Australian & New Zealand Journal of Statistics最新文献

{"title":"The incremental progression from fixed to random factors in the analysis of variance: a new synthesis","authors":"Marti J. Anderson,&nbsp;Ray N. Gorley,&nbsp;Antonio Terlizzi","doi":"10.1111/anzs.70001","DOIUrl":"https://doi.org/10.1111/anzs.70001","url":null,"abstract":"<p>Classically, the distinction between a fixed versus a random factor in analysis of variance has been considered a binary choice. Here we consider that any given factor can also occur along an incremental series of steps between these two extremes, depending on the sampling fraction of its levels from the wider population. Fixed factors occur where all possible levels are drawn, and random factors occur in the limit as the population of possible levels approaches infinity. When some identifiable fraction of a finite population of possible levels is drawn, the factor can be thought of as something in between fixed and random, and can be analysed explicitly as finite directly within the analysis of variance (ANOVA) framework. Requiring explicit specification of the population size from which observed levels are drawn for each factor, we provide a unified approach to derive expectations of mean squares (EMS) in ANOVA for any types of factors along the entire graded progression from fixed to random, inclusive, that may be nested within or crossed with one another, from balanced, asymmetrical or unbalanced designs, including multi-level hierarchical sampling designs, mixed models and interactions. Implications for estimation of variance components, tailored bootstrap methods and tests of hypotheses under minimal assumptions of exchangeability are described and further extended to multivariate dissimilarity-based settings.</p>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"3-30"},"PeriodicalIF":0.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/anzs.70001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simultaneous clustering of individuals and covariates for high-dimensional longitudinal data","authors":"Chao Han,&nbsp;Jiaqi Wu,&nbsp;Weiping Zhang","doi":"10.1111/anzs.12437","DOIUrl":"https://doi.org/10.1111/anzs.12437","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper considers identifying and estimating high-dimensional longitudinal data models with latent subgroups and clustered covariates. We propose a regularised approach to recover group structures while simultaneously detecting clusters of significant covariates. The consistency and asymptotic normality are established for the estimator under mild conditions. Besides, we develop an effective algorithm based on local quadratic approximation to optimise the objective function. The finite-sample performance is illustrated through extensive simulations, and the proposed method is applied to study the shift in the economic structure of European countries before and after the debt crisis.</p>\u0000 </div>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"31-50"},"PeriodicalIF":0.8,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of nonparametric approach to extreme value inference in distribution estimation of sample maximum and its properties","authors":"T. Moriyama","doi":"10.1111/anzs.12436","DOIUrl":"https://doi.org/10.1111/anzs.12436","url":null,"abstract":"<div>\u0000 \u0000 <p>Extreme value theory has constructed asymptotic properties of the sample maximum. This article concerns probability distribution estimation of the sample maximum. The traditional approach is parametric fitting to the limiting distribution—the generalised extreme value distribution; however, the model in non-limiting cases is misspecified to a certain extent. We propose a plug-in type of nonparametric estimator that does not need model specification. Asymptotic properties of the distribution estimator are derived. The simulation study numerically investigates the relative performance in finite-sample cases. This study assumes that the underlying distribution of the original sample belongs to one of the Hall class, the Weibull class or the bounded class, whose types of the limiting distributions are all different: the Fréchet, Gumbel or Weibull. It is proven that the convergence rate of the parametric fitting estimator depends on both the extreme value index and the second-order parameter, and gets slower as the extreme value index tends to zero. On the other hand, the rate of the nonparametric estimator is proven to be independent of the extreme value index under certain conditions. The numerical performances of the parametric fitting estimator and the nonparametric estimator are compared, which shows that the nonparametric estimator performs better, especially for the extreme value index close to zero. Finally, we report two real case studies: the Potomac River peak stream flow (cfs) data and the Danish Fire Insurance data.</p>\u0000 </div>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"51-76"},"PeriodicalIF":0.8,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Circular and spherical projected Cauchy distributions: A novel framework for directional data modelling","authors":"M. Tsagris,&nbsp;O. Alzeley","doi":"10.1111/anzs.12434","DOIUrl":"https://doi.org/10.1111/anzs.12434","url":null,"abstract":"<div>\u0000 \u0000 <p>We introduce a novel family of projected distributions on the circle and the sphere, called the circular and spherical projected Cauchy distributions, as promising alternatives for modelling circular and spherical data. The circular distribution encompasses the wrapped Cauchy distribution as a special case while featuring a more convenient parameterisation. We also propose a generalised wrapped Cauchy distribution that includes an extra parameter, enhancing the fit of the distribution. In the spherical context, we impose two conditions on the scatter matrix of the Cauchy distribution, resulting in an elliptically symmetric distribution. Our projected distributions exhibit attractive properties such as a closed-form normalising constant and straightforward random value generation. The distribution parameters can be estimated using maximum likelihood, and we assess their bias through numerical studies. Further, we compare our proposed distributions with existing models with real datasets, demonstrating equal or superior fitting both with and without covariates.</p>\u0000 </div>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"77-103"},"PeriodicalIF":0.8,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lower bounds of projection weighted symmetric discrepancy on uniform designs","authors":"Hao Zheng,&nbsp;Kang Fu,&nbsp;Yao Xiao","doi":"10.1111/anzs.12433","DOIUrl":"https://doi.org/10.1111/anzs.12433","url":null,"abstract":"<div>\u0000 \u0000 <p>A critical aspect of experimental designs is to determine the effective and efficient lower bounds of the discrepancy criterion in uniform designs. These lower bounds serve as benchmarks for measuring the design uniformity and for constructing uniform designs. Nowadays, symmetric discrepancy and projection weighted symmetric discrepancy are two commonly used discrepancy criteria. In this paper, we investigate the general lower bounds of these two discrepancies for symmetric multi-level designs and present sharp lower bounds for three-level designs, thereby complementing the existing lower bound theory of discrepancies in uniform designs. Several design examples are used to validate the theoretical results presented. Furthermore, we conduct two popular practical computer experiments to evaluate the performance of uniform designs based on these two discrepancies.</p>\u0000 </div>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"104-120"},"PeriodicalIF":0.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Post-Shrinkage Strategies in Statistical and Machine Learning for High Dimensional Data. By S. E. Ahmed, F. Ahmed, and B. Yüzbaşi, Boca Raton, FL: CRC Press. 2023. 408 pages. AU$ 210.40 (hardback). ISBN: 978-0-367-77205-5.","authors":"Paul Kabaila","doi":"10.1111/anzs.12432","DOIUrl":"https://doi.org/10.1111/anzs.12432","url":null,"abstract":"","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"121-122"},"PeriodicalIF":0.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simon Christopher Barry, 12 February 1965–16 July 2023","authors":"Brent Henderson,&nbsp;Peter Caley,&nbsp;Emma Lawrence,&nbsp;Alan Welsh","doi":"10.1111/anzs.12431","DOIUrl":"https://doi.org/10.1111/anzs.12431","url":null,"abstract":"&lt;p&gt;Simon Barry was a statistical scientist of the highest calibre, a champion for the discipline throughout his illustrious career in government, the CSIRO and academia. He was a giant physically (a 6′ 5′′ frame with his frizzy hair seeming to gift additional height) and intellectually, who made a strong and lasting impression on all who encountered him. Tragically, Simon Barry died in a car accident on 16 July 2023, aged 58, leaving the world a diminished place.&lt;/p&gt;&lt;p&gt;Simon was born in Brisbane but grew up in Canberra, attending Pearce Primary School, Lyneham Primary School, Lyneham High School and Dickson College. He commenced an agriculture degree at the University of Sydney but transferred to Australian National University (ANU) after his second year where he studied botany. He started his honours degree working on the genetics of &lt;i&gt;Onychophora&lt;/i&gt; a.k.a. peripatus, before switching to statistics, and graduating with first class honours in 1990. Field work in his thesis involved breaking open rotting logs to find peripatus, and then collecting them, along with any funnel webs also present in the logs (for a colleague doing a similar study).&lt;/p&gt;&lt;p&gt;Simon's first job was at the Australian Bureau of Statistics (ABS) and it gave him a valuable grounding in survey sampling and survey inference, but whetted his appetite for more. He subsequently joined the Australian Defence Force Academy (ADFA) in Canberra, working with Ted Catchpole and Ted's UK collaborators Byron Morgan and Steve Brooks on capture-recapture methods. While at ADFA, he commenced a PhD at the ANU on modelling truncated data (supervised by Terry O'Neill) and was awarded his PhD in 1996 (Barry &lt;span&gt;1995&lt;/span&gt;). His thesis received the P.A.P. Moran Prize at the ANU for its contribution to the Advancement of Probability or Statistics in 1999.&lt;/p&gt;&lt;p&gt;Simon joined the ANU as a consultant in the Statistical Consulting Unit with Ross Cunningham and Christine Donnelly and later as a lecturer in the then Department of Statistics and Econometrics. He collaborated with many in the ANU, but particularly those with a passion for ecology (Gibbons &lt;i&gt;et al&lt;/i&gt;. &lt;span&gt;2000&lt;/span&gt;; Cunningham &lt;i&gt;et al&lt;/i&gt;. &lt;span&gt;2006&lt;/span&gt;; Manning &lt;i&gt;et al&lt;/i&gt;. &lt;span&gt;2006&lt;/span&gt;).&lt;/p&gt;&lt;p&gt;In 1999, Simon joined the Bureau of Rural Sciences (BRS), then the science research division in the Commonwealth Department of Agriculture, Fisheries and Forestry (DAFF). For the first few years he was the only statistician working in a mostly GIS group, but as Simon preached how statistics could change the lives of all the people in DAFF and demonstrated how he could do so, the team grew and he flourished personally.&lt;/p&gt;&lt;p&gt;One aspect that his BRS work provided was the opportunity to ‘fight fires’, as he put it. These were the real-world, big-impact projects where management decisions had the potential for real impact. Never shy of engaging in healthy dispute, Simon pushed to make changes in very significant areas such as import ","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"123-129"},"PeriodicalIF":0.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/anzs.12431","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"John Newton Darroch, 1930–2024","authors":"Gary Glonek","doi":"10.1111/anzs.12430","DOIUrl":"https://doi.org/10.1111/anzs.12430","url":null,"abstract":"&lt;p&gt;John Darroch was born in England in Melksham, Wiltshire, to George Darroch and Phyllis Lacey on 22 October 1930 and died, aged 93 years, on 15 April 2024.&lt;/p&gt;&lt;p&gt;He attended grammar school where he excelled in the classroom and at sports, and subsequently gained admission to study civil engineering at the University of Bristol. Recognising his talent, his mathematics teacher persuaded him to postpone university and take the exam for the Cambridge Open Scholarship to study mathematics.&lt;/p&gt;&lt;p&gt;John was successful and studied for 4 years, specialising in theoretical physics and completing the Diploma in Mathematical Statistics under the supervision of Dennis Lindley. He studied briefly with R.A. Fisher in this time, although this appears not to have been a significant factor in his future career choices. It was also there that he met his future wife, Elisabeth Pennington. He completed 2 years of national service in the RAF, at the rank of Pilot Officer, teaching mathematics, and in 1955 he and Elisabeth set sail for Cape Town to take up his new position as a lecturer at the University.&lt;/p&gt;&lt;p&gt;John arrived at the University of Cape Town ‘with no thought of doing any research’. Within a few months, an enquiry from the professor of biology awakened his instinct for research, culminating in his 1958 &lt;i&gt;Biometrika&lt;/i&gt; paper on capture-recapture experiments. He enrolled in a Ph.D. by Publication program at Cape Town, and was subsequently awarded the degree on the basis of his series of three &lt;i&gt;Biometrika&lt;/i&gt; papers on capture-recapture (Darroch &lt;span&gt;1958&lt;/span&gt;, &lt;span&gt;1959&lt;/span&gt;, &lt;span&gt;1961&lt;/span&gt;). This seminal contribution proposed models and provided maximum likelihood estimates for a number of capture-recapture settings, and provided a basis for much of the development that followed. It was through this work, undertaken without supervision and with only rudimentary access to the literature, that John developed his first-principles approach to research.&lt;/p&gt;&lt;p&gt;John's academic career flourished. He and Elisabeth returned to England to take up a lectureship at the University of Manchester, where he supervised George Seber for a period introducing him to a problem in capture-recapture. Keen to escape the cold winters, John and his young family moved to Adelaide where he took up a senior lectureship at the University of Adelaide. This was followed by a position at the University of Michigan, Ann Arbor, but John and his family were drawn back to Adelaide. In 1966 he was offered and accepted the Inaugural Chair in Statistics at Flinders University, a position he held until his retirement in 1996.&lt;/p&gt;&lt;p&gt;John is best known for his contributions to statistical methodology, especially in the area of multivariate categorical data. His work was recognised in 2005 through the award of the SSA Pitman Medal. Writing in support of the award, Stephen Fienberg observed: &lt;i&gt;Someone once remarked to me that there are few statisticians who have a major new idea that coul","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"67 1","pages":"130-134"},"PeriodicalIF":0.8,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/anzs.12430","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PanIC: Consistent information criteria for general model selection problems","authors":"Hien Duy Nguyen","doi":"10.1111/anzs.12426","DOIUrl":"https://doi.org/10.1111/anzs.12426","url":null,"abstract":"<p>Model selection is a ubiquitous problem that arises in the application of many statistical and machine learning methods. In the likelihood and related settings, it is typical to use the method of information criteria (ICs) to choose the most parsimonious among competing models by penalizing the likelihood-based objective function. Theorems guaranteeing the consistency of ICs can often be difficult to verify and are often specific and bespoke. We present a set of results that guarantee consistency for a class of ICs, which we call PanIC (from the Greek root ‘<i>pan</i>’, meaning ‘<i>of everything</i>’), with easily verifiable regularity conditions. PanICs are applicable in any loss-based learning problem and are not exclusive to likelihood problems. We illustrate the verification of regularity conditions for model selection problems regarding finite mixture models, least absolute deviation and support vector regression and principal component analysis, and demonstrate the effectiveness of PanICs for such problems via numerical simulations. Furthermore, we present new sufficient conditions for the consistency of BIC-like estimators and provide comparisons of the BIC with PanIC.</p>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"66 4","pages":"441-466"},"PeriodicalIF":0.8,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/anzs.12426","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142869230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction de-correlated inference: A safe approach for post-prediction inference","authors":"Feng Gan,&nbsp;Wanfeng Liang,&nbsp;Changliang Zou","doi":"10.1111/anzs.12429","DOIUrl":"https://doi.org/10.1111/anzs.12429","url":null,"abstract":"<div>\u0000 \u0000 <p>In modern data analysis, it is common to use machine learning methods to predict outcomes on unlabelled datasets and then use these pseudo-outcomes in subsequent statistical inference. Inference in this setting is often called post-prediction inference. We propose a novel assumption-lean framework for statistical inference under post-prediction setting, called prediction de-correlated inference (PDC). Our approach is safe, in the sense that PDC can automatically adapt to any black-box machine-learning model and consistently outperform the supervised counterparts. The PDC framework also offers easy extensibility for accommodating multiple predictive models. Both numerical results and real-world data analysis demonstrate the superiority of PDC over the state-of-the-art methods.</p>\u0000 </div>","PeriodicalId":55428,"journal":{"name":"Australian & New Zealand Journal of Statistics","volume":"66 4","pages":"417-440"},"PeriodicalIF":0.8,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142869056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}