pith. sign in

arxiv: 2605.19100 · v1 · pith:GGU2BAIPnew · submitted 2026-05-18 · 📊 stat.CO · stat.AP· stat.ME

ldmppr: Location Dependent Marked Point Processes in R

Lane Drew , Andee Kaplan This is my paper

Pith reviewed 2026-05-20 07:37 UTC · model grok-4.3

classification 📊 stat.CO stat.APstat.ME
keywords marked point processesspatial statisticspoint process simulationlocation dependenceR packagemark-location dependencegoodness of fit
0
0 comments X

The pith

A new R package models marked point processes allowing dependence between marks and their locations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a framework and R package for marked spatial point processes in which marks can depend on locations instead of assuming independence. This independence assumption has been standard but often fails in real applications such as forestry. The package supplies methods to estimate the dependence, simulate new patterns, check goodness of fit, and visualize results. A sympathetic reader would care because it makes it possible to generate point patterns that better reflect observed data where location influences mark values.

Core claim

We present ldmppr, an R package for estimating, evaluating, simulating from, and visualizing location-dependent marked spatial point processes. The package implements a practical framework for generating marked point processes that include dependence between the marks and locations, discusses the supporting theory, and demonstrates use on real data to produce realistic patterns given a reference or chosen parameters.

What carries the argument

The location-dependent marked point process framework realized in the R package, which employs a tractable parametric form to represent and estimate dependence between marks and locations.

If this is right

  • Simulation of new point patterns becomes feasible from either a reference pattern or user-specified parameters that include location-mark dependence.
  • Goodness-of-fit tests can now be performed for models that allow dependence between marks and locations.
  • Parameter estimation and visualization are supported directly from observed data exhibiting such dependence.
  • Users can generate more realistic spatial patterns for applications where the independence assumption does not hold.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same parametric dependence structure could be adapted to model temporal marked point processes with time-dependent marks.
  • Extensions might combine the framework with non-parametric methods to relax the need for a fully specified parametric form.
  • The approach suggests testing whether similar dependence modeling improves accuracy in other spatial domains such as ecology or epidemiology.

Load-bearing premise

Dependence between marks and locations can be captured by a tractable parametric form that is estimable from typical real-world data sets and is correctly realized by the package implementation.

What would settle it

Apply the package to a forestry or similar data set, fit the model, then simulate many realizations and check whether the simulated mark-location dependence matches the original data within sampling variation.

Figures

Figures reproduced from arXiv: 2605.19100 by Andee Kaplan, Lane Drew.

Figure 1
Figure 1. Figure 1: Combined global envelope test for the realizations from the fitted process. Solid black lines represent the reference process, dashed black lines represent a homogeneous Poisson process (or CSR), and the colored band represents the global envelope for the simulated datasets at the α = .05 level. Reference values outside the envelope are highlighted in red and suggest a poor fit. The R Journal Vol. XX/YY, A… view at source ↗
Figure 2
Figure 2. Figure 2: Combined global envelope test for the realizations from the improved fitted process. As in [PITH_FULL_IMAGE:figures/full_fig_p022_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Plots a) - c) provide a comparison of a realization from the improved estimated process with the original reference dataset and a realization from the initial estimated process. Plot d) shows the corresponding observed mark distributions from the reference dataset and the simulation realizations. self-correcting process estimation, mark-model training with cross-validation/tuning, and goodness-of-fit simul… view at source ↗
read the original abstract

In this article, we present $\textbf{ldmppr}$, an R package for estimating, evaluating, simulating from, and visualizing location-dependent marked spatial point processes. To date, it has commonly been assumed that the marks associated with a point process are independent of the locations. However, when dealing with many point processes, such as those arising in forestry applications, the independence assumption proves unreasonable. We introduce a practical framework for generating marked point processes with dependence between the marks and locations. We provide a brief discussion of the theory underpinning our modeling approach and outline the use of the package in a typical scenario involving real data. We highlight the functionality of the package for both generating from and assessing the goodness-of-fit of a given model, enabling users to generate realistic point patterns given a reference pattern or parameter values of interest.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript presents the ldmppr R package for estimating, evaluating, simulating from, and visualizing location-dependent marked spatial point processes. It challenges the standard independence assumption between marks and locations (common in forestry and similar applications), introduces a practical parametric framework for modeling such dependence, provides a brief theory discussion, and demonstrates package usage via a real-data example with emphasis on generation from reference patterns or parameters and goodness-of-fit assessment.

Significance. If the implementation and framework hold, the package supplies a needed practical tool for spatial statistics applications where mark-location dependence is realistic rather than ignorable. The focus on simulation and GOF tools could enable more accurate pattern generation and model checking in applied settings. Credit is due for releasing an R implementation that directly addresses a common modeling gap, though the absence of detailed validation limits immediate impact.

major comments (2)
  1. [Theory discussion] Theory discussion (brief section on modeling approach): The specific parametric form used to capture dependence between marks and locations is not stated (e.g., no equations for the conditional mark distribution, whether linear, kernel-based, or otherwise). This is load-bearing for the central claim of a 'practical framework' that realizes realistic dependence without hidden restrictions, as it prevents evaluation against the stress-test concern that the parametrization may implicitly limit the coupling structure.
  2. [Real-data example] Real-data example and package functionality sections: No recovery experiments, parameter recovery simulations, or comparisons to established marked point process models (e.g., those with arbitrary mark-location kernels) are reported. This undermines the claim that the framework and R implementation are estimable from typical data sets and correctly realize the dependence without unstated constraints.
minor comments (2)
  1. Add references to standard literature on marked point processes (e.g., works on mark correlation functions or inhomogeneous marked processes) to better situate the contribution.
  2. [Package usage outline] Clarify the exact input formats and output objects for the simulation and visualization functions in the usage outline to aid reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed comments on our manuscript. We address each major comment below and indicate the revisions we will make to strengthen the presentation of the ldmppr package.

read point-by-point responses

  1. Referee: [Theory discussion] Theory discussion (brief section on modeling approach): The specific parametric form used to capture dependence between marks and locations is not stated (e.g., no equations for the conditional mark distribution, whether linear, kernel-based, or otherwise). This is load-bearing for the central claim of a 'practical framework' that realizes realistic dependence without hidden restrictions, as it prevents evaluation against the stress-test concern that the parametrization may implicitly limit the coupling structure.

    Authors: We appreciate the referee pointing out this gap in the theory section. The current manuscript provides only a high-level outline of the modeling approach without the explicit parametric equations for the conditional mark distribution. In the revised manuscript we will insert the specific functional form (including the relevant equations) used to model the dependence between marks and locations. This addition will make the framework's assumptions transparent and allow readers to evaluate its flexibility directly. revision: yes

  2. Referee: [Real-data example] Real-data example and package functionality sections: No recovery experiments, parameter recovery simulations, or comparisons to established marked point process models (e.g., those with arbitrary mark-location kernels) are reported. This undermines the claim that the framework and R implementation are estimable from typical data sets and correctly realize the dependence without unstated constraints.

    Authors: We acknowledge that the manuscript demonstrates package usage via a real-data example but does not include parameter-recovery simulations or systematic comparisons with other marked point process models. To address this concern, the revised version will add a short simulation study illustrating parameter recovery under the proposed model, together with a brief discussion relating the framework to existing approaches that allow more general mark-location dependence. These additions will provide direct evidence of estimability from typical data sets. revision: yes

Circularity Check

0 steps flagged

Software implementation with no circular derivation chain

full rationale

The paper presents an R package for estimating, simulating, and visualizing location-dependent marked point processes. It introduces a practical framework and provides a brief theory discussion plus a real-data example, but contains no mathematical derivations, equations, or predictions that reduce by construction to fitted parameters, self-definitions, or self-citation chains. The contribution is the software realization itself rather than any claimed first-principles result or statistical prediction, making the work self-contained against external benchmarks with no load-bearing circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The work rests on standard spatial point process theory plus the domain assumption that mark-location dependence is both present and modelable in applied data; no free parameters or invented entities are introduced in the abstract.

axioms (1)
  • domain assumption Marks associated with points in a spatial process can exhibit dependence on the point locations.
    The abstract explicitly contrasts this with the common independence assumption and states that the independence assumption proves unreasonable for many processes such as forestry.

pith-pipeline@v0.9.0 · 5662 in / 1290 out tokens · 36282 ms · 2026-05-20T07:37:07.211533+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

32 extracted references · 32 canonical work pages

  1. [1]

    Baddeley and R

    A. Baddeley and R. Turner. spatstat : An R package for analyzing spatial point patterns. Journal of Statistical Software, 12 0 (6): 0 1--42, 2005. doi:10.18637/jss.v012.i06

    work page doi:10.18637/jss.v012.i06 2005

  2. [2]

    Baddeley, E

    A. Baddeley, E. Rubak, and R. Turner. Spatial Point Patterns : Methodology and Applications with R . Chapman and Hall/CRC , New York, Nov. 2015. ISBN 978-0-429-16170-4. doi:10.1201/b19708

    work page doi:10.1201/b19708 2015

  3. [3]

    F. L. Bayisa, M. dahl, P. Ryd \'e n, and O. Cronie. Regularised Semi-parametric Composite Likelihood Intensity Modelling of a Swedish Spatial Ambulance Call Point Pattern . Journal of Agricultural, Biological and Environmental Statistics, 28 0 (4): 0 664--683, Dec. 2023. ISSN 1537-2693. doi:10.1007/s13253-023-00534-5

    work page doi:10.1007/s13253-023-00534-5 2023

  4. [4]

    L. Breiman. Random Forests . Machine Learning, 45 0 (1): 0 5--32, Oct. 2001. ISSN 1573-0565. doi:10.1023/A:1010933404324

    work page doi:10.1023/a:1010933404324 2001

  5. [5]

    Chen and C

    T. Chen and C. Guestrin. XGBoost : A Scalable Tree Boosting System . In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , KDD '16, pages 785--794, New York, NY, USA, Aug. 2016. Association for Computing Machinery. ISBN 978-1-4503-4232-2. doi:10.1145/2939672.2939785

    work page doi:10.1145/2939672.2939785 2016

  6. [6]

    T. Chen, T. He, M. Benesty, V. Khotilovich, Y. Tang, H. Cho, K. Chen, R. Mitchell, I. Cano, T. Zhou, M. Li, J. Xie, M. Lin, Y. Geng, Y. Li, J. Yuan, and D. Cortes. Xgboost: Extreme Gradient Boosting , 2026

    work page 2026

  7. [7]

    M. A. Contreras, D. Affleck, and W. Chung. Evaluating tree competition indices as predictors of basal area increment in western Montana forests. Forest Ecology and Management, 262 0 (11): 0 1939--1949, Dec. 2011. ISSN 0378-1127. doi:10.1016/j.foreco.2011.08.031

    work page doi:10.1016/j.foreco.2011.08.031 1939

  8. [8]

    D. J. Daley and D. Vere-Jones . An Introduction to the Theory of Point Processes. Springer, New York, NY, 1 edition, 1988. ISBN 978-0-387-96666-3

    work page 1988

  9. [9]

    P. J. Diggle. Statistical Analysis of Spatial and Spatio-Temporal Point Patterns . Chapman and Hall/CRC , New York, 3 edition, July 2013. ISBN 978-0-429-09809-3. doi:10.1201/b15326

    work page doi:10.1201/b15326 2013

  10. [10]

    P. J. Diggle and R. J. Gratton. Monte Carlo Methods of Inference for Implicit Statistical Models . Journal of the Royal Statistical Society: Series B (Methodological), 46 0 (2): 0 193--212, Jan. 1984. ISSN 0035-9246. doi:10.1111/j.2517-6161.1984.tb01290.x

    work page doi:10.1111/j.2517-6161.1984.tb01290.x 1984

  11. [11]

    Drew and A

    L. Drew and A. Kaplan. Ldmppr: Estimate and Simulate from Location Dependent Marked Point Processes , 2025

    work page 2025

  12. [12]

    A Bayesian Record Linkage Approach to Applications in Tree Demography Using Overlapping LiDAR Scans

    L. Drew, A. Kaplan, and I. Breckheimer. Data from " A Bayesian Record Linkage Approach to Applications in Tree Demography Using Overlapping LiDAR Scans ", 2024

    work page 2024

  13. [13]

    L. Drew, A. Kaplan, and I. Breckheimer. A Bayesian Record Linkage Approach to Applications in Tree Demography Using Overlapping LiDAR Scans . The Annals of Applied Statistics, 0 0 (0): 0 1--26, June 2025

    work page 2025

  14. [14]

    D. S. Harte. PtProcess : An R package for modelling marked point processes indexed by time. Journal of Statistical Software, 35 0 (8): 0 1--32, 2010. doi:10.18637/jss.v035.i08

    work page doi:10.18637/jss.v035.i08 2010

  15. [15]

    Isham and M

    V. Isham and M. Westcott. A self-correcting point process. Stochastic Processes and their Applications, 8 0 (3): 0 335--347, May 1979. ISSN 0304-4149. doi:10.1016/0304-4149(79)90008-5

    work page doi:10.1016/0304-4149(79)90008-5 1979

  16. [16]

    S. G. Johnson. The NLopt Nonlinear-Optimization Package , 2008

    work page 2008

  17. [17]

    Kaelo and M

    P. Kaelo and M. M. Ali. Some Variants of the Controlled Random Search Algorithm for Global Optimization . Journal of Optimization Theory and Applications, 130 0 (2): 0 253--264, Aug. 2006. ISSN 1573-2878. doi:10.1007/s10957-006-9101-0

    work page doi:10.1007/s10957-006-9101-0 2006

  18. [18]

    G. O. Mohler, M. B. Short, P. J. Brantingham, F. P. Schoenberg, and G. E. Tita. Self- Exciting Point Process Modeling of Crime . Journal of the American Statistical Association, 106 0 (493): 0 100--108, Mar. 2011. ISSN 0162-1459. doi:10.1198/jasa.2011.ap09546

    work page doi:10.1198/jasa.2011.ap09546 2011

  19. [19]

    M ller and R

    J. M ller and R. P. Waagepetersen. Statistical Inference and Simulation for Spatial Point Processes . Chapman and Hall/CRC , New York, Sept. 2003. ISBN 978-0-203-49693-0. doi:10.1201/9780203496930

    work page doi:10.1201/9780203496930 2003

  20. [20]

    M ller, M

    J. M ller, M. Ghorbani, and E. Rubak. Mechanistic spatio-temporal point process models for marked point processes, with a view to forest stand data. Biometrics, 72 0 (3): 0 687--696, 2016. ISSN 1541-0420. doi:10.1111/biom.12466

    work page doi:10.1111/biom.12466 2016

  21. [21]

    Myllym \"a ki, T

    M. Myllym \"a ki, T. Mrkvi c ka, P. Grabarnik, H. Seijo, and U. Hahn. Global envelope tests for spatial processes. Journal of the Royal Statistical Society. Series B (Statistical Methodology), 79 0 (2): 0 381--404, 2017. ISSN 1369-7412

    work page 2017

  22. [22]

    J. A. Nelder and R. Mead. A Simplex Method for Function Minimization . The Computer Journal, 7 0 (4): 0 308--313, Jan. 1965. ISSN 0010-4620, 1460-2067. doi:10.1093/comjnl/7.4.308

    work page doi:10.1093/comjnl/7.4.308 1965

  23. [23]

    Pommerening and A

    A. Pommerening and A. J. S \'a nchez Meador. Tamm review: Tree interactions between myth and reality. Forest Ecology and Management, 424: 0 164--176, Sept. 2018. ISSN 0378-1127. doi:10.1016/j.foreco.2018.04.051

    work page doi:10.1016/j.foreco.2018.04.051 2018

  24. [24]

    M. Powell. The BOBYQA algorithm for bound constrained optimization without derivatives. Technical Report, Department of Applied Mathematics and Theoretical Physics, Jan. 2009

    work page 2009

  25. [25]

    W. L. Price. Global optimization by controlled random search. Journal of Optimization Theory and Applications, 40 0 (3): 0 333--348, July 1983. ISSN 1573-2878. doi:10.1007/BF00933504

    work page doi:10.1007/bf00933504 1983

  26. [26]

    S. L. Rathbun and N. Cressie. A space-time survival point process for a longleaf pine forest in southern georgia. Journal of the American Statistical Association, 89 0 (428): 0 1164--1174, 1994. ISSN 0162-1459. doi:10.2307/2290979

    work page doi:10.2307/2290979 1994

  27. [27]

    B. D. Ripley. The second-order analysis of stationary point processes. Journal of Applied Probability, 13 0 (2): 0 255--266, June 1976. ISSN 0021-9002, 1475-6072. doi:10.2307/3212829

    work page doi:10.2307/3212829 1976

  28. [28]

    B. D. Ripley. Statistical Inference for Spatial Processes . Cambridge University Press, Cambridge, 1988. ISBN 978-0-521-42420-2. doi:10.1017/CBO9780511624131

    work page doi:10.1017/cbo9780511624131 1988

  29. [29]

    T. H. Rowan. Functional Stability Analysis of Numerical Algorithms. PhD thesis, University of Texas at Austin, USA, 1990

    work page 1990

  30. [30]

    Schlather, P

    M. Schlather, P. J. Ribeiro, and P. J. Diggle. Detecting Dependence between Marks and Locations of Marked Point Processes . Journal of the Royal Statistical Society. Series B (Statistical Methodology), 66 0 (1): 0 79--93, 2004. ISSN 1369-7412

    work page 2004

  31. [31]

    M. N. M. van Lieshout. A J-Function for Marked Point Patterns . Annals of the Institute of Statistical Mathematics, 58 0 (2): 0 235--259, June 2006. ISSN 1572-9052. doi:10.1007/s10463-005-0015-7

    work page doi:10.1007/s10463-005-0015-7 2006

  32. [32]

    M. N. Wright and A. Ziegler. ranger : A fast implementation of random forests for high dimensional data in C ++ and R . Journal of Statistical Software, 77 0 (1): 0 1--17, 2017. doi:10.18637/jss.v077.i01

    work page doi:10.18637/jss.v077.i01 2017