arXiv subjects

Shinichiro Shirota

Publications and source records attributed to Shinichiro Shirota.

13 recordsLinked to original sources

arXiv2026

Assessing Preferential Sampling in Retail Survival Data: A Bayesian Joint LGCP and Spatial Probit Model for Mini-Supermarket Closure in Tokyo

Retail store locations are strategically selected rather than randomly distributed, potentially inducing preferential sampling when the latent spatial factors governing placement also affect store survival. We propose a Bayesian hierarchical model that jointly combines a log-Gaussian Cox process for store locations with a probit regression for binary survival outcomes. The two components share a Gaussian process spatial effect, with a loading parameter measuring the association between the latent drivers of store placement and survival. To enable efficient inference for approximately 1,000 observations, we use a nearest-neighbor Gaussian process approximation and a Metropolis-within-Gibbs algorithm. We apply the model to 999 mini-supermarkets in Tokyo's 23 special wards, including 897 operating and 102 closed stores, using seven spatial covariates and a 3,471-point integration grid. The estimated loading is close to zero, with its credible interval including zero, providing no clear evidence of residual preferential sampling. Regression estimates are also stable across models with and without preferential sampling. Simulations show that the method can distinguish absent from strong preferential sampling. Proximity to full-scale supermarkets is the most robust predictor of closure risk, consistent with competitive substitution.

stat.ME↗

arXiv2025

Fast spatio-temporally varying coefficient modeling with reluctant interaction selection

Spatially and temporally varying coefficient (STVC) models are currently attracting attention as a flexible tool to explore the spatio-temporal patterns in regression coefficients. However, these models often struggle with balancing computational efficiency and model flexibility. To address this challenge, this study develops a fast and flexible method for STVC modeling. For enhanced flexibility in modeling, we assume multiple processes in each varying coefficient, including purely spatial, purely temporal, and spatio-temporal interaction processes with or without time cyclicity. While considering multiple processes can be time consuming, we combine a pre-conditioning method with a model selection procedure, inspired by reluctant interaction modeling. This approach allows us to computationally efficiently select and specify the latent space-time structure. Monte Carlo experiments demonstrate that the proposed method outperforms alternatives in terms of coefficient estimation accuracy and computational efficiency. Finally, we apply the proposed method to crime analysis using a sample size of 279,360, confirming that the proposed method provides reasonable estimates of varying coefficients. The STVC model is implemented in an R package spmoran.

stat.ME↗

arXiv2022

Preferential Sampling for Bivariate Spatial Data

Preferential sampling provides a formal modeling specification to capture the effect of bias in a set of sampling locations on inference when a geostatistical model is used to explain observed responses at the sampled locations. In particular, it enables modification of spatial prediction adjusted for the bias. Its original presentation in the literature addressed assessment of the presence of such sampling bias while follow on work focused on regression specification to improve spatial interpolation under such bias. All of the work in the literature to date considers the case of a univariate response variable at each location, either continuous or modeled through a latent continuous variable. The contribution here is to extend the notion of preferential sampling to the case of bivariate response at each location. This exposes sampling scenarios where both responses are observed at a given location as well as scenarios where, for some locations, only one of the responses is recorded. That is, there may be different sampling bias for one response than for the other. It leads to assessing the impact of such bias on co-kriging. It also exposes the possibility that preferential sampling can bias inference regarding dependence between responses at a location. We develop the idea of bivariate preferential sampling through various model specifications and illustrate the effect of these specifications on prediction and dependence behavior. We do this both through simulation examples as well as with a forestry dataset that provides mean diameter at breast height (MDBH) and trees per hectare (TPH) as the point-referenced bivariate responses.

stat.ME↗

arXiv2020

Analyzing Car Thefts and Recoveries with Connections to Modeling Origin-Destination Point Patterns

For a given region, we have a dataset composed of car theft locations along with a linked dataset of recovery locations which, due to partial recovery, is a relatively small subset of the set of theft locations. For an investigator seeking to understand the behavior of car thefts and recoveries in the region, several questions are addressed. Viewing the set of theft locations as a point pattern, can we propose useful models to explain the pattern? What types of predictive models can be built to learn about recovery location given theft location? Can the dependence between theft locations and recovery locations be formalized? Can the flow between theft sites and recovery sites be captured? Origin-destination modeling offers a natural framework for such problems. However, here the data is not for areal units but rather is a pair of point patterns, with the recovery point pattern only partially observed. We offer modeling approaches for investigating the questions above and apply the approaches to two datasets. One is small from the state of Neza in Mexico with areal covariate information regarding population features and crime type. A second, much larger one, is from Belo Horizonte in Brazil but lacks covariates.

stat.AP↗

arXiv2019

Clarifying species dependence under joint species distribution modeling

Joint species distribution modeling is attracting increasing attention these days, acknowledging the fact that individual level modeling fails to take into account expected dependence/interaction between species. These models attempt to capture species dependence through an associated correlation matrix arising from a set of latent multivariate normal variables. However, these associations offer little insight into dependence behavior between species at sites. We focus on presence/absence data using joint species modeling which incorporates spatial dependence between sites. For pairs of species, we emphasize the induced odds ratios (along with the joint probabilities of occurrence); they provide much clearer understanding of joint presence/absence behavior. In fact, we propose a spatial odds ratio surface over the region of interest to capture how dependence varies over the region. We illustrate with a dataset from the Cape Floristic Region of South Africa consisting of more than 600 species at more than 600 sites. We present the spatial distribution of odds ratios for pairs of species that are positively correlated and pairs that are negatively correlated under the joint species distribution model. The multivariate normal covariance matrix associated with a collection of species is only a device for creating dependence among species but it lacks interpretation. By considering odds ratios, the quantitative ecologist will be able to better appreciate the practical dependence between species that is implicit in these joint species distribution modeling specifications.

stat.ME↗

arXiv2019

Conjugate Nearest Neighbor Gaussian Process Models for Efficient Statistical Interpolation of Large Spatial Data

A key challenge in spatial statistics is the analysis for massive spatially-referenced data sets. Such analyses often proceed from Gaussian process specifications that can produce rich and robust inference, but involve dense covariance matrices that lack computationally exploitable structures. The matrix computations required for fitting such models involve floating point operations in cubic order of the number of spatial locations and dynamic memory storage in quadratic order. Recent developments in spatial statistics offer a variety of massively scalable approaches. Bayesian inference and hierarchical models, in particular, have gained popularity due to their richness and flexibility in accommodating spatial processes. Our current contribution is to provide computationally efficient exact algorithms for spatial interpolation of massive data sets using scalable spatial processes. We combine low-rank Gaussian processes with efficient sparse approximations. Following recent work by [1], we model the low-rank process using a Gaussian predictive process (GPP) and the residual process as a sparsity-inducing nearest-neighbor Gaussian process (NNGP). A key contribution here is to implement these models using exact conjugate Bayesian modeling to avoid expensive iterative algorithms. Through the simulation studies, we evaluate performance of the proposed approach and the robustness of our models, especially for long range prediction. We implement our approaches for remotely sensed light detection and ranging (LiDAR) data collected over the US Forest Service Tanana Inventory Unit (TIU) in a remote portion of Interior Alaska.

stat.ME↗

arXiv2019

Preferential sampling for presence/absence data and for fusion of presence/absence data with presence-only data

Presence/absence data and presence-only data are the two customary sources for learning about species distributions over a region. We illuminate the fundamental modeling differences between the two types of data. Most simply, locations are considered as fixed under presence/absence data; locations are random under presence-only data. The definition of "probability of presence" is incompatible between the two. So, we take issue with modeling strategies in the literature which ignore this incompatibility, which assume that presence/absence modeling can be induced from presence-only specifications and therefore, that fusion of presence-only and presence/absence data sources is routine. We argue that presence/absence data should be modeled at point level. That is, we need to specify a surface which provides the probability of presence at any location in the region. A realization from this surface is a binary map yielding the results of Bernoulli trials across all locations. Presence-only data should be modeled as a point pattern driven by specification of an intensity function. We further argue that, with just presence/absence data, preferential sampling, using a shared process perspective, can improve our estimated presence/absence surface and prediction of presence. We also argue that preferential sampling can enable a probabilistically coherent fusion of the two data types. We illustrate with two real datasets, one presence/absence, one presence-only for invasive species presence in New England in the United States. We demonstrate that potential bias in sampling locations can affect inference with regard to presence/absence and show that inference can be improved with preferential sampling ideas. We also provide a probabilistically coherent fusion of the two datasets to again improve inference with regard to presence/absence.

stat.ME↗

arXiv2018

Scalable Inference for Space-Time Gaussian Cox Processes

The log-Gaussian Cox process is a flexible and popular class of point pattern models for capturing spatial and space-time dependence for point patterns. Model fitting requires approximation of stochastic integrals which is implemented through discretization over the domain of interest. With fine scale discretization, inference based on Markov chain Monte Carlo is computationally burdensome because of the cost of matrix decompositions and storage, such as the Cholesky, for high dimensional covariance matrices associated with latent Gaussian variables. This article addresses these computational bottlenecks by combining two recent developments: (i) a data augmentation strategy that has been proposed for space-time Gaussian Cox processes that is based on exact Bayesian inference and does not require fine grid approximations for infinite dimensional integrals, and (ii) a recently developed family of sparsity-inducing Gaussian processes, called nearest-neighbor Gaussian processes, to avoid expensive matrix computations. Our inference is delivered within the fully model-based Bayesian paradigm and does not sacrifice the richness of traditional log-Gaussian Cox processes. We apply our method to crime event data in San Francisco and investigate the recovery of the intensity surface.

stat.CO↗

arXiv2018

Spatial Joint Species Distribution Modeling using Dirichlet Processes

Species distribution models usually attempt to explain presence-absence or abundance of a species at a site in terms of the environmental features (socalled abiotic features) present at the site. Historically, such models have considered species individually. However, it is well-established that species interact to influence presence-absence and abundance (envisioned as biotic factors). As a result, there has been substantial recent interest in joint species distribution models with various types of response, e.g., presence-absence, continuous and ordinal data. Such models incorporate dependence between species response as a surrogate for interaction. The challenge we focus on here is how to address such modeling in the context of a large number of species (e.g., order 102) across sites numbering in the order of 102 or 103 when, in practice, only a few species are found at any observed site. Again, there is some recent literature to address this; we adopt a dimension reduction approach. The novel wrinkle we add here is spatial dependence. That is, we have a collection of sites over a relatively small spatial region so it is anticipated that species distribution at a given site would be similar to that at a nearby site. Specifically, we handle dimension reduction through Dirichlet processes joined with spatial dependence through Gaussian processes. We use both simulated data and a plant communities dataset for the Cape Floristic Region (CFR) of South Africa to demonstrate our approach. The latter consists of presence-absence measurements for 639 tree species on 662 locations. Through both data examples we are able to demonstrate improved predictive performance using the foregoing specification.

stat.ME↗

arXiv2016

Approximate Marginal Posterior for Log Gaussian Cox Processes

The log Gaussian Cox process is a flexible class of Cox processes, whose intensity surface is stochastic, for incorporating complex spatial and time structure of point patterns. The straightforward inference based on Markov chain Monte Carlo is computationally heavy because the computational cost of inverse or Cholesky decomposition of high dimensional covariance matrices of Gaussian latent variables is cubic order of their dimension. Furthermore, since hyperparameters for Gaussian latent variables have high correlations with sampled Gaussian latent processes themselves, standard Markov chain Monte Carlo strategies are inefficient. In this paper, we propose an efficient and scalable computational strategy for spatial log Gaussian Cox processes. The proposed algorithm is based on pseudo-marginal Markov chain Monte Carlo approach. Based on this approach, we propose estimation of approximate marginal posterior for parameters and comprehensive model validation strategies. We provide details for all of the above along with some simulation investigation for univariate and multivariate settings and analysis of a point pattern of tree data exhibiting positive and negative interaction between different species.

stat.CO↗

arXiv2016

Inference for log Gaussian Cox processes using an approximate marginal posterior

The log Gaussian Cox process is a flexible class of point pattern models for capturing spatial and spatio-temporal dependence for point patterns. Model fitting requires approximation of stochastic integrals which is implemented through discretization of the domain of interest. With fine scale discretization, inference based on Markov chain Monte Carlo is computationally heavy because of the cost of repeated iteration or inversion or Cholesky decomposition (cubic order) of high dimensional covariance matrices associated with latent Gaussian variables. Furthermore, hyperparameters for latent Gaussian variables have strong dependence with sampled latent Gaussian variables. Altogether, standard Markov chain Monte Carlo strategies are inefficient and not well behaved. In this paper, we propose an efficient computational strategy for fitting and inferring with spatial log Gaussian Cox processes. The proposed algorithm is based on a pseudo-marginal Markov chain Monte Carlo approach. We estimate an approximate marginal posterior for parameters of log Gaussian Cox processes and propose comprehensive model inference strategy. We provide details for all of the above along with some simulation investigation for the univariate and multivariate settings. As an example, we present an analysis of a point pattern of locations of three tree species, exhibiting positive and negative interaction between different species.

stat.CO↗

arXiv2016

Space and circular time log Gaussian Cox processes with application to crime event data

We view the locations and times of a collection of crime events as a space-time point pattern. So, with either a nonhomogeneous Poisson process or with a more general Cox process, we need to specify a space-time intensity. For the latter, we need a \emph{random} intensity which we model as a realization of a spatio-temporal log Gaussian process. Importantly, we view time as circular not linear, necessitating valid separable and nonseparable covariance functions over a bounded spatial region crossed with circular time. In addition, crimes are classified by crime type. Furthermore, each crime event is recorded by day of the year which we convert to day of the week marks. The contribution here is to develop models to accommodate such data. Our specifications take the form of hierarchical models which we fit within a Bayesian framework. In this regard, we consider model comparison between the nonhomogeneous Poisson process and the log Gaussian Cox process. We also compare separable vs. nonseparable covariance specifications. Our motivating dataset is a collection of crime events for the city of San Francisco during the year 2012. We have location, hour, day of the year, and crime type for each event. We investigate models to enhance our understanding of the set of incidences.

stat.AP↗

arXiv2016

Approximate Bayesian Computation and Model Validation for Repulsive Spatial Point Processes

In many applications involving spatial point patterns, we find evidence of inhibition or repulsion. The most commonly used class of models for such settings are the Gibbs point processes. A recent alternative, at least to the statistical community, is the determinantal point process. Here, we examine model fitting and inference for both of these classes of processes in a Bayesian framework. While usual MCMC model fitting can be available, the algorithms are complex and are not always well behaved. We propose using approximate Bayesian computation (ABC) for such fitting. This approach becomes attractive because, though likelihoods are very challenging to work with for these processes, generation of realizations given parameter values is relatively straightforward. As a result, the ABC fitting approach is well-suited for these models. In addition, such simulation makes them well-suited for posterior predictive inference as well as for model assessment. We provide details for all of the above along with some simulation investigation and an illustrative analysis of a point pattern of tree data exhibiting repulsion. R-code and datasets are included in the supplementary material.

stat.CO↗