pith. sign in

arxiv: 1907.05802 · v1 · pith:IUOJTSS6new · submitted 2019-07-12 · 🧮 math.ST · math.PR· stat.TH

Asymptotics for Spherical Functional Autoregressions

Alessia Caponera , Domenico Marinucci This is my paper

Pith reviewed 2026-05-24 22:05 UTC · model grok-4.3

classification 🧮 math.ST math.PRstat.TH
keywords spherical functional autoregressionautoregressive kernelconsistencycentral limit theoremWasserstein distanceweak convergenceasymptotics
0
0 comments X

The pith

Estimates of the autoregressive kernel for spherical functional autoregressive processes are consistent in sup and mean-square norm and satisfy a quantitative central limit theorem.

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

This paper studies estimation for spherical functional autoregressive processes. It proves that the autoregressive kernel estimator is consistent both in the supremum norm and in mean square. It also derives a quantitative central limit theorem measuring the distance to normality in Wasserstein metric, plus a weak convergence result that needs stronger assumptions. These findings provide a foundation for statistical inference on processes that evolve on the sphere.

Core claim

The authors establish a consistency result for the kernel estimator in sup and mean-square norm, followed by a quantitative central limit theorem in Wasserstein distance, and finally a weak convergence result under more restrictive regularity conditions on the spherical functional autoregressive process and its kernel.

What carries the argument

The autoregressive kernel of the spherical functional autoregressive process, whose estimator is shown to have the stated asymptotic properties.

If this is right

  • The kernel estimator converges to the true kernel in sup norm and mean square.
  • The normalized estimation error converges to a normal limit at a quantifiable rate in Wasserstein distance.
  • Under additional regularity, the estimator satisfies a weak convergence property.
  • The results are supported by numerical simulations.

Where Pith is reading between the lines

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

  • The consistency and CLT could support construction of confidence bands for the kernel on the sphere.
  • Similar asymptotics might hold for functional autoregressions on other compact manifolds.
  • Applications could include modeling of directional time series data in geostatistics or astronomy.

Load-bearing premise

The spherical functional autoregressive process and its kernel satisfy the regularity conditions needed for the asymptotic results to hold.

What would settle it

Numerical experiments on a spherical FAR process where the Wasserstein distance to the limiting normal does not decrease as predicted by the quantitative CLT.

Figures

Figures reproduced from arXiv: 1907.05802 by Alessia Caponera, Domenico Marinucci.

Figure 1
Figure 1. Figure 1: Two realizations of sphere cross time random fields at time [PITH_FULL_IMAGE:figures/full_fig_p026_1.png] view at source ↗
read the original abstract

In this paper, we investigate a class of spherical functional autoregressive processes, and we discuss the estimation of the corresponding autoregressive kernels. In particular, we first establish a consistency result (in sup and mean-square norm), then a quantitative central limit theorem (in Wasserstein distance), and finally a weak convergence result, under more restrictive regularity conditions. Our results are validated by a small numerical investigation.

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

0 major / 2 minor

Summary. The paper investigates a class of spherical functional autoregressive processes and the estimation of the corresponding autoregressive kernels. It first establishes consistency of the estimators in supremum and mean-square norms, then a quantitative central limit theorem in Wasserstein distance, and finally a weak convergence result under more restrictive regularity conditions on the process and kernel. The theoretical results are supported by a small numerical investigation.

Significance. If the derivations hold, the results supply asymptotic theory for kernel estimation in spherical FAR models, extending functional time series methods to directional data. The quantitative CLT in Wasserstein distance and the progression from consistency to weak convergence are strengths; the numerical validation provides practical support.

minor comments (2)
  1. [Abstract] Abstract: the phrase 'under more restrictive regularity conditions' for the weak convergence result is vague; a brief indication of the additional assumptions (or a forward reference to the relevant theorem) would clarify the scope.
  2. The numerical investigation is described only as 'small'; adding details on the simulation design, sample sizes, and performance metrics would strengthen reproducibility.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary, significance assessment, and recommendation of minor revision. No specific major comments were provided in the report, so we have no individual points to address point-by-point. We are pleased that the progression of results from consistency to quantitative CLT to weak convergence, along with the numerical validation, was viewed favorably.

Circularity Check

0 steps flagged

No significant circularity; standard asymptotic derivation

full rationale

The paper derives consistency, quantitative CLT, and weak convergence results for spherical functional autoregressive processes and their kernels. No equations, fitted parameters, or predictions are visible in the abstract or summary that reduce to inputs by construction. No self-citations are invoked as load-bearing uniqueness theorems, and the derivation chain consists of standard regularity conditions and limit theorems without self-referential fitting or renaming. The work is self-contained against external benchmarks of functional time series asymptotics.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no explicit free parameters, axioms, or invented entities are stated. The regularity conditions alluded to for weak convergence are not enumerated.

pith-pipeline@v0.9.0 · 5580 in / 1045 out tokens · 30274 ms · 2026-05-24T22:05:35.860002+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

45 extracted references · 45 canonical work pages · 1 internal anchor

  1. [1]

    Asymptotics for Spherical Functional Autoregressions

    Introduction. In recent years, a lot of interest has been drawn by the statistical analysis of spherical isotropic random fields. These investigations have been motivated by a wide array of applications arising in many different areas, including in particular, Cosmology, Astrophysics, Geophysics, Climate and Atmospheric Sciences, and many others, see, e.g.,...

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  2. [2]

    Background and Notation. 2.1. Spectral Representation of Isotropic Random Fields on the Sphere.Let{T (x), x∈ S2} denote a finite variance, isotropic random field on the unit sphereS2 ={x∈ R3 : ∥x∥ = 1}, by which we mean as usual thatT (g·) d= T (·), ∀g∈ SO(3) the standard 3- dimensional group of rotations; here the identity in distribution must be understoo...

    work page

  3. [3]

    characteristic scale

    Spherical Random Fields with T emporal Dependence. We are now ready to introduce our model of interest. As usual, by space-time spherical random fields we mean a collection of random variables{T (x,t ), (x,t )∈ S2× Z} such that the application T : Ω× S2× Z→ R isℑ⊗B (S2× Z)-measurable, for some probability space(Ω,ℑ, P). The following definition is standard:...

    work page

  4. [4]

    high frequency

    Main Results. Throughout this paper, we shall assume to be able to observe the projections of the fields on the orthonormal basis{Yℓm}, i.e., we assume to observe aℓ,m(t) := ∫ S2 T (x,t )Yℓ,m(x)dx , t = 1,...,n . The estimator we shall focus on is a form of least square regression on an increasing subset of the orthonormal system{Yℓ,m} ; more precisely, we...

    work page

  5. [5]

    We now present the main arguments of our proofs, which are based on a number of technical results collected in the Appendix (Supplementary Material)

    Proofs of the Main Results. We now present the main arguments of our proofs, which are based on a number of technical results collected in the Appendix (Supplementary Material). Forℓ = 0, 1, 2,..., it is convenient to introduce theN(2ℓ+1)-dimensional vectors Yℓ;N := (aℓ,−ℓ(p + 1),...,a ℓ,ℓ(p + 1),...,a ℓ,ℓ(n))′ , εℓ;N := (aℓ,−ℓ;Z(p + 1),...,a ℓ,ℓ;Z(p + 1)...

    work page

  6. [6]

    In this section, we present some short numerical results to illustrate the models and methods that we discussed in this paper

    Some Numerical Evidence. In this section, we present some short numerical results to illustrate the models and methods that we discussed in this paper. We stress first that random fields on the sphere cross time can be very conveniently generated by combining the general features of Python with the HEALPix software (see

    work page

  7. [7]

    variance

    and https://healpix.sourceforge.io). More precisely, HEALPix (which stands for Hierarchical Equal Area and iso-Latitude Pixelation) is a multi-purpose computer software package for a high resolution numerical analysis of functions on the sphere, based on a clever tessellation scheme: the spherical surface is hierarchically partitioned into curvilinear qua...

    work page

  8. [8]

    Throught this Appendix, we assume that Conditions 8 and 13 hold

    Appendix. Throught this Appendix, we assume that Conditions 8 and 13 hold. Under these assumptions the proof that Equation (7) admits a unique stationary and isotropic solution can be given along the same lines as in [5] and it is omitted for brevity’s sake; see

    work page

  9. [9]

    for more discussion and details. Note that, under these two Conditions, the varianceCℓ can be written in terms of the coefficientsφℓ;j, j = 1,...,p , the autocorrelationsρℓ(j) = Cℓ(j)/Cℓ, j = 1,...,p , and the error varianceCℓ;Z; namely Cℓ = Cℓ;Z 1−φℓ;1ρℓ(1)−···− φℓ;pρℓ(p) > 0 , ℓ ≥ 0 . Hence, 0< Cℓ;Z Cℓ = 1−φℓ;1ρℓ(1)−···− φℓ;pρℓ(p) , and there exists a pos...

    work page

  10. [10]

    Then, (2ℓ + 1)P 2 ℓ (cosθ) = (2ℓ + 1) (√ 2 πℓ sinθ sin (ℓθ +α) +O ( ℓ−3/2 ))2 = 4 π sinθ sin2 (ℓθ +α) +O ( ℓ−1) , 0<θ<π . In view of the standard identities sinx = eix−e−ix 2i , and n−1∑ k=0 eixk = 1−eixn 1−eix , x ̸= 0 , we have L∑ ℓ=1 sin2(ℓθ +α) = L∑ ℓ=1 ( ei(ℓθ+α)−e−i(ℓθ+α) 2i )2 =−1 4 L∑ ℓ=1 [ ei2(ℓθ+α) +e−i2(ℓθ+α)− 2 ] =−ei2(θ+α) 4 (1−ei2θL 1−ei2θ )...

    work page

  11. [11]

    (2017) Testing for stationarity of functional time series in the frequency domain, arXiv preprint: 1701.01741

    Aue, A., van Delft, A. (2017) Testing for stationarity of functional time series in the frequency domain, arXiv preprint: 1701.01741

    work page arXiv 2017

  12. [12]

    (2009) Asymptotics for spherical needlets, Annals of Statistics, 37, no

    Baldi, P., Kerkyacharian, G., Marinucci, D., Picard, D. (2009) Asymptotics for spherical needlets, Annals of Statistics, 37, no. 3, 1150–1171

    work page 2009

  13. [13]

    (1999)Convergence of Probability Measures, second edition, Wiley Series in Probability and Statistics

    Billingsley, P. (1999)Convergence of Probability Measures, second edition, Wiley Series in Probability and Statistics

    work page 1999

  14. [14]

    (2017) From Schoenberg coefficients to Schoenberg functions,Constructive Ap- proximations, 45, no

    Berg, C., Porcu, E. (2017) From Schoenberg coefficients to Schoenberg functions,Constructive Ap- proximations, 45, no. 2, 217–241

    work page 2017

  15. [15]

    (2000)Linear processes in function spaces

    Bosq, D. (2000)Linear processes in function spaces. Theory and applications.Lecture Notes in Statis- tics, 149, Springer-Verlag, New York

    work page 2000

  16. [16]

    (2015) On the limiting behaviour of needlets polyspectra,Ann

    Cammarota, V., Marinucci, D. (2015) On the limiting behaviour of needlets polyspectra,Ann. Inst. Henri Poincaré Probab. Stat., 51, no. 3, 1159–1189

    work page 2015

  17. [17]

    (2018) A quantitative central limit theorem for the Euler-Poincaré characteristic of random spherical eigenfunctions,Annals of Probability, 46, n.6, 3188–3228

    Cammarota, V., Marinucci, D. (2018) A quantitative central limit theorem for the Euler-Poincaré characteristic of random spherical eigenfunctions,Annals of Probability, 46, n.6, 3188–3228

    work page 2018

  18. [18]

    (2019) Statistical Inference for Spherical Functional Autoregressions, PhD Thesis, Sapienza University of Rome

    Caponera, A. (2019) Statistical Inference for Spherical Functional Autoregressions, PhD Thesis, Sapienza University of Rome

    work page 2019

  19. [19]

    (2016) Excursion probability of Gaussian random fields on sphere,Bernoulli, 22, 2, 1113-1130

    Cheng, D., Xiao, Y. (2016) Excursion probability of Gaussian random fields on sphere,Bernoulli, 22, 2, 1113-1130

    work page 2016

  20. [20]

    (2018) Expected number and height distribution of critical points of smooth isotropic Gaussian random fields,Bernoulli, 24, no

    Cheng, D., Schwartzman, A. (2018) Expected number and height distribution of critical points of smooth isotropic Gaussian random fields,Bernoulli, 24, no. 4B, 3422–3446

    work page 2018

  21. [21]

    (2019+) Multiple testing of local maxima for detection of peaks on the (celestial) sphere,Bernoulli, in press, arXiv: 1602.08296

    Cheng, D., Cammarota, V., Fantaye, Y., Marinucci, D., Schwartzman, A. (2019+) Multiple testing of local maxima for detection of peaks on the (celestial) sphere,Bernoulli, in press, arXiv: 1602.08296

    work page arXiv 2019

  22. [22]

    (2018) Regularity properties and simulations of Gaussian random fields on the sphere cross time,Electronic Journal of Statistics, 12, no

    Clarke De la Cerda, J., Alegría, A., Porcu, E. (2018) Regularity properties and simulations of Gaussian random fields on the sphere cross time,Electronic Journal of Statistics, 12, no. 1, 399–426

    work page 2018

  23. [23]

    (2018) A multi-resolution model for non-Gaussian random fields on a sphere with application to ionospheric electrostatic potentials,Annals of Applied Statistics, no

    Fan, M., Paul, D., Lee, T.C.M., Matsuo, T. (2018) A multi-resolution model for non-Gaussian random fields on a sphere with application to ionospheric electrostatic potentials,Annals of Applied Statistics, no. 1, 459–489

    work page 2018

  24. [24]

    (2018) Modeling tangential vector fields on a sphere, Journal of the American Statistical Association, 113, no

    Fan, M., Paul, D., Lee, T.C.M., Matsuo, T. (2018) Modeling tangential vector fields on a sphere, Journal of the American Statistical Association, 113, no. 524, 1625–1636

    work page 2018

  25. [25]

    M., Hivon, E., Banday, A.J., Wandelt, B.D.,Hansen, F.K., Reinecke, M

    Gorski, K. M., Hivon, E., Banday, A.J., Wandelt, B.D.,Hansen, F.K., Reinecke, M. and Bartelmann M. (2005) HEALPix: A Framework for High-Resolution Discretization and Fast Analysis of Data Distributed on the Sphere,The Astrophysical Journal, Volume 622, Number 2

    work page 2005

  26. [26]

    (2013) Strictly and non-strictly positive definite functions on spheres,Bernoulli, 19, no

    Gneiting, T. (2013) Strictly and non-strictly positive definite functions on spheres,Bernoulli, 19, no. 4, 1327–1349

    work page 2013

  27. [27]

    S., Ryzhik, I

    Gradshteyn, I. S., Ryzhik, I. M. (2015)Table of integrals, series, and products.Translated from the Russian. Eighth edition, Elsevier/Academic Press, Amsterdam, 2015

    work page 2015

  28. [28]

    (2018) Testing for periodicity in functional time series,Annals of Statistics, 46, no

    Hormann, S., Kokoszka, P., Nisol, G. (2018) Testing for periodicity in functional time series,Annals of Statistics, 46, no. 6A, 2960-2984

    work page 2018

  29. [29]

    (2015)Theoretical foundations of functional data analysis, with an introduction to linear operators, Wiley Series in Probability and Statistics, John Wiley and Sons

    Hsing, T., Eubank, R. (2015)Theoretical foundations of functional data analysis, with an introduction to linear operators, Wiley Series in Probability and Statistics, John Wiley and Sons

    work page 2015

  30. [30]

    (2014) Matérn-based nonstationary cross-covariance models for global processes,Journal of Multivariate Analysis, 128, 134–146

    Jun, M. (2014) Matérn-based nonstationary cross-covariance models for global processes,Journal of Multivariate Analysis, 128, 134–146

    work page 2014

  31. [31]

    (1996).The NCEP/NCAR 40-year reanalysis project,Bulletin of the American meteorological Society, 77, no

    Kalnay, E., Kanamitsu, M., Kistler, R., Collins, W., Deaven, D., Gandin, L., Zhu, Y., et al. (1996).The NCEP/NCAR 40-year reanalysis project,Bulletin of the American meteorological Society, 77, no. 3, 437-472

    work page 1996

  32. [32]

    (2015) Isotropic Gaussian random fields on the sphere: regularity, fast simulation and stochastic partial differential equations,Annals of Applied Probability, 25, no

    Lang, A., Schwab, C. (2015) Isotropic Gaussian random fields on the sphere: regularity, fast simulation and stochastic partial differential equations,Annals of Applied Probability, 25, no. 6, 3047–3094

    work page 2015

  33. [33]

    N., Taqqu, M

    Leonenko, N. N., Taqqu, M. S., Terdik, G. H. (2018) Estimation of the covariance function of Gaus- sian isotropic random fields on spheres, related Rosenblatt-type distributions and the cosmic variance 40 CAPONERA AND MARINUCCI problem, Electronic Journal of Statistics, 12, no. 2, 3114–3146

    work page 2018

  34. [34]

    (2011)Random Fields on the Sphere: Representations, Limit Theorems and Cosmological Applications, Cambridge University Press

    Marinucci, D., Peccati, G. (2011)Random Fields on the Sphere: Representations, Limit Theorems and Cosmological Applications, Cambridge University Press

    work page 2011

  35. [35]

    (2016) High-frequency asymptotics for Lipschitz-Killing curvatures of excursion sets on the sphere,Annals of Applied Probability, 26, no

    Marinucci, D., Vadlamani, S. (2016) High-frequency asymptotics for Lipschitz-Killing curvatures of excursion sets on the sphere,Annals of Applied Probability, 26, no. 1, 462-506

    work page 2016

  36. [36]

    (2012) General moments of the inverse real Wishart distribution and orthogonal Wein- garten functions,Journal of Theoretical Probability, 25, no

    Matsumoto, S. (2012) General moments of the inverse real Wishart distribution and orthogonal Wein- garten functions,Journal of Theoretical Probability, 25, no. 3, 798-822

    work page 2012

  37. [37]

    (2009) Stein’s method on Wiener chaos,Probability Theory and Related Fields, 145, no

    Nourdin, I., Peccati, G. (2009) Stein’s method on Wiener chaos,Probability Theory and Related Fields, 145, no. 1-2, 75–118

    work page 2009

  38. [38]

    (2012)Normal Approximations Using Malliavin Calculus: from Stein’s Method to Universality, Cambridge University Press

    Nourdin, I., Peccati, G. (2012)Normal Approximations Using Malliavin Calculus: from Stein’s Method to Universality, Cambridge University Press

    work page 2012

  39. [39]

    (2013) Fourier analysis of stationary time series in function space,Annals of Statistics, 41, no

    Panaretos, V.M., Tavakoli, S. (2013) Fourier analysis of stationary time series in function space,Annals of Statistics, 41, no. 2, 568–603

    work page 2013

  40. [40]

    Planck Collaboration (2016) Planck 2015 results. I. Overview of products and scientific results,As- tronomy and Astrophysics, Volume 594, October 2016, A1, 38 pp

    work page 2016

  41. [41]

    (2016) Spatio-temporal covariance and cross-covariance func- tions of the great circle distance on a sphere,Journal of the American Statistical Association, 111, no

    Porcu, E., Bevilacqua, M., Genton, M.G. (2016) Spatio-temporal covariance and cross-covariance func- tions of the great circle distance on a sphere,Journal of the American Statistical Association, 111, no. 514, 888–898

    work page 2016

  42. [42]

    Robinson, P. M. (1995) Log-periodogram regression of time series with long range dependence,Annals of Statistics,23, no. 3, 1048–1072

    work page 1995

  43. [43]

    (1975)Orthogonal polynomials.Fourth edition

    Szegő, G. (1975)Orthogonal polynomials.Fourth edition. American Mathematical Society, Colloquium Publications, Vol. XXIII. American Mathematical Society, Providence, R.I

    work page 1975

  44. [44]

    1, 466–493

    Xiao,H.,Wu,W.B.(2012)Covariancematrixestimationforstationarytimeseries, Annals of Statistics, 40, no. 1, 466–493

    work page 2012

  45. [45]

    Wigman, I. (2010) Fluctuations of the nodal length of random spherical harmonics,Communications in Mathematical Physics, 298, 3, 787-831 Piazzale Aldo Moro, 5 00185 Roma Italy E-mail: alessia.caponera@uniroma1.it Via della Ricerca Scientifica, 1 00133 Roma Italy E-mail: marinucc@mat.uniroma2.it

    work page 2010