Filtering algorithms are fundamental for inference on partially observed stochastic dynamic systems, since they provide access to the likelihood function and hence enable likelihood-based or Bayesian inference. A novel Poisson approximate likelihood (PAL) filter was introduced by Whitehouse et al. (2023). PAL employs a Poisson approximation to conditional densities, offering a fast approximation to the likelihood function for a certain subset of partially observed Markov process models. A central piece of evidence for PAL is the comparison in Table 1 of Whitehouse et al. (2023), which claims a large improvement for PAL over a standard particle filter algorithm. This evidence, based on a model and data from a previous scientific study by Stocks et al. (2020), might suggest that researchers confronted with similar models should use PAL rather than particle filter methods. Taken at face value, this evidence also reduces the credibility of Stocks et al. (2020) by indicating a shortcoming with the numerical methods that they used. However, we show that the comparison of log-likelihood values made by Whitehouse et al. (2023) is flawed because their PAL calculations were carried out using a dataset scaled differently from the previous study. If PAL and the particle filter are applied to the same data, the advantage claimed for PAL disappears. On simulations where the model is correctly specified, the particle filter outperforms PAL.
滤波算法是部分观测随机动态系统推断的基础，因为它们提供了对似然函数的访问，从而实现基于似然或贝叶斯的推断。怀特豪斯等人（2023 年）提出了一种新型泊松近似似然（PAL）滤波器。PAL 对条件密度采用泊松近似，为部分观测的马尔可夫过程模型的某些子集提供了快速近似似然函数。怀特豪斯等人（2023 年）在表 1 中对 PAL 进行了比较，认为 PAL 比标准粒子滤波算法有很大改进。这一证据基于 Stocks 等人（2020 年）以前的一项科学研究中的模型和数据，可能表明研究人员在面对类似模型时应使用 PAL 而不是粒子滤波方法。从表面价值来看，这一证据也降低了斯托克斯等人（2020 年）的可信度，因为它表明他们使用的数值方法存在缺陷。然而，我们发现怀特豪斯等人（2023 年）的对数似然值比较存在缺陷，因为他们的 PAL 计算使用的数据集比例与前一项研究不同。如果将 PAL 和粒子过滤器应用于相同的数据，那么 PAL 的优势就会消失。在正确指定模型的模拟中，粒子滤波器的性能优于 PAL。
{"title":"Poisson approximate likelihood compared to the particle filter","authors":"Yize Hao, Aaron A. Abkemeier, Edward L. Ionides","doi":"arxiv-2409.12173","DOIUrl":"https://doi.org/arxiv-2409.12173","url":null,"abstract":"Filtering algorithms are fundamental for inference on partially observed\u0000stochastic dynamic systems, since they provide access to the likelihood\u0000function and hence enable likelihood-based or Bayesian inference. A novel\u0000Poisson approximate likelihood (PAL) filter was introduced by Whitehouse et al.\u0000(2023). PAL employs a Poisson approximation to conditional densities, offering\u0000a fast approximation to the likelihood function for a certain subset of\u0000partially observed Markov process models. A central piece of evidence for PAL\u0000is the comparison in Table 1 of Whitehouse et al. (2023), which claims a large\u0000improvement for PAL over a standard particle filter algorithm. This evidence,\u0000based on a model and data from a previous scientific study by Stocks et al.\u0000(2020), might suggest that researchers confronted with similar models should\u0000use PAL rather than particle filter methods. Taken at face value, this evidence\u0000also reduces the credibility of Stocks et al. (2020) by indicating a\u0000shortcoming with the numerical methods that they used. However, we show that\u0000the comparison of log-likelihood values made by Whitehouse et al. (2023) is\u0000flawed because their PAL calculations were carried out using a dataset scaled\u0000differently from the previous study. If PAL and the particle filter are applied\u0000to the same data, the advantage claimed for PAL disappears. On simulations\u0000where the model is correctly specified, the particle filter outperforms PAL.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In clinical studies upon which decisions are based there are two types of errors that can be made: a type I error arises when the decision is taken to declare a positive outcome when the truth is in fact negative, and a type II error arises when the decision is taken to declare a negative outcome when the truth is in fact positive. Commonly the primary analysis of such a study entails a two-sided hypothesis test with a type I error rate of 5% and the study is designed to have a sufficiently low type II error rate, for example 10% or 20%. These values are arbitrary and often do not reflect the clinical, or regulatory, context of the study and ignore both the relative costs of making either type of error and the sponsor's prior belief that the drug is superior to either placebo, or a standard of care if relevant. This simplistic approach has recently been challenged by numerous authors both from a frequentist and Bayesian perspective since when resources are constrained there will be a need to consider a trade-off between type I and type II errors. In this paper we review proposals to utilise the trade-off by formally acknowledging the costs to optimise the choice of error rates for simple, point null and alternative hypotheses and extend the results to composite, or interval hypotheses, showing links to the Probability of Success of a clinical study.
在作为决策依据的临床研究中，可能会出现两种类型的错误：当决定宣布阳性结果时，如果真相实际上是阴性，就会出现 I 型错误；当决定宣布阴性结果时，如果真相实际上是阳性，就会出现 II 型错误。通常情况下，此类研究的初步分析需要进行双侧假设检验，I 型错误率为 5%，研究的 II 型错误率要足够低，例如 10%或 20%。这些数值都是任意设定的，通常不能反映研究的临床或监管背景，而且忽略了出现任一类型错误的相对成本，以及申办者事先认为药物优于安慰剂或相关护理标准的信念。这种简单化的方法最近受到了许多学者的质疑，无论是从频繁论者还是贝叶斯论者的角度来看，因为当资源有限时，就需要考虑 I 类和 II 类错误之间的权衡。在本文中，我们回顾了利用这种权衡的建议，即通过正式确认成本来优化简单假说、点空假说和替代假说的错误率选择，并将结果扩展到复合假说或区间假说，显示与临床研究成功概率的联系。
{"title":"Optimising the Trade-Off Between Type I and Type II Errors: A Review and Extensions","authors":"Andrew P Grieve","doi":"arxiv-2409.12081","DOIUrl":"https://doi.org/arxiv-2409.12081","url":null,"abstract":"In clinical studies upon which decisions are based there are two types of\u0000errors that can be made: a type I error arises when the decision is taken to\u0000declare a positive outcome when the truth is in fact negative, and a type II\u0000error arises when the decision is taken to declare a negative outcome when the\u0000truth is in fact positive. Commonly the primary analysis of such a study\u0000entails a two-sided hypothesis test with a type I error rate of 5% and the\u0000study is designed to have a sufficiently low type II error rate, for example\u000010% or 20%. These values are arbitrary and often do not reflect the clinical,\u0000or regulatory, context of the study and ignore both the relative costs of\u0000making either type of error and the sponsor's prior belief that the drug is\u0000superior to either placebo, or a standard of care if relevant. This simplistic\u0000approach has recently been challenged by numerous authors both from a\u0000frequentist and Bayesian perspective since when resources are constrained there\u0000will be a need to consider a trade-off between type I and type II errors. In\u0000this paper we review proposals to utilise the trade-off by formally\u0000acknowledging the costs to optimise the choice of error rates for simple, point\u0000null and alternative hypotheses and extend the results to composite, or\u0000interval hypotheses, showing links to the Probability of Success of a clinical\u0000study.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"123 14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matching is a commonly used causal inference framework in observational studies. By pairing individuals with different treatment values but with the same values of covariates (i.e., exact matching), the sample average treatment effect (SATE) can be consistently estimated and inferred using the classic Neyman-type (difference-in-means) estimator and confidence interval. However, inexact matching typically exists in practice and may cause substantial bias for the downstream treatment effect estimation and inference. Many methods have been proposed to reduce bias due to inexact matching in the binary treatment case. However, to our knowledge, no existing work has systematically investigated bias due to inexact matching in the continuous treatment case. To fill this blank, we propose a general framework for reducing bias in inexactly matched observational studies with continuous treatments. In the matching stage, we propose a carefully formulated caliper that incorporates the information of both the paired covariates and treatment doses to better tailor matching for the downstream SATE estimation and inference. In the estimation and inference stage, we propose a bias-corrected Neyman estimator paired with the corresponding bias-corrected variance estimator to leverage the information on propensity density discrepancies after inexact matching to further reduce the bias due to inexact matching. We apply our proposed framework to COVID-19 social mobility data to showcase differences between classic and bias-corrected SATE estimation and inference.
{"title":"Bias Reduction in Matched Observational Studies with Continuous Treatments: Calipered Non-Bipartite Matching and Bias-Corrected Estimation and Inference","authors":"Anthony Frazier, Siyu Heng, Wen Zhou","doi":"arxiv-2409.11701","DOIUrl":"https://doi.org/arxiv-2409.11701","url":null,"abstract":"Matching is a commonly used causal inference framework in observational\u0000studies. By pairing individuals with different treatment values but with the\u0000same values of covariates (i.e., exact matching), the sample average treatment\u0000effect (SATE) can be consistently estimated and inferred using the classic\u0000Neyman-type (difference-in-means) estimator and confidence interval. However,\u0000inexact matching typically exists in practice and may cause substantial bias\u0000for the downstream treatment effect estimation and inference. Many methods have\u0000been proposed to reduce bias due to inexact matching in the binary treatment\u0000case. However, to our knowledge, no existing work has systematically\u0000investigated bias due to inexact matching in the continuous treatment case. To\u0000fill this blank, we propose a general framework for reducing bias in inexactly\u0000matched observational studies with continuous treatments. In the matching\u0000stage, we propose a carefully formulated caliper that incorporates the\u0000information of both the paired covariates and treatment doses to better tailor\u0000matching for the downstream SATE estimation and inference. In the estimation\u0000and inference stage, we propose a bias-corrected Neyman estimator paired with\u0000the corresponding bias-corrected variance estimator to leverage the information\u0000on propensity density discrepancies after inexact matching to further reduce\u0000the bias due to inexact matching. We apply our proposed framework to COVID-19\u0000social mobility data to showcase differences between classic and bias-corrected\u0000SATE estimation and inference.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We introduce a compositional power transformation, known as an {alpha}-transformation, to model and forecast a time series of life-table death counts, possibly with zero counts observed at older ages. As a generalisation of the isometric log-ratio transformation (i.e., {alpha} = 0), the {alpha} transformation relies on the tuning parameter {alpha}, which can be determined in a data-driven manner. Using the Australian age-specific period life-table death counts from 1921 to 2020, the {alpha} transformation can produce more accurate short-term point and interval forecasts than the log-ratio transformation. The improved forecast accuracy of life-table death counts is of great importance to demographers and government planners for estimating survival probabilities and life expectancy and actuaries for determining annuity prices and reserves for various initial ages and maturity terms.
{"title":"Forecasting age distribution of life-table death counts via α-transformation","authors":"Han Lin Shang, Steven Haberman","doi":"arxiv-2409.11658","DOIUrl":"https://doi.org/arxiv-2409.11658","url":null,"abstract":"We introduce a compositional power transformation, known as an\u0000{alpha}-transformation, to model and forecast a time series of life-table\u0000death counts, possibly with zero counts observed at older ages. As a\u0000generalisation of the isometric log-ratio transformation (i.e., {alpha} = 0),\u0000the {alpha} transformation relies on the tuning parameter {alpha}, which can\u0000be determined in a data-driven manner. Using the Australian age-specific period\u0000life-table death counts from 1921 to 2020, the {alpha} transformation can\u0000produce more accurate short-term point and interval forecasts than the\u0000log-ratio transformation. The improved forecast accuracy of life-table death\u0000counts is of great importance to demographers and government planners for\u0000estimating survival probabilities and life expectancy and actuaries for\u0000determining annuity prices and reserves for various initial ages and maturity\u0000terms.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We analyze common types of e-variables and e-processes for composite exponential family nulls: the optimal e-variable based on the reverse information projection (RIPr), the conditional (COND) e-variable, and the universal inference (UI) and sequen-tialized RIPr e-processes. We characterize the RIPr prior for simple and Bayes-mixture based alternatives, either precisely (for Gaussian nulls and alternatives) or in an approximate sense (general exponential families). We provide conditions under which the RIPr e-variable is (again exactly vs. approximately) equal to the COND e-variable. Based on these and other interrelations which we establish, we determine the e-power of the four e-statistics as a function of sample size, exactly for Gaussian and up to $o(1)$ in general. For $d$-dimensional null and alternative, the e-power of UI tends to be smaller by a term of $(d/2) log n + O(1)$ than that of the COND e-variable, which is the clear winner.
{"title":"E-Values for Exponential Families: the General Case","authors":"Yunda Hao, Peter Grünwald","doi":"arxiv-2409.11134","DOIUrl":"https://doi.org/arxiv-2409.11134","url":null,"abstract":"We analyze common types of e-variables and e-processes for composite\u0000exponential family nulls: the optimal e-variable based on the reverse\u0000information projection (RIPr), the conditional (COND) e-variable, and the\u0000universal inference (UI) and sequen-tialized RIPr e-processes. We characterize\u0000the RIPr prior for simple and Bayes-mixture based alternatives, either\u0000precisely (for Gaussian nulls and alternatives) or in an approximate sense\u0000(general exponential families). We provide conditions under which the RIPr\u0000e-variable is (again exactly vs. approximately) equal to the COND e-variable.\u0000Based on these and other interrelations which we establish, we determine the\u0000e-power of the four e-statistics as a function of sample size, exactly for\u0000Gaussian and up to $o(1)$ in general. For $d$-dimensional null and alternative,\u0000the e-power of UI tends to be smaller by a term of $(d/2) log n + O(1)$ than\u0000that of the COND e-variable, which is the clear winner.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a novel cointegrated autoregressive model for matrix-valued time series, with bi-linear cointegrating vectors corresponding to the rows and columns of the matrix data. Compared to the traditional cointegration analysis, our proposed matrix cointegration model better preserves the inherent structure of the data and enables corresponding interpretations. To estimate the cointegrating vectors as well as other coefficients, we introduce two types of estimators based on least squares and maximum likelihood. We investigate the asymptotic properties of the cointegrated matrix autoregressive model under the existence of trend and establish the asymptotic distributions for the cointegrating vectors, as well as other model parameters. We conduct extensive simulations to demonstrate its superior performance over traditional methods. In addition, we apply our proposed model to Fama-French portfolios and develop a effective pairs trading strategy.
{"title":"Cointegrated Matrix Autoregression Models","authors":"Zebang Li, Han Xiao","doi":"arxiv-2409.10860","DOIUrl":"https://doi.org/arxiv-2409.10860","url":null,"abstract":"We propose a novel cointegrated autoregressive model for matrix-valued time\u0000series, with bi-linear cointegrating vectors corresponding to the rows and\u0000columns of the matrix data. Compared to the traditional cointegration analysis,\u0000our proposed matrix cointegration model better preserves the inherent structure\u0000of the data and enables corresponding interpretations. To estimate the\u0000cointegrating vectors as well as other coefficients, we introduce two types of\u0000estimators based on least squares and maximum likelihood. We investigate the\u0000asymptotic properties of the cointegrated matrix autoregressive model under the\u0000existence of trend and establish the asymptotic distributions for the\u0000cointegrating vectors, as well as other model parameters. We conduct extensive\u0000simulations to demonstrate its superior performance over traditional methods.\u0000In addition, we apply our proposed model to Fama-French portfolios and develop\u0000a effective pairs trading strategy.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lucas Kock, G. S. Rodrigues, Scott A. Sisson, Nadja Klein, David J. Nott
Calibration ensures that predicted uncertainties align with observed uncertainties. While there is an extensive literature on recalibration methods for univariate probabilistic forecasts, work on calibration for multivariate forecasts is much more limited. This paper introduces a novel post-hoc recalibration approach that addresses multivariate calibration for potentially misspecified models. Our method involves constructing local mappings between vectors of marginal probability integral transform values and the space of observations, providing a flexible and model free solution applicable to continuous, discrete, and mixed responses. We present two versions of our approach: one uses K-nearest neighbors, and the other uses normalizing flows. Each method has its own strengths in different situations. We demonstrate the effectiveness of our approach on two real data applications: recalibrating a deep neural network's currency exchange rate forecast and improving a regression model for childhood malnutrition in India for which the multivariate response has both discrete and continuous components.
校准可确保预测的不确定性与观测到的不确定性相一致。关于单变量概率预测的重新校准方法已有大量文献，但关于多变量预测的校准工作则有限得多。本文介绍了一种新颖的事后重新校准方法，可解决潜在不确定模型的多变量校准问题。我们的方法涉及在边际概率积分变换值向量和观测空间之间构建局部映射，提供一种灵活的、不受模型限制的解决方案，适用于连续、离散和混合响应。我们介绍了我们方法的两个版本：一个使用 K 最近邻，另一个使用归一化流。我们在两个实际数据应用中展示了我们方法的有效性：重新校准深度神经网络的汇率预测，以及改进印度儿童营养不良的回归模型，其中多变量响应既有离散成分，也有连续成分。
{"title":"Calibrated Multivariate Regression with Localized PIT Mappings","authors":"Lucas Kock, G. S. Rodrigues, Scott A. Sisson, Nadja Klein, David J. Nott","doi":"arxiv-2409.10855","DOIUrl":"https://doi.org/arxiv-2409.10855","url":null,"abstract":"Calibration ensures that predicted uncertainties align with observed\u0000uncertainties. While there is an extensive literature on recalibration methods\u0000for univariate probabilistic forecasts, work on calibration for multivariate\u0000forecasts is much more limited. This paper introduces a novel post-hoc\u0000recalibration approach that addresses multivariate calibration for potentially\u0000misspecified models. Our method involves constructing local mappings between\u0000vectors of marginal probability integral transform values and the space of\u0000observations, providing a flexible and model free solution applicable to\u0000continuous, discrete, and mixed responses. We present two versions of our\u0000approach: one uses K-nearest neighbors, and the other uses normalizing flows.\u0000Each method has its own strengths in different situations. We demonstrate the\u0000effectiveness of our approach on two real data applications: recalibrating a\u0000deep neural network's currency exchange rate forecast and improving a\u0000regression model for childhood malnutrition in India for which the multivariate\u0000response has both discrete and continuous components.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
For handling intercurrent events in clinical trials, one of the strategies outlined in the ICH E9(R1) addendum targets the hypothetical scenario of non-occurrence of the intercurrent event. While this strategy is often implemented by setting data after the intercurrent event to missing even if they have been collected, g-estimation allows for a more efficient estimation by using the information contained in post-IE data. As the g-estimation methods have largely developed outside of randomised clinical trials, optimisations for the application in clinical trials are possible. In this work, we describe and investigate the performance of modifications to the established g-estimation methods, leveraging the assumption that some intercurrent events are expected to have the same impact on the outcome regardless of the timing of their occurrence. In a simulation study in Alzheimer disease, the modifications show a substantial efficiency advantage for the estimation of an estimand that applies the hypothetical strategy to the use of symptomatic treatment while retaining unbiasedness and adequate type I error control.
在处理临床试验中的并发症时，ICH E9（R1）附录中列出的策略之一是针对并发症不发生的假设情况。实施这一策略的方法通常是将并发症发生后的数据设为缺失（即使已经收集到），而 g 估计法可以利用并发症发生后数据中包含的信息进行更有效的估计。由于 g 估计方法主要是在随机临床试验之外发展起来的，因此有可能在临床试验中进行优化应用。在这项工作中，我们描述并研究了对已建立的 g 估计方法进行修改后的性能，这些修改利用了这样一个假设，即无论发生的时间如何，一些并发症都会对结果产生相同的影响。在一项关于阿尔茨海默病的模拟研究中，修改后的方法在估算将假设策略应用于对症治疗的估算值时显示出巨大的效率优势，同时保持了无偏性和充分的 I 型误差控制。
{"title":"Comparison of g-estimation approaches for handling symptomatic medication at multiple timepoints in Alzheimer's Disease with a hypothetical strategy","authors":"Florian Lasch, Lorenzo Guizzaro, Wen Wei Loh","doi":"arxiv-2409.10943","DOIUrl":"https://doi.org/arxiv-2409.10943","url":null,"abstract":"For handling intercurrent events in clinical trials, one of the strategies\u0000outlined in the ICH E9(R1) addendum targets the hypothetical scenario of\u0000non-occurrence of the intercurrent event. While this strategy is often\u0000implemented by setting data after the intercurrent event to missing even if\u0000they have been collected, g-estimation allows for a more efficient estimation\u0000by using the information contained in post-IE data. As the g-estimation methods\u0000have largely developed outside of randomised clinical trials, optimisations for\u0000the application in clinical trials are possible. In this work, we describe and\u0000investigate the performance of modifications to the established g-estimation\u0000methods, leveraging the assumption that some intercurrent events are expected\u0000to have the same impact on the outcome regardless of the timing of their\u0000occurrence. In a simulation study in Alzheimer disease, the modifications show\u0000a substantial efficiency advantage for the estimation of an estimand that\u0000applies the hypothetical strategy to the use of symptomatic treatment while\u0000retaining unbiasedness and adequate type I error control.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Phillip Gräfensteiner, Markus Osenberg, André Hilger, Nicole Bohn, Joachim R. Binder, Ingo Manke, Volker Schmidt, Matthias Neumann
A stochastic 3D modeling approach for the nanoporous binder-conductive additive phase in hierarchically structured cathodes of lithium-ion batteries is presented. The binder-conductive additive phase of these electrodes consists of carbon black, polyvinylidene difluoride binder and graphite particles. For its stochastic 3D modeling, a three-step procedure based on methods from stochastic geometry is used. First, the graphite particles are described by a Boolean model with ellipsoidal grains. Second, the mixture of carbon black and binder is modeled by an excursion set of a Gaussian random field in the complement of the graphite particles. Third, large pore regions within the mixture of carbon black and binder are described by a Boolean model with spherical grains. The model parameters are calibrated to 3D image data of cathodes in lithium-ion batteries acquired by focused ion beam scanning electron microscopy. Subsequently, model validation is performed by comparing model realizations with measured image data in terms of various morphological descriptors that are not used for model fitting. Finally, we use the stochastic 3D model for predictive simulations, where we generate virtual, yet realistic, image data of nanoporous binder-conductive additives with varying amounts of graphite particles. Based on these virtual nanostructures, we can investigate structure-property relationships. In particular, we quantitatively study the influence of graphite particles on effective transport properties in the nanoporous binder-conductive additive phase, which have a crucial impact on electrochemical processes in the cathode and thus on the performance of battery cells.
本文介绍了锂离子电池分层结构阴极中纳米多孔粘结导电添加相的随机三维建模方法。这些电极的粘结导电添加相由炭黑、聚偏二氟乙烯粘结剂和石墨颗粒组成。为了对其进行随机三维建模，采用了基于随机几何方法的三步程序。首先，用椭圆形颗粒的布尔模型来描述石墨颗粒。其次，炭黑和粘合剂的混合物由石墨颗粒补充部分的高斯随机场偏移集建模。第三，炭黑和粘合剂混合物中的大孔隙区域由球形颗粒的布尔模型描述。模型参数根据聚焦离子束扫描电子显微镜获取的锂离子电池阴极三维图像数据进行校准。随后，通过比较模型实现值与测量图像数据，对模型进行验证，这些数据包含模型拟合时未使用的各种形态描述符。最后，我们使用随机 3D 模型进行预测模拟，生成具有不同数量石墨颗粒的纳米多孔粘结导电添加剂的虚拟但真实的图像数据。基于这些虚拟纳米结构，我们可以研究结构与性能之间的关系。特别是，我们定量研究了石墨颗粒对纳米多孔粘结剂导电添加剂相中有效传输特性的影响，这些特性对阴极的电化学过程以及电池的性能有着至关重要的影响。
{"title":"Data-driven stochastic 3D modeling of the nanoporous binder-conductive additive phase in battery cathodes","authors":"Phillip Gräfensteiner, Markus Osenberg, André Hilger, Nicole Bohn, Joachim R. Binder, Ingo Manke, Volker Schmidt, Matthias Neumann","doi":"arxiv-2409.11080","DOIUrl":"https://doi.org/arxiv-2409.11080","url":null,"abstract":"A stochastic 3D modeling approach for the nanoporous binder-conductive\u0000additive phase in hierarchically structured cathodes of lithium-ion batteries\u0000is presented. The binder-conductive additive phase of these electrodes consists\u0000of carbon black, polyvinylidene difluoride binder and graphite particles. For\u0000its stochastic 3D modeling, a three-step procedure based on methods from\u0000stochastic geometry is used. First, the graphite particles are described by a\u0000Boolean model with ellipsoidal grains. Second, the mixture of carbon black and\u0000binder is modeled by an excursion set of a Gaussian random field in the\u0000complement of the graphite particles. Third, large pore regions within the\u0000mixture of carbon black and binder are described by a Boolean model with\u0000spherical grains. The model parameters are calibrated to 3D image data of\u0000cathodes in lithium-ion batteries acquired by focused ion beam scanning\u0000electron microscopy. Subsequently, model validation is performed by comparing\u0000model realizations with measured image data in terms of various morphological\u0000descriptors that are not used for model fitting. Finally, we use the stochastic\u00003D model for predictive simulations, where we generate virtual, yet realistic,\u0000image data of nanoporous binder-conductive additives with varying amounts of\u0000graphite particles. Based on these virtual nanostructures, we can investigate\u0000structure-property relationships. In particular, we quantitatively study the\u0000influence of graphite particles on effective transport properties in the\u0000nanoporous binder-conductive additive phase, which have a crucial impact on\u0000electrochemical processes in the cathode and thus on the performance of battery\u0000cells.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"187 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The ICH E9 (R1) addendum on estimands, coupled with recent advancements in causal inference, has prompted a shift towards using model-free treatment effect estimands that are more closely aligned with the underlying scientific question. This represents a departure from traditional, model-dependent approaches where the statistical model often overshadows the inquiry itself. While this shift is a positive development, it has unintentionally led to the prioritization of an estimand's theoretical appeal over its practical learnability from data under plausible assumptions. We illustrate this by scrutinizing assumptions in the recent clinical trials literature on principal stratum estimands, demonstrating that some popular assumptions are not only implausible but often inevitably violated. We advocate for a more balanced approach to estimand formulation, one that carefully considers both the scientific relevance and the practical feasibility of estimation under realistic conditions.
ICH E9 (R1)关于估计值的附录，加上最近因果推断方面的进步，促使人们转向使用与基本科学问题更密切相关的无模型治疗效果估计值。虽然这种转变是一种积极的发展，但它无意中导致了估算指标的理论吸引力优先于其在合理假设下从数据中的实际可学习性。我们通过对近期临床试验文献中有关本底估计值的假设进行细分来说明这一点，证明一些流行的假设不仅不合理，而且经常不可避免地遭到违反。我们主张采用更加平衡的方法来制定估计值，即在现实条件下仔细考虑估计值的科学相关性和实际可行性。
{"title":"Chasing Shadows: How Implausible Assumptions Skew Our Understanding of Causal Estimands","authors":"Stijn Vansteelandt, Kelly Van Lancker","doi":"arxiv-2409.11162","DOIUrl":"https://doi.org/arxiv-2409.11162","url":null,"abstract":"The ICH E9 (R1) addendum on estimands, coupled with recent advancements in\u0000causal inference, has prompted a shift towards using model-free treatment\u0000effect estimands that are more closely aligned with the underlying scientific\u0000question. This represents a departure from traditional, model-dependent\u0000approaches where the statistical model often overshadows the inquiry itself.\u0000While this shift is a positive development, it has unintentionally led to the\u0000prioritization of an estimand's theoretical appeal over its practical\u0000learnability from data under plausible assumptions. We illustrate this by\u0000scrutinizing assumptions in the recent clinical trials literature on principal\u0000stratum estimands, demonstrating that some popular assumptions are not only\u0000implausible but often inevitably violated. We advocate for a more balanced\u0000approach to estimand formulation, one that carefully considers both the\u0000scientific relevance and the practical feasibility of estimation under\u0000realistic conditions.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：