in the greater Boston area. Measurements of these pollutants, which are markers of traffic particles, were obtained from several individual exposure studies conducted at specific household locations as well as 15 ambient monitoring sites in the city. The models allow for both flexible, nonlinear effects of covariates and for unexplained spatial and temporal variability in exposure. In addition, the different individual exposure studies recorded different surrogates of traffic particles, with some recording only outdoor concentrations of black or elemental carbon, some recording indoor concentrations of black carbon, and others recording both indoor and outdoor concentrations of black carbon. A joint model for outdoor and indoor exposure that specifies a spatially varying latent variable provides greater spatial coverage in the area of interest. We propose a penalised spline formation of the model that relates to generalised kringing of the latent traffic pollution variable and leads to a natural Bayesian Markov Chain Monte Carlo algorithm for model fitting. We propose methods that allow us to control the degress of freedom of the smoother in a Bayesian framework. Finally, we present results from an analysis that applies the model to data from summer and winter separately

DECOMPOSITION OF REGRESSION ESTIMATORS TO EXPLORE THE INFLUENCE OF "UNMEASURED" TIME-VARYING CONFOUNDERS

In environmental epidemiology, exposure X and health outcome Y vary in space and time. We present a method to diagnose the possible influence of unmeasured confounders U on the estimated effect of X on Y and to propose several approaches to robust estimation. The idea is to use space and time as proxy measures for the unmeasured factors U. We start with the time series case where X and Y are continuous variables at equally-spaced times and assume a linear model. We define matching estimator b(u)s that correspond to pairs of observations with specific lag u. Controlling for a smooth function of time, St, using a kernel estimator is roughly equivalent to estimating the association with a linear combination of the b(u)s with weights that involve two components: the assumptions about the smoothness of St and the normalized variogram of the X process. When an unmeasured confounder U exists, but the model otherwise correctly controls for measured confounders, the excess variation in b(u)s is evidence of confounding by U. We use the plot of b(u)s versus lag u, lagged-estimator-plot (LEP), to diagnose the influence of U on the effect of X on Y. We use appropriate linear combination of b(u)s or extrapolate to b(0) to obtain novel estimators that are more robust to the influence of smooth U. The methods are extended to time series log-linear models and to spatial analyses. The LEP plot gives us a direct view of the magnitude of the estimators for each lag u and provides evidence when models did not adequately describe the data.

Checking Assumptions in Latent Class Regression Models via a Markov Chain Monte Carlo Estimation Approach: An Application to Depression and Socio-Economic Status

Latent class regression models are useful tools for assessing associations between covariates and latent variables. However, evaluation of key model assumptions cannot be performed using methods from standard regression models due to the unobserved nature of latent outcome variables. This paper presents graphical diagnostic tools to evaluate whether or not latent class regression models adhere to standard assumptions of the model: conditional independence and non-differential measurement. An integral part of these methods is the use of a Markov Chain Monte Carlo estimation procedure. Unlike standard maximum likelihood implementations for latent class regression model estimation, the MCMC approach allows us to calculate posterior distributions and point estimates of any functions of parameters. It is this convenience that allows us to provide the diagnostic methods that we introduce. As a motivating example we present an analysis focusing on the association between depression and socioeconomic status, using data from the Epidemiologic Catchment Area study. We consider a latent class regression analysis investigating the association between depression and socioeconomic status measures, where the latent variable depression is regressed on education and income indicators, in addition to age, gender, and marital status variables. While the fitted latent class regression model yields interesting results, the model parameters are found to be invalid due to the violation of model assumptions. The violation of these assumptions is clearly identified by the presented diagnostic plots. These methods can be applied to standard latent class and latent class regression models, and the general principle can be extended to evaluate model assumptions in other types of models.

PENALIZED FUNCTIONAL REGRESSION

We develop fast fitting methods for generalized functional linear models. An undersmooth of the functional predictor is obtained by projecting on a large number of smooth eigenvectors and the coefficient function is estimated using penalized spline regression. Our method can be applied to many functional data designs including functions measured with and without error, sparsely or densely sampled. The methods also extend to the case of multiple functional predictors or functional predictors with a natural multilevel structure. Our approach can be implemented using standard mixed effects software and is computationally fast. Our methodology is motivated by a diffusion tensor imaging (DTI) study. The aim of this study is to analyze differences between various cerebral white matter tract property measurements of multiple sclerosis (MS) patients and controls. While the statistical developments proposed here were motivated by the DTI study, the methodology is designed and presented in generality and is applicable to many other areas of scientific research. An online appendix provides R implementations of all simulations.

Mast fruiting of large ectomycorrhizal African rain forest trees: importance of dry season intensity, and the resource limitation hypothesis

Mast fruiting is a distinctive reproductive trait in trees. This rain forest study, at a nutrient-poor site with a seasonal climate in tropical Africa, provides new insights into the causes of this mode of phenological patterning. •  At Korup, Cameroon, 150 trees of the large, ectomycorrhizal caesalp, Microberlinia bisulcata, were recorded almost monthly for leafing, flowering and fruiting during 1995–2000. The series was extended to 1988–2004 with less detailed data. Individual transitions in phenology were analysed. •  Masting occurred when the dry season before fruiting was drier, and the one before that was wetter, than average. Intervals between events were usually 2 or 3 yr. Masting was associated with early leaf exchange, followed by mass flowering, and was highly synchronous in the population. Trees at higher elevation showed more fruiting. Output declined between 1995 and 2000. •  Mast fruiting in M. bisulcata appears to be driven by climate variation and is regulated by internal tree processes. The resource-limitation hypothesis was supported. An ‘alternative bearing’ system seems to underlie masting. That ectomycorrhizal habit facilitates masting in trees is strongly implied.

Intra-annual radial growth and water relations of trees - implications towards a growth mechanism

There is a missing link between tree physiological and wood-anatomical knowledge which makes it impossible mechanistically to explain and predict the radial growth of individual trees from climate data. Empirical data of microclimatic factors, intra-annual growth rates, and tree-specific ratios between actual and potential transpiration (T PET−1) of trees of three species (Quercus pubescens, Pinus sylvestris, and Picea abies) at two dry sites in the central Wallis, Switzerland, were recorded from 2002 to 2004 at a 10 min resolution. This included the exceptionally hot and dry summer of 2003. These data were analysed in terms of direct (current conditions) and indirect impacts (predispositions of the past year) on growth. Rain was found to be the only factor which, to a large extent, consistently explained the radial increment for all three tree species at both sites and in the short term as well. Other factors had some explanatory power on the seasonal time-scale only. Quercus pubescens built up much of its tree ring before bud break. Pinus sylvestris and Picea abies started radial growth 1–2 weeks after Quercus pubescens and this was despite the fact that they had a high T PET−1 before budburst and radial growth started. A high T PET−1 was assumed to be related to open stomata, a very high net CO2 assimilation rate, and thus a potential carbon (C)-income for the tree. The main period of radial growth covered about 30–70% of the productive days of a year. In terms of C-allocation, these results mean that Quercus pubescens depended entirely on internal C-stores in the early phase of radial growth and that for all three species there was a long time period of C-assimilation which was not used for radial growth in above-ground wood. The results further suggest a strong dependence of radial growth on the current tree water relations and only secondarily on the C-balance. A concept is discussed which links radial growth over a feedback loop to actual tree water-relations and long-term affected C-storage to microclimate.

Retention of canopy trees as biological legacies for balancing woody biomass production and biodiversity in managed aspen forests of the Great Lakes Region

Green-tree retention under the conceptual framework of ecological forestry has the potential to provide both biomass feedstock for industry and maintain quality wildlife habitat. I examined the effects of retained canopy trees as biological legacies (“legacy trees”) in aspen (Populus spp.) forests on above-ground live woody biomass, understory plant floristic quality, and bird diversity. Additionally, I evaluated habitat quality for a high conservation priority species, the Golden-winged Warbler (Vermivora chrysoptera). I selected 27 aspen-dominated forest stands in northern Wisconsin with nine stands in each of three legacy tree retention treatments (conifer retention, hardwood retention, and clearcuts or no retention) across a chronosequence (4-36 years post-harvest). Conifer retention stands had greater legacy tree and all tree species biomass but lower regenerating tree biomass than clearcuts. Coniferous but not hardwood legacy trees appeared to suppress regenerating tree biomass. I evaluated the floristic quality of the understory plant assemblage by estimating the mean coefficient of conservatism (C). Mean C was lower in young stands than in middle-age or old stands; there was a marginally significant (p=0.058) interaction effect between legacy tree retention treatment and stand age. Late-seral plant species were positively associated with stand age and legacy tree diameter or age revealing an important relationship between legacy tree retention and stand development. Bird species richness was greatest in stands with hardwood retention particularly early in stand development. Six conservation priority bird species were indicators of legacy tree retention or clearcuts. Retention of legacy trees in aspen stands provided higher quality nest habitat for the Golden-winged Warbler than clearcuts based on high pairing success and nesting activity. Retention of hardwoods, particularly northern red oak (Quercus rubra), yielded the most consistent positive effects in this study with the highest bird species richness and the highest quality habitat for the Golden-winged Warbler. This treatment maintained stand biomass comparable to clearcuts and did not suppress regenerating tree biomass. In conclusion, legacy tree retention can enhance even-aged management techniques to produce a win-win scenario for the conservation of declining bird species and late-seral understory plants and for production of woody biomass feedstock from naturally regenerating aspen forests.