pith. machine review for the scientific record. sign in

arxiv: 2605.11766 · v1 · submitted 2026-05-12 · 📊 stat.ME

Recognition: 2 theorem links

· Lean Theorem

Uncovering Local Heterogeneity: Local Summary Characteristics for Spatial Point Processes with Composition-Valued Marks

Clemens Baldzuhn, Matthias Eckardt

Pith reviewed 2026-05-13 05:42 UTC · model grok-4.3

classification 📊 stat.ME
keywords local indicators of mark associationcomposition-valued marksspatial point processescentered log-ratio transformationspatial heterogeneitymark associationlocal summary statistics
0
0 comments X

The pith

Local indicators of mark association using centered log-ratio transformations detect localized clusters in composition-valued spatial point processes more accurately than global statistics.

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

The paper introduces Local Indicators of Mark Association (LIMA) specifically for composition-valued marks in spatial point processes. Composition marks, which consist of non-negative components summing to a fixed total, are mapped via the centered log-ratio transformation into Euclidean space so that global association measures can be decomposed into point-specific local versions. Simulations show these clr-based local functions identify mark clusters with higher accuracy than their global counterparts. The framework is demonstrated on economic sector composition data from Castile-La Mancha, Spain, where it exposes local clustering patterns and drainage effects that global averages conceal. The authors position the extended LIMA approach as a diagnostic for non-stationary, high-dimensional marked point patterns.

Core claim

By projecting composition-valued marks into Euclidean space via the centered log-ratio transformation, the proposed LIMA functions enable the pointwise decomposition of mark association measures, thereby uncovering local spatial heterogeneity in marked point patterns that is averaged out in traditional global summaries.

What carries the argument

The clr-based LIMA functions, which are local versions of mark association measures obtained by applying centered log-ratio transformations to composition marks and computing point-specific associations.

If this is right

  • Local LIMA functions can identify point-specific mark clusters in non-stationary spatial patterns.
  • The approach supplies granular regional insights, such as localized economic drainage effects, that global metrics miss.
  • The framework serves as a diagnostic tool for high-dimensional marked point processes with constrained marks.
  • Simulation results establish consistently higher cluster detection rates for the local clr-based versions.

Where Pith is reading between the lines

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

  • The same local decomposition technique could be adapted to other constrained mark types, such as directional or positive data.
  • Extending LIMA to spatio-temporal point processes would allow tracking of evolving local associations.
  • Integrating these local measures with spatial clustering algorithms could automate detection of heterogeneous subregions.

Load-bearing premise

The centered log-ratio transformation faithfully preserves the relevant spatial dependencies among the original constrained composition marks without introducing geometric artifacts or information loss.

What would settle it

A controlled simulation containing known local composition clusters in which the clr-based LIMA functions show detection accuracy no higher than global summaries would falsify the claimed superiority.

Figures

Figures reproduced from arXiv: 2605.11766 by Clemens Baldzuhn, Matthias Eckardt.

Figure 1
Figure 1. Figure 1: Visual representation of the dependence structures for scenarios I - III. To emphasize the spatial extent of the mark distributions, point locations are shown without compositional values. The specific Dirichlet-sampled compositions for these patterns are provided in the appendix ( [PITH_FULL_IMAGE:figures/full_fig_p006_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Diagnostic analysis of Scenario I. (Left) A pattern incorrectly flagged by the global characteristic. (Middle/Right) Local analysis reveals that the significance is driven by a small, localized cluster of points with high 𝑉 3 associations, providing a granular view of the stochastic noise. counterpart 𝜏 clr,𝑗𝑗. Our primary hypotheses are twofold: (i) both measures should exhibit similar type I error rates … view at source ↗
Figure 3
Figure 3. Figure 3: Results for Scenario II. The top row contrasts the global 𝑝-value distribution with the high local detection rate within the discs. The bottom panel displays the distance-dependent nature of these local associations, highlighting how points "sense" their environment. function across a distance range 𝑟 ∈ [0, 0.25]. For each point 𝑥𝑖 in the local case, and for the pattern in the global case, 500 permutations… view at source ↗
Figure 4
Figure 4. Figure 4: Economic sector compositions (2022) for 278 municipalities with > 1000 inhabitants within the area of study Castile-La Mancha, a high plateau in central Spain [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Global summary characteristics for clr-transformed marks. (Top) Conditional mean product 𝜏 clr,𝑗𝑗. (Bottom) Mark variogram 𝛾 clr,𝑗𝑗. Observed values (black) outside the 95% envelopes indicate significant global dependence. (𝑟 ∈ [60, 80]). While these global findings provide a clear "rejection" of spatial randomness, they offer a "flat" perspective: they suggest a regional trend of clustering but fail to di… view at source ↗
Figure 6
Figure 6. Figure 6: Spatial distribution of local significance bands (𝜏 clr,𝑗𝑗 𝑖 ). Green discs indicate significant local association; red discs indicate repulsion. These plots pinpoint where sectors behave similarly to their neighbors. : Preprint submitted to Elsevier Page 10 of 17 [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Visualization of 500 samples from a Dirichlet distribution with different parametrizations corresponding to those chosen for the simulation scenarios in chapter 4. (Top row, left) A sample from a Dirichlet with 𝛼1 = (5, 5, 5). (Top row, middle): A sample with 𝛼2 = (20, 5, 5). (Top row, right) A sample with 𝛼3 = (5, 5, 20). Note that with alpha approaching one in each dimension, the distributional mass shif… view at source ↗
Figure 8
Figure 8. Figure 8: Comparison for Scenario III. The local approach (right) shows a significantly higher and more stable fraction of correctly detected dependent points compared to the global 𝑝-values (left), which exhibit higher variance. : Preprint submitted to Elsevier Page 12 of 17 [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Examples for the mark dependence structures in the three simulation scenarios with sampled compositions. Patterns are the same as in [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Results of the global test employing Shimatani’s 𝐼. : Preprint submitted to Elsevier Page 13 of 17 [PITH_FULL_IMAGE:figures/full_fig_p013_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Local associations of sector proportions. (Left) Municipalities with significant global envelope tests (red stars). (Right) Point-specific results for a northern municipality, showing significant association in agriculture at short and long distances. : Preprint submitted to Elsevier Page 14 of 17 [PITH_FULL_IMAGE:figures/full_fig_p014_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Significance bands obtained from employing 𝛾 clr,𝑗𝑗 𝑖 in a global envelope test. : Preprint submitted to Elsevier Page 15 of 17 [PITH_FULL_IMAGE:figures/full_fig_p015_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Significance bands obtained from employing 𝜄clr,𝑗𝑗 𝑖 in a global envelope test. : Preprint submitted to Elsevier Page 16 of 17 [PITH_FULL_IMAGE:figures/full_fig_p016_13.png] view at source ↗
read the original abstract

Traditional analysis of marked spatial point processes often relies on global summary statistics, which tend to obscure local spatial heterogeneity by averaging dependencies across the entire observation window. To overcome this limitation, this paper introduces a framework for Local Indicators of Mark Association (LIMA) specifically designed for composition-valued marks. Such marks, characterized by their non-negative components and sum-to-constant constraint, require a specialized treatment within the Aitchison geometry. By employing log-ratio transformations, we project these constrained marks into a Euclidean space, enabling the point-specific decomposition of global mark characteristics. The efficacy of the proposed clr-based LIMA functions is validated through extensive simulation studies. The results demonstrate a superior capacity to detect localized mark clusters, achieving detection accuracies consistently higher than their global counterparts. The practical utility of this framework is demonstrated using an empirical dataset of economic sector compositions in Castile-La Mancha, Spain. The analysis uncovers latent economic clustering patterns and localized \textit{drainage} effects that are invisible to global metrics, providing granular insights into regional spatial dynamics. Our findings suggest that the extended LIMA framework serves as a vital diagnostic tool for high-dimensional, non-stationary marked point patterns.

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 introduces Local Indicators of Mark Association (LIMA) for spatial point processes with composition-valued marks. It applies the centered log-ratio (clr) transformation to project the constrained marks into Euclidean space, then decomposes standard global mark-association summaries (such as cross-type K-functions or pair-correlation functions) into pointwise local versions. The framework is validated in simulation studies that report higher detection accuracy for localized mark clusters relative to global counterparts, and is demonstrated on an empirical dataset of economic sector compositions in Castile-La Mancha, Spain, where it identifies local clustering and drainage effects not visible globally.

Significance. If the simulation results hold under the reported conditions, the work supplies a practical, geometry-aware extension of existing marked-point-process tools to the compositional setting. This addresses a genuine gap in the analysis of non-stationary patterns with proportional marks, which arise in economics, ecology, and geology. The provision of both simulation benchmarks and a real-data illustration strengthens the case for adoption as a diagnostic tool.

major comments (2)
  1. [§3.2] §3.2 (Definition of clr-based LIMA): the pointwise decomposition of the global summary is presented as a direct consequence of the clr isometry, yet the manuscript does not state whether the local functions remain unbiased estimators of the underlying intensity when the mark composition varies spatially; a short derivation or reference to the corresponding global unbiasedness result would clarify this.
  2. [§4] §4 (Simulation studies): the reported detection accuracies are described as “consistently higher,” but the text supplies neither the number of Monte Carlo replicates, the precise point-process models used to generate the clustered compositions, nor standard-error bands on the accuracy figures; without these, the quantitative superiority claim cannot be fully assessed.
minor comments (2)
  1. The notation for the local LIMA functions occasionally re-uses symbols already defined for their global counterparts; a distinct subscript (e.g., LIMA_loc) would reduce ambiguity.
  2. Figure 3 (empirical maps) would benefit from an inset showing the global summary for direct visual comparison.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments and the recommendation of minor revision. We address each major comment below.

read point-by-point responses

  1. Referee: [§3.2] §3.2 (Definition of clr-based LIMA): the pointwise decomposition of the global summary is presented as a direct consequence of the clr isometry, yet the manuscript does not state whether the local functions remain unbiased estimators of the underlying intensity when the mark composition varies spatially; a short derivation or reference to the corresponding global unbiasedness result would clarify this.

    Authors: We agree that a clarification is useful. The clr map is a linear isometry, so the unbiasedness property of the global mark-association estimators carries over to the local LIMA functions. When the mark composition varies spatially, the local versions remain unbiased for the spatially varying intensity under the usual local-homogeneity approximation within the kernel support. We will insert a short derivation in the revised §3.2 that references the corresponding global unbiasedness result. revision: yes

  2. Referee: [§4] §4 (Simulation studies): the reported detection accuracies are described as “consistently higher,” but the text supplies neither the number of Monte Carlo replicates, the precise point-process models used to generate the clustered compositions, nor standard-error bands on the accuracy figures; without these, the quantitative superiority claim cannot be fully assessed.

    Authors: We thank the referee for noting these omissions. The simulation details—including the number of Monte Carlo replicates, the exact point-process models used to generate the clustered compositions, and standard-error bands on the accuracy figures—will be supplied in the revised §4 so that the quantitative claims can be fully assessed. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper presents LIMA functions as a direct pointwise decomposition of global mark-association summaries after applying the standard centered log-ratio (clr) transformation to map composition marks into Euclidean space. This construction follows immediately from the accepted Aitchison geometry and existing global summaries; no equation reduces a claimed prediction or result to a fitted parameter, self-definition, or load-bearing self-citation. Simulations and the empirical example serve as external validation rather than internal tautologies. The derivation chain remains self-contained against the cited standard transformations.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The framework rests on the domain assumption that Aitchison geometry and log-ratio maps are appropriate for compositional marks in spatial settings; no free parameters are mentioned and no new entities beyond the LIMA definition itself are postulated.

axioms (1)
  • domain assumption Composition-valued marks can be projected into Euclidean space via centered log-ratio transformations without distorting spatial association structure.
    Invoked to justify the definition of local indicators in the transformed space.
invented entities (1)
  • Local Indicators of Mark Association (LIMA) for composition marks no independent evidence
    purpose: Point-specific decomposition of global mark-association measures to reveal local heterogeneity.
    Newly defined functions; no independent evidence outside the paper is supplied.

pith-pipeline@v0.9.0 · 5506 in / 1368 out tokens · 136650 ms · 2026-05-13T05:42:22.217885+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.

Reference graph

Works this paper leans on

92 extracted references · 92 canonical work pages

  1. [1]

    and Pietrostefani, Elisabetta , year = 2019, journal =

    Ahlfeldt, Gabriel M. and Pietrostefani, Elisabetta , year = 2019, journal =. The

    work page 2019

  2. [2]

    Aitchison, John , year = 2003, pages =. A. Compositional

    work page 2003

  3. [3]

    , editor =

    Aitchison, J. , editor =. Simplicial. Algebraic

    work page

  4. [4]

    , year = 1986, series =

    Aitchison, J. , year = 1986, series =. The. doi:10.1007/978-94-009-4109-0 , langid =

    work page doi:10.1007/978-94-009-4109-0 1986

  5. [5]

    Anselin, Luc , year = 1995, month = apr, journal =. Local. doi:10.1111/j.1538-4632.1995.tb00338.x , urldate =

    work page doi:10.1111/j.1538-4632.1995.tb00338.x 1995

  6. [6]

    and Feldman, Maryann P

    Audretsch, David B. and Feldman, Maryann P. , year = 1996, journal =. R&

    work page 1996

  7. [7]

    Compositional

    A. Compositional. doi:10.1002/9781119976462.ch1 , urldate =

    work page doi:10.1002/9781119976462.ch1

  8. [8]

    Handbook of Spatial Statistics , author =

    Multivariate and. Handbook of Spatial Statistics , author =. doi:10.1201/9781420072884 , langid =

    work page doi:10.1201/9781420072884

  9. [9]

    Baddeley, A. J. and Moller, J. and Waagepetersen, R. , year = 2000, month = nov, journal =. Non- and. doi:10.1111/1467-9574.00144 , urldate =

    work page doi:10.1111/1467-9574.00144 2000

  10. [10]

    Baddeley, Adrian and Rubak, Ege and Turner, Rolf , year = 2016, publisher =. Spatial. doi:10.1201/b19708 , langid =

    work page doi:10.1201/b19708 2016

  11. [11]

    Spatstat:

    Baddeley, Adrian and Turner, Rolf and Rubak, Ege , year =. Spatstat:

    work page

  12. [12]

    and Hardegen, Andrew and Lawrence, Thomas and Milne, Robin K

    Baddeley, Adrian and Diggle, Peter J. and Hardegen, Andrew and Lawrence, Thomas and Milne, Robin K. and Nair, Gopalan , year = 2014, month = aug, journal =. On. doi:10.1890/13-2042.1 , urldate =

    work page doi:10.1890/13-2042.1 2014

  13. [13]

    Discussion on

    Barnard, George A , year = 1963, journal =. Discussion on. doi:10.1111/j.2517-6161.1963.tb00509.x , urldate =

    work page doi:10.1111/j.2517-6161.1963.tb00509.x 1963

  14. [14]

    , year = 1977, journal =

    Besag, Julian and Diggle, Peter J. , year = 1977, journal =. Simple. doi:10.2307/2346974 , urldate =

    work page doi:10.2307/2346974 1977

  15. [15]

    and Pebesma, Edzer and

    Bivand, Roger S. and Pebesma, Edzer and. Applied. doi:10.1007/978-1-4614-7618-4 , urldate =

    work page doi:10.1007/978-1-4614-7618-4

  16. [16]

    Gerald and

    van den Boogaart, K. Gerald and. Compositions:

    work page

  17. [17]

    Compositional

    Buccianti, Antonella and. Compositional

    work page

  18. [18]

    Campbell, N , year = 1909, journal =. The

    work page 1909

  19. [19]

    Capasso, Vincenzo and Bakstein, David , year = 2021, series =. An. doi:10.1007/978-3-030-69653-5 , urldate =

    work page doi:10.1007/978-3-030-69653-5 2021

  20. [20]

    Stochastic

    Chiu, Sung Nok and Stoyan, Dietrich and Kendall, Wilfrid S and Mecke, Joseph , year = 2013, publisher =. Stochastic. doi:10.1002/9781118658222 , langid =

    work page doi:10.1002/9781118658222 2013

  21. [21]

    Coeurjolly, Jean-Fran. A. International Statistical Review , volume =. doi:10.1111/insr.12205 , urldate =

    work page doi:10.1111/insr.12205

  22. [22]

    Analysis of

    Cressie, Noel and Collins, Linda Brant , year = 2001, month = mar, journal =. Analysis of. doi:10.1198/108571101300325292 , urldate =

    work page doi:10.1198/108571101300325292 2001

  23. [23]

    Patterns in

    Cressie, Noel and Collins, Linda Brant , year = 2001, month = aug, journal =. Patterns in. doi:10.1002/nav.1022 , urldate =

    work page doi:10.1002/nav.1022 2001

  24. [24]

    Statistics for

    Cressie, Noel , year = 1993, series =. Statistics for

    work page 1993

  25. [25]

    Discussion of the

    Cronie, Ottmar and Jansson, Julia and Konstantinou, Konstantinos , year = 2024, month = jun, journal =. Discussion of the. doi:10.1007/s13253-024-00606-0 , urldate =

    work page doi:10.1007/s13253-024-00606-0 2024

  26. [26]

    Inhomogeneous

    Cronie, Ottmar and Moradi, Mehdi and Mateu, Jorge , year = 2020, month = sep, journal =. Inhomogeneous. doi:10.1007/s11222-020-09942-w , urldate =

    work page doi:10.1007/s11222-020-09942-w 2020

  27. [27]

    Daley, Daryl J. and. An

    work page

  28. [28]

    Daley, Daryl J. and. An. doi:10.1007/978-0-387-49835-5 , langid =

    work page doi:10.1007/978-0-387-49835-5

  29. [29]

    and Zerubia, J

    Descombes, X. and Zerubia, J. , year = 2002, month = sep, journal =. Marked. doi:10.1109/MSP.2002.1028354 , urldate =

    work page doi:10.1109/msp.2002.1028354 2002

  30. [30]

    Journal of Agricultural, Biological and Environmental Statistics , year=

    Eckardt, Matthias and Moradi, Mehdi , title=. Journal of Agricultural, Biological and Environmental Statistics , year=

    work page

  31. [31]

    International Statistical Review , volume =

    Eckardt, Matthias and Comas, Carles and Mateu, Jorge , title =. International Statistical Review , volume =. 2025 , doi =

    work page 2025

  32. [32]

    2024 , eprint=

    Second-Order Characteristics for Spatial Point Processes with Graph-Valued Marks , author=. 2024 , eprint=

    work page 2024

  33. [33]

    and Stoyan, D

    Bonneau, F. and Stoyan, D. , title =. JGR Solid Earth , volume =

    work page

  34. [34]

    and Delicado, P

    Comas, C. and Delicado, P. and Mateu, J. , title=. Test , year=

    work page

  35. [35]

    2021 , pages=

    Ghorbani, Mohammad and Cronie, Ottmar and Mateu, Jorge and Yu, Jun , title=. 2021 , pages=. doi:10.1007/s11749-020-00730-2 , journal=

    work page doi:10.1007/s11749-020-00730-2 2021

  36. [36]

    Journal of Agricultural, Biological and Environmental Statistics , year=

    Eckardt, Matthias and Moradi, Mehdi , title=. Journal of Agricultural, Biological and Environmental Statistics , year=. doi:10.1007/s13253-024-00613-1 , url=

    work page doi:10.1007/s13253-024-00613-1

  37. [37]

    , year = 1979, journal =

    Diggle, Peter J. , year = 1979, journal =. On. doi:10.2307/2529938 , urldate =

    work page doi:10.2307/2529938 1979

  38. [38]

    and Moraga, Paula and Rowlingson, Barry and Taylor, Benjamin M

    Diggle, Peter J. and Moraga, Paula and Rowlingson, Barry and Taylor, Benjamin M. , year = 2013, journal =. Spatial and. doi:10.1214/13-STS441 , urldate =

    work page doi:10.1214/13-sts441 2013

  39. [39]

    , year = 2013, month = jul, edition =

    Diggle, Peter J. , year = 2013, month = jul, edition =. Statistical. doi:10.1201/b15326 , urldate =

    work page doi:10.1201/b15326 2013

  40. [40]

    Dudley, R M and Bollobas, B and Fulton, W and Katok, A and Kirwan, F and Sarnak, P , year = 2002, publisher =. Real. doi:10.1017/CBO9780511755347 , langid =

    work page doi:10.1017/cbo9780511755347 2002

  41. [41]

    Duranton, Gilles and Puga, Diego , editor =. Micro-. Handbook of. doi:10.1016/S1574-0080(04)80005-1 , urldate =

    work page doi:10.1016/s1574-0080(04)80005-1

  42. [42]

    Function-

    Eckardt, Matthias and Mateu, Jorge and Moradi, Mehdi , year = 2024, month = jul, number =. Function-. arXiv , langid =:2407.07637 , primaryclass =

    work page arXiv 2024

  43. [43]

    Journal of Computational and Graphical Statistics , number=

    Local Indicators of Mark Association for Marked Spatial Point Processes , author=. Journal of Computational and Graphical Statistics , number=. 2026 , publisher=

    work page 2026

  44. [44]

    International Statistical Review , year =

    On Spatial Point Processes with Composition-Valued Marks , author =. International Statistical Review , year =

    work page

  45. [45]

    Egozcue, Juan Jos. Basic. Compositional. doi:10.1002/9781119976462.ch2 , collaborator =

    work page doi:10.1002/9781119976462.ch2

  46. [46]

    Isometric

    Egozcue, J J and. Isometric. Mathematical geology , volume =. doi:10.1023/A:1023818214614 , langid =

    work page doi:10.1023/a:1023818214614

  47. [47]

    Getis, Arthur and Ord, J. K. , year = 1992, month = jul, journal =. The. doi:10.1111/j.1538-4632.1992.tb00261.x , urldate =

    work page doi:10.1111/j.1538-4632.1992.tb00261.x 1992

  48. [48]

    Interaction

    Getis, A , year = 1984, month = feb, journal =. Interaction. doi:10.1068/a160173 , urldate =

    work page doi:10.1068/a160173 1984

  49. [49]

    Getis, Arthur , year = 1987, journal =. Second-

    work page 1987

  50. [50]

    , year = 1971, month = sep, journal =

    Glass, Leon and Tobler, Waldo R. , year = 1971, month = sep, journal =. General:. doi:10.1038/233067a0 , urldate =

    work page doi:10.1038/233067a0 1971

  51. [51]

    Afiliacion a uttimo dia de mes por sectores econ

    work page

  52. [52]

    Descargas de Datos Geogr

    work page

  53. [53]

    Compositional

    Greenacre, Michael , year = 2021, month = mar, journal =. Compositional. doi:10.1146/annurev-statistics-042720-124436 , urldate =

    work page doi:10.1146/annurev-statistics-042720-124436 2021

  54. [54]

    Statistics and

    Hartmann, K and Krois, J and Rudolph, A , year = 2023, journal =. Statistics and

    work page 2023

  55. [55]

    Tidyterra: 'tidyverse'

    Hernang. Tidyterra: 'tidyverse'

    work page

  56. [56]

    and Barbosa, M

    Hijmans, Robert J. and Barbosa, M. Terra:

    work page

  57. [57]

    Statistical

    Illian, Janine and Penttinen, Antti and Stoyan, Helga and Stoyan, Dietrich , year = 2008, publisher =. Statistical

    work page 2008

  58. [58]

    Isham, Valerie , year = 1985, publisher =. Marked. Spatial Processes and Spatial Time Series Analysis : Proceedings of the 6th

    work page 1985

  59. [59]

    Kallenberg, Olav , year = 2017, series =. Random. doi:10.1007/978-3-319-41598-7 , urldate =

    work page doi:10.1007/978-3-319-41598-7 2017

  60. [60]

    , year = 2008, edition =

    Karlin, Samuel and Taylor, Howard M. , year = 2008, edition =. A

    work page 2008

  61. [61]

    Compositional Data Analysis , author =

    The. Compositional Data Analysis , author =. 2011 , pages =. doi:10.1002/9781119976462.ch3 , langid =

    work page doi:10.1002/9781119976462.ch3 2011

  62. [62]

    Mohler, George , year = 2014, month = jul, journal =. Marked. doi:10.1016/j.ijforecast.2014.01.004 , urldate =

    work page doi:10.1016/j.ijforecast.2014.01.004 2014

  63. [63]

    Inhomogeneous

    Moradi, Mehdi and Eckardt, Matthias , year = 2025, month = may, journal =. Inhomogeneous. arXiv , langid =:2505.24501 , primaryclass =

    work page arXiv 2025

  64. [64]

    Notes on

    Moran, P A P , year = 1950, journal =. Notes on. doi:10.2307/2332142 , langid =

    work page doi:10.2307/2332142 1950

  65. [65]

    Mrkvicka, Tomas and Myllym. New. Statistics in Medicine , volume =. doi:10.1002/sim.9236 , urldate =

    work page doi:10.1002/sim.9236

  66. [66]

    Journal of Statistical Software , volume =

    Myllym. Journal of Statistical Software , volume =. doi:10.18637/jss.v111.i03 , urldate =

    work page doi:10.18637/jss.v111.i03

  67. [67]

    Myllym. Global. Journal of the Royal Statistical Society Series B: Statistical Methodology , volume =. doi:10.1111/rssb.12172 , urldate =

    work page doi:10.1111/rssb.12172

  68. [68]

    Predicting

    Ogira, Carol and Kamau, Roselynn and Kamau, Shallom and Bwoma, Bridgette Kerubo and Komora, Bonaya Kiinywi and Athiany, Henry , year = 2024, month = feb, journal =. Predicting. doi:10.11648/ijdsa.20241001.11 , urldate =

    work page doi:10.11648/ijdsa.20241001.11 2024

  69. [69]

    , year = 1983, month = jan, journal =

    Ohser, J. , year = 1983, month = jan, journal =. On. doi:10.1080/02331888308801687 , urldate =

    work page doi:10.1080/02331888308801687 1983

  70. [70]

    Mathematical

    Pearson, Karl , year = 1897, month = dec, journal =. Mathematical. doi:10.1098/rspl.1896.0076 , urldate =

    work page doi:10.1098/rspl.1896.0076

  71. [71]

    Pebesma, Edzer and Bivand, Roger and Racine, Etienne and Sumner, Michael and Cook, Ian and Keitt, Tim and Lovelace, Robin and Wickham, Hadley and Ooms, Jeroen and M. Sf:

    work page

  72. [72]

    Statistical

    Pentitinen, A and Stoyan, D , year = 1989, journal =. Statistical

    work page 1989

  73. [73]

    , year = 1992, month = nov, journal =

    Penttinen, Antti and Stoyan, Dietrich and Henttonen, Helena M. , year = 1992, month = nov, journal =. Marked. doi:10.1093/forestscience/38.4.806 , urldate =

    work page doi:10.1093/forestscience/38.4.806 1992

  74. [74]

    and Evans, Gregory W

    Platt, William J. and Evans, Gregory W. and Rathbun, Stephen L. , year = 1988, journal =. The

    work page 1988

  75. [75]

    Reinhart, Alex , year = 2018, month = aug, journal =. A. doi:10.1214/17-STS629 , urldate =

    work page doi:10.1214/17-sts629 2018

  76. [76]

    Ripley, B. D. , year = 1977, month = jan, journal =. Modelling. doi:10.1111/j.2517-6161.1977.tb01615.x , urldate =

    work page doi:10.1111/j.2517-6161.1977.tb01615.x 1977

  77. [77]

    , year = 1976, journal =

    Ripley, B.D. , year = 1976, journal =. The. doi:10.2307/3212829 , langid =

    work page doi:10.2307/3212829 1976

  78. [78]

    and Diggle, Peter J

    Schlather, Martin and Ribeiro, Paulo J. and Diggle, Peter J. , year = 2004, journal =. Detecting

    work page 2004

  79. [79]

    Schlather, Martin , year = 2001, month = feb, journal =. On the. doi:10.2307/3318604 , urldate =

    work page doi:10.2307/3318604 2001

  80. [80]

    Shimatani, Kenichiro , year = 2002, month = apr, journal =. Point. doi:10.1002/1521-4036(200204)44:3<325::AID-BIMJ325>3.0.CO;2-B , urldate =

    work page doi:10.1002/1521-4036(200204)44:3 2002

Showing first 80 references.