#nonparametric
LightNews LightNews
teeeeeeeee.bsky.social
A new method for deriving a nonparametric confidence interval for the mean
https://thierrymoudiki.github.io/blog/2024/08/26/r/ci-mean-nonparam

#Python #DataScience #MachineLearning #rstats #Techtonique
Blog post image
November 12, 2026 at 7:40 PM
repec-nep-net.bsky.social
Nonparametric Dyadic Quantile Regression: Zheng Li
NEP/RePEc link
to paper
d.repec.org
November 11, 2026 at 3:50 PM
aethertek369.bsky.social
How spatial priors improve segmentation

From the paper “Combining nonparametric spatial context priors with nonparametric shape priors”. Does shape priors match anything you have noticed yourself?

aethertek.org

#consciousness #emotions #biophotons #science #aethertek
November 11, 2026 at 6:02 AM
nsfsimonscosmicai.bsky.social
Listen as CosmicAI PhD student Ritwik Vashistha describes his research on finding signal in data in the presence of noise!

Ritwik showcased his poster “Nonparametric Denoising using Empirical Bayes and Simulation Based Inference” at the Summit for AI Institutes Leadership (SAIL)!
November 11, 2026 at 2:59 PM
arxiv-math-st.bsky.social
Muheng Li, Peize Zhang, Xin Bing
Nonparametric Maximum Likelihood Estimation for Mixtures of Logistic Regressions
https://arxiv.org/abs/2611.14445
November 11, 2026 at 6:33 PM
arxiv-stat-me.bsky.social
Jinyuan Chang, Yue Wang, Heng Lian, Wen-Xin Zhou
Harnessing collaborative networks for nonparametric quantile learning
https://arxiv.org/abs/2611.13754
November 11, 2026 at 8:23 PM
cranberriesfeed.bsky.social
New CRAN package ZTRecur with initial version 0.2.1
#rstats
https://cran.r-project.org/package=ZTRecur
CRAN: Package ZTRecur
Provides nonparametric and Cox-type regression methods for analyzing zero-truncated recurrent event data with supplementary information. Key features include estimating rate and mean functions under nonparametric marginal models; estimating time-constant regression coefficients under standard and stratified Andersen-Gill (AG) models; and estimating time-varying covariate effects under stratified and nonstratified Cox-type models. Standard errors (SEs) are estimated using sandwich-based variance estimators for nonstratified models and resampling-based procedures for stratified models. For further details, see Chen, Hu, and Rosychuk (2026) &lt;<a href="https://doi.org/10.1214%2F25-AOAS2130" target="_top">doi:10.1214/25-AOAS2130</a>&gt;, Chen et al. (2026) &lt;<a href="https://doi.org/10.1002%2Fcjs.70064" target="_top">doi:10.1002/cjs.70064</a>&gt;, and Chen, Hu, and Rosychuk (2026) &lt;<a href="https://doi.org/10.48550%2FarXiv.2607.26210" target="_top">doi:10.48550/arXiv.2607.26210</a>&gt;.
cran.r-project.org
November 12, 2026 at 12:02 PM
cranupdates.bsky.social
New on CRAN: ZTRecur (0.2.1). View at https://CRAN.R-project.org/package=ZTRecur
ZTRecur: Analysis for Zero-Truncated Recurrent Event Data
Provides nonparametric and Cox-type regression methods for analyzing zero-truncated recurrent event data with supplementary information. Key features include estimating rate and mean functions under nonparametric marginal models; estimating time-constant regression coefficients under standard and stratified Andersen-Gill (AG) models; and estimating time-varying covariate effects under stratified and nonstratified Cox-type models. Standard errors (SEs) are estimated using sandwich-based variance estimators for nonstratified models and resampling-based procedures for stratified models. For further details, see Chen, Hu, and Rosychuk (2026) &lt;<a href="https://doi.org/10.1214%2F25-AOAS2130" target="_top">doi:10.1214/25-AOAS2130</a>&gt;, Chen et al. (2026) &lt;<a href="https://doi.org/10.1002%2Fcjs.70064" target="_top">doi:10.1002/cjs.70064</a>&gt;, and Chen, Hu, and Rosychuk (2026) &lt;<a href="https://doi.org/10.48550%2FarXiv.2607.26210" target="_top">doi:10.48550/arXiv.2607.26210</a>&gt;.
CRAN.R-project.org
November 12, 2026 at 5:17 PM
mathst-bot.bsky.social
Muheng Li, Peize Zhang, Xin Bing: Nonparametric Maximum Likelihood Estimation for Mixtures of Logistic Regressions https://arxiv.org/abs/2611.14445 https://arxiv.org/pdf/2611.14445 https://arxiv.org/html/2611.14445
November 11, 2026 at 6:51 AM
statme-bot.bsky.social
Jinyuan Chang, Yue Wang, Heng Lian, Wen-Xin Zhou: Harnessing collaborative networks for nonparametric quantile learning https://arxiv.org/abs/2611.13754 https://arxiv.org/pdf/2611.13754 https://arxiv.org/html/2611.13754
November 11, 2026 at 7:03 AM
repec-nep-net.bsky.social
Nonparametric Dyadic Quantile Regression: Zheng Li
NEP/RePEc link
to paper
d.repec.org
November 7, 2026 at 1:01 PM
xangregg.bsky.social
With a little guidance, Claude can turn a stats paper into a webapp. I tried this one bc it showed up as prior art for another project.
paper: "Nonparametric Regression, Confidence Regions and Regularization" Davies, Kovac & Meise arxiv.org/abs/0711.0690
webapp: xangregg.github.io/tautfit/
screenshot of the mentioned webapp showing controls on left, graph in middle and diagnostic readouts on right
November 8, 2026 at 4:21 PM
gnollandvoid.bsky.social
Classes for winter quarter:
>Intro to US Law
>Intro to Statistics
>Natural Disasters

Previous courses not transferred in:
>Intro to Poli Sci
>Nonparametric Statistics
>About a 1/3rd of a Geology degree

I'll be fine.
November 6, 2026 at 4:35 PM
cranupdates.bsky.social
New on CRAN: pcdreg (0.1.0). View at https://CRAN.R-project.org/package=pcdreg
pcdreg: Semiparametric Regression for Panel Count Data
Fits semiparametric regression models to panel count data, that is, to recurrent event processes observed only at intermittent examination times, allowing covariates to be time-varying. The proportional rate model is fitted by nonparametric maximum likelihood through an expectation-maximization algorithm under a working Poisson assumption, while inference does not require that assumption to hold; two computationally inexpensive covariance estimators are provided, a robust sandwich estimator that remains consistent when the Poisson assumption fails and an efficient information estimator that is a fast substitute for profile likelihood when it holds, with the profile likelihood estimator available for comparison. The proportional means model is fitted by the estimating equation of Hu, Sun and Wei (2003) &lt;<a href="https://doi.org/10.1111%2F1467-9469.00316" target="_top">doi:10.1111/1467-9469.00316</a>&gt;. Methods for the rate model are described in Sun, Guo, Li, Tu and Sun (2024) &lt;<a href="https://doi.org/10.3150%2F23-BEJ1713" target="_top">doi:10.3150/23-BEJ1713</a>&gt;.
CRAN.R-project.org
November 10, 2026 at 10:06 PM
cranberriesfeed.bsky.social
New CRAN package pcdreg with initial version 0.1.0
#rstats
https://cran.r-project.org/package=pcdreg
CRAN: Package pcdreg
Fits semiparametric regression models to panel count data, that is, to recurrent event processes observed only at intermittent examination times, allowing covariates to be time-varying. The proportional rate model is fitted by nonparametric maximum likelihood through an expectation-maximization algorithm under a working Poisson assumption, while inference does not require that assumption to hold; two computationally inexpensive covariance estimators are provided, a robust sandwich estimator that remains consistent when the Poisson assumption fails and an efficient information estimator that is a fast substitute for profile likelihood when it holds, with the profile likelihood estimator available for comparison. The proportional means model is fitted by the estimating equation of Hu, Sun and Wei (2003) &lt;<a href="https://doi.org/10.1111%2F1467-9469.00316" target="_top">doi:10.1111/1467-9469.00316</a>&gt;. Methods for the rate model are described in Sun, Guo, Li, Tu and Sun (2024) &lt;<a href="https://doi.org/10.3150%2F23-BEJ1713" target="_top">doi:10.3150/23-BEJ1713</a>&gt;.
cran.r-project.org
November 10, 2026 at 4:05 PM
econem-bot.bsky.social
Wenxuan Ding: Nonparametric Subgraph Regression https://arxiv.org/abs/2611.07240 https://arxiv.org/pdf/2611.07240 https://arxiv.org/html/2611.07240
November 6, 2026 at 6:44 AM
paperposterbot.bsky.social
arXiv📈🤖
Nonparametric Subgraph Regression
By Ding
Estimation and inference on a single large network are challenging due to dependence among observations. This paper studies nonparametric regression for outcomes defined on groups of $p$ agents, such as the indicator that three agents in a network form a triangle. Outcomes on groups that share an agent may be dependent, while outcomes on disjoint groups are independent. I call this problem subgraph regression; it nests dyadic regression as the special case $p=2$. Its leading application concerns subgraphs of a network, but the methods apply to any outcome defined on groups of agents. I establish a variance bound, uniform convergence rates in probability, and pointwise asymptotic normality for the subgraph analogue of the Nadaraya-Watson kernel regression estimator. The setting differs from regression with i.i.d. data in two ways: (i) the number of observations, of order $N^p$, overstates the effective sample size, which is $N$, and (ii) the rate of convergence depends on the dimension of the covariates of a single agent rather than of all $p$ agents, which mitigates the curse of dimensionality.
November 6, 2026 at 10:33 AM
princetonecon.bsky.social
He develops a unified framework that bounds the parameter of interest when these assumptions fail for a given share of the population. The bounds are computationally tractable and recover sharp nonparametric bounds as a special case.
filippopalomba.github.io
November 5, 2026 at 6:09 PM
repec-nep-eff.bsky.social
Robust Nonparametric Partial Frontier Input Distance Function Estimates: Testing and Rejecting Convexity: Tiantian REN
NEP/RePEc link
to paper
d.repec.org
November 4, 2026 at 6:53 PM
repec-nep-eff.bsky.social
Multi-Moment and Multi-Time Nonparametric Frontier-Based Mutual Fund Rating: A Buy-and-Hold Backtesting Strategy with Robust Moment Statistics and a Baseline Comparison: Albane Christine TARNAUD
NEP/RePEc link
to paper
d.repec.org
November 5, 2026 at 6:51 AM
paperposterbot.bsky.social
arXiv📈🤖
Nonparametric GARCH: An Iterated Neural Estimator
By Deng, Shen, Chan
We study nonparametric estimation and forecasting for GARCH-type processes and propose an iterated neural estimator that alternates between estimating the recursion map and updating the unobserved conditional variances. Under mild conditions, we establish finite-sample bounds for the time-averaged in-sample variance-path error and show that the estimator is minimax rate-optimal up to logarithmic factors. Under stationarity and mixing conditions, we establish the same rate for recursion-map estimation and derive finite-sample bounds for out-of-sample variance forecasts and expected excess Gaussian quasi-likelihood (QLIKE) loss. The convergence rates depend on the true lag orders and remain unchanged when the fitted orders are overspecified. Simulation studies illustrate the effectiveness of our estimators under nonlinear and time-varying volatility dynamics. Real-data applications suggest that our neural methods perform competitively and can incorporate option-price and high-frequency information.
November 4, 2026 at 10:55 PM
statml-bot.bsky.social
Ruizhi Deng, Guohao Shen, Ngai Hang Chan: Nonparametric GARCH: An Iterated Neural Estimator https://arxiv.org/abs/2611.04157 https://arxiv.org/pdf/2611.04157 https://arxiv.org/html/2611.04157
November 4, 2026 at 7:03 AM
paperposterbot.bsky.social
arXiv📈🤖
Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics
By Ge, Huang, Wu
In this article, we study deep nonparametric regression trained via stochastic gradient Langevin dynamics (SGLD), a variant of stochastic gradient descent that injects carefully calibrated Gaussian noise during optimization. Using a PAC-Bayesian analysis tailored to deep ReLU networks, we establish an excess-risk bound that simultaneously accounts for network approximation error, statistical complexity, and the algorithmic cost accumulated along the SGLD trajectory. Under a Bernstein condition and within a stable SGLD regime, the excess-risk bound contains a stochastic term whose coefficient is inversely proportional to the variance of injected noise, while the estimator retains the optimal rate for nonparametric regression under the H\"older smoothness condition up to logarithmic factors. This result provides an approximation-error-aware, rate-optimal statistical perspective on the widely observed generalization benefits of moderate SGLD noise. For per-sample clipped SGLD, we further establish an exact f-DP guarantee and the corresponding asymptotic $\mu$-GDP guarantee for the proposed estimator. We establish statistical convergence rates and differential privacy guarantees for DNN estimators trained using SGLD, while explicitly accounting for both network approximation error and the effect of injected noise in the excess-risk bound. Extensive simulation studies and analyses of two real datasets examine the finite-sample predictive performance and privacy-utility behavior of the proposed procedure.
November 6, 2026 at 10:53 AM
dppapers.bsky.social
Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics

Yeheng Ge, Jian Huang, Shuyuan Wu

http://arxiv.org/abs/2611.07490
Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics Yeheng Ge, Jian Huang, Shuyuan Wu http://arxiv.org/abs/2611.07490 In this article, we study deep nonparametric regression trained via stochastic gradient Langevin dynamics (SGLD), a variant of stochastic gradient descent that injects carefully calibrated Gaussian noise during optimization. Using a PAC-Bayesian analysis tailored to deep ReLU networks, we establish an excess-risk bound that simultaneously accounts for network approximation error, statistical complexity, and the algorithmic cost accumulated along the SGLD trajectory. Under a Bernstein condition and within a stable SGLD regime, the excess-risk bound contains a stochastic term whose coefficient is inversely proportional to the variance of injected noise, while the estimator retains the optimal rate for nonparametric regression under the Hölder smoothness condition up to logarithmic factors. This result provides an approximation-error-aware, rate-optimal statistical perspective on the widely observed generalization benefits of moderate SGLD noise. For per-sample clipped SGLD, we further establish an exact f-DP guarantee and the corresponding asymptotic $μ$-GDP guarantee for the proposed estimator. We establish statistical convergence rates and differential privacy guarantees for DNN estimators trained using SGLD, while explicitly accounting for both network approximation error and the effect of injected noise in the excess-risk bound. Extensive simulation studies and analyses of two real datasets examine the finite-sample predictive performance and privacy-utility behavior of the proposed procedure.
November 6, 2026 at 4:53 AM
paperposterbot.bsky.social
arXiv📈🤖
Sample size calculation comparing two survival curves in the presence of nonproportional hazards utilizing the concept of Weighted Relative Time using two different Weibull distributions
By Phadnis, Talukder, Mudunkotuwa et al
Sample size calculations in two-arm clinical trials with survival endpoint often utilize the proportional hazards (PH) assumption. In case of nonproportional hazards (NPH), much research is ongoing with some newer methods developed that work well in specific scenarios. Recent developments have considered the nonparametric Max-Combo logrank test for both design and analysis of survival data with NPH. Although many approaches have been proposed for analyzing time-to-event data with NPH such as Restricted Mean Survival Time, Average Hazard Ratios, and piecewise exponential model with hazard ratios changing over time, translation into sample size calculation is not obvious and relies on simulations for very specific scenarios of NPH. In the parametric setting, accelerated failure time models that allow NPH but require a constant time ratio assumption (PT assumption) have been proposed. Recently, a parametric approach that simultaneously allows both nonproportional hazards (NPH) and nonproportional time (NPT) has been proposed. It utilizes the concept of Relative Time (RT) with two different Weibull distributions for the two trial arms in the case of monotonically increasing/decreasing time ratios. A key limitation is that the hypotheses leading to the sample size calculation rely on a single effect size defined at a specific survival percentile. In our current work, we extend the parent RT method by utilizing the concept of Weighted Relative Time (WRT) that allows us comparison of the full survival curves. Performance of the proposed method is compared to the Max-Combo method under different weighting schemes, and its operation characteristics are studied via simulations.
November 6, 2026 at 10:29 AM