In the statistics community, outlier detection for time series data has been studied for decades. Recently, with advances in hardware and software technology, there has been a large body of work on temporal outlier detection from a computational perspective within the computer science community. In particular, advances in hardware technology have enabled the availability of various forms of temporal data collection mechanisms, and advances in software technology have enabled a variety of data management mechanisms. This has fueled the growth of different kinds of data sets such as data streams, spatio-temporal data, distributed streams, temporal networks, and time series data, generated by a multitude of applications. There arises a need for an organized and detailed study of the work done in the area of outlier detection with respect to such temporal datasets. In this survey, we provide a comprehensive and structured overview of a large set of interesting outlier definitions for various forms of temporal data, novel techniques, and application scenarios in which specific definitions and techniques have been widely used.

https://romisatriawahono.net/lecture/rm/survey/machine%20learning/Gupta%20-%20Outlier%20Detection%20for%20Temporal%20Data%20-%202014.pdf

Outlier Detection for Temporal Data: A Survey

We developed a linear-time algorithm applicable to a large class of trait evolution models, for efficient likelihood calculations and parameter inference on very large trees. Our algorithm solves the traditional computational burden associated with two key terms, namely the determinant of the phylogenetic covariance matrix V and quadratic products involving the inverse of V. Applications include Gaussian models such as Brownian motion-derived models like Pagel's lambda, kappa, delta, and the early-burst model; Ornstein-Uhlenbeck models to account for natural selection with possibly varying selection parameters along the tree; as well as non-Gaussian models such as phylogenetic logistic regression, phylogenetic Poisson regression, and phylogenetic generalized linear mixed models. Outside of phylogenetic regression, our algorithm also applies to phylogenetic principal component analysis, phylogenetic discriminant analysis or phylogenetic prediction. The computational gain opens up new avenues for complex models or extensive resampling procedures on very large trees. We identify the class of models that our algorithm can handle as all models whose covariance matrix has a 3-point structure. We further show that this structure uniquely identifies a rooted tree whose branch lengths parametrize the trait covariance matrix, which acts as a similarity matrix. The new algorithm is implemented in the R package phylolm, including functions for phylogenetic linear regression and phylogenetic logistic regression.

/pdf/a-linear-time-algorithm-for-gaussian-and-non-gaussian-trait-3rjr4wvm1h.pdf

A Linear-Time Algorithm for Gaussian and Non-Gaussian Trait Evolution Models

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal. This paper presents a random forest for spatial predictions framework (RFsp) where buffer distances from observation points are used as explanatory variables, thus incorporating geographical proximity effects into the prediction process. The RFsp framework is illustrated with examples that use textbook datasets and apply spatial and spatio-temporal prediction to numeric, binary, categorical, multivariate and spatiotemporal variables. Performance of the RFsp framework is compared with the state-of-the-art kriging techniques using fivefold cross-validation with refitting. The results show that RFsp can obtain equally accurate and unbiased predictions as different versions of kriging. Advantages of using RFsp over kriging are that it needs no rigid statistical assumptions about the distribution and stationarity of the target variable, it is more flexible towards incorporating, combining and extending covariates of different types, and it possibly yields more informative maps characterizing the prediction error. RFsp appears to be especially attractive for building multivariate spatial prediction models that can be used as "knowledge engines" in various geoscience fields. Some disadvantages of RFsp are the exponentially growing computational intensity with increase of calibration data and covariates and the high sensitivity of predictions to input data quality. The key to the success of the RFsp framework might be the training data quality-especially quality of spatial sampling (to minimize extrapolation problems and any type of bias in data), and quality of model validation (to ensure that accuracy is not effected by overfitting). For many data sets, especially those with lower number of points and covariates and close-to-linear relationships, model-based geostatistics can still lead to more accurate predictions than RFsp.

Random Forest as a generic framework for predictive modeling of spatial and spatio-temporal variables

Robert Dunn was supported by the Met Office Hadley Centre Climate Programme funded by BEIS and Defra (GA01101) and thanks Nick Rayner and Lizzie Good for helpful comments on the manuscript Lisa Alexander is supported by the Australian Research Council (ARC) Grants DP160103439 and CE170100023 Markus Donat acknowledges funding by the Spanish Ministry for the Economy, Industry and Competitiveness Ramon y Cajal 2017 Grant Reference RYC‐2017‐22964 Mohd Noor'Arifin Bin Hj Yussof and Muhammad Khairul Izzat Bin Ibrahim thank the Brunei Darussalam Meteorological Department (BDMD) Ying Sun was supported by China funding agencies 2018YFA0605604 and 2018YFC1507702 Fatemeh Rahimzadeh and Mahbobeh Khoshkam thank IR of Iranian Meteorological Organization (IRIMO) and the Atmospheric Science and Meteorological Organization Research Center (ASMERC) for Data and also sharing their experiences, especially Abbas Rangbar Jose Marengo was supported by the National Institute of Science and Technology for Climate Change Phase 2 under CNPq Grant 465501/2014‐1, FAPESP Grants 2014/50848‐9 and 2015/03804‐9, and the National Coordination for High Level Education and Training (CAPES) Grant 88887136402‐00INCT The team that worked on the data in West Africa received funding from the UK's National Environment Research Council (NERC)/Department for International Development DFID) Future Climate For Africa programme, under the AMMA‐2050 project (Grants NE/M020428/1 and NE/M019969/1) Data from Southeast Asia (excl Indonesia) was supported by work on using ClimPACT2 during the Second Workshop on ASEAN Regional Climate Data, Analysis and Projections (ARCDAP‐2), 25–29 March 2019, Singapore, jointly funded by Meteorological Service Singapore and WMO through the Canada‐Climate Risk and Early Warning Systems (CREWS) initiative This research was supported by Thai Meteorological Department (TMD) and Thailand Science Research and Innovation (TSRI) under Grant RDG6030003 Daily data for Mexico were provided by the Servicio Meteorologico Nacional (SMN) of Comision Nacional del Agua (CONAGUA) We acknowledge the data providers in the ECA&D project (https://wwwecadeu), the SACA&D project (https://saca-bmkgknminl), and the LACA&D project (https://ciifenknminl) We thank the three anonymous reviewers for their detailed comments which improved the manuscript

Development of an updated global land In situ‐based data set of temperature and precipitation extremes : HadEX3

Summary 1. Presence-only records may provide data on the distributions of rare species, but commonly suffer from large, unknown biases due to their typically haphazard collection schemes. Presence–absence or count data collected in systematic, planned surveys are more reliable but typically less abundant. 2. We proposed a probabilistic model to allow for joint analysis of presence-only and survey data to exploit their complementary strengths. Our method pools presence-only and presence–absence data for many species and maximizes a joint likelihood, simultaneously estimating and adjusting for the sampling bias affecting the presence-only data. By assuming that the sampling bias is the same for all species, we can borrow strength across species to efficiently estimate the bias and improve our inference from presence-only data. 3. We evaluate our model’s performance on data for 36 eucalypt species in south-eastern Australia. We find that presence-only records exhibit a strong sampling bias towards the coast and towards Sydney, the largest city. Our data-pooling technique substantially improves the out-of-sample predictive performance of our model when the amount of available presence–absence data for a given species is scarce 4. If we have only presence-only data and no presence–absence data for a given species, but both types of data for several other species that suf fer from the same spatial sampling bias, then our method can obtain an unbiased estimate of the first species’ geographic range.

SPECIAL FEATURE PAPER: NEW OPPORTUNITIES AT THE INTERFACE BETWEEN ECOLOGY AND STATISTICS Bias correction in species distribution models: pooling survey and collection data for multiple species

Statistics For Spatial Data

The aim of this retrospective study was to evaluate the oral health-related quality of life (oHRQoL) and patient-reported outcome measures (PROMs) after 10 years of supportive periodontal care (SPC).Patients were re-examined 120±12 months after active periodontal therapy. Dental and periodontal status and oHRQoL by completing Oral Health Impact Profile-G49 (OHIP-G49) and PROMs by marking a visual analogue scale (VAS) for self-perceived esthetics (VASe), chewing function (VASc), and hygiene ability (VASh) were assessed. Patient- and tooth-related factors (age, insurance status, number of SPC, compliance, change of therapist, smoking, tooth loss, need for surgery or antibiotic intake, bleeding on probing (BOP), periodontal inflamed surface area) influencing oHRQoL and PROMs were evaluated.One hundred eight periodontally compromised patients (59 female, mean age 65.4±10.7 years) lost 135 teeth during 10 years of SPC. At re-examination, 1.8% of all sites showed PPD ≥6mm. The mean OHIP-G49 sum score was 17.6±18.5, and VAS resulted in 76.0±22.5 (VASe), 86.3±16.3 (VASc), and 79.8±15.8 (VASh). Linear regression analyses identified a positive correlation with oHRQoL and/or PROMs for private insurance status (OHIP-G49, p=0.015, R2=0.204; VASc, p=0.005, R2=0.084; VASh, p=0.012, R2=0.222) and compliance to SPC (VASe, p=0.032; R2=0.204), as well as a negative correlation for active smoking (VASc, p=0.012, R2=0.084), increased BOP (VASh, p=0.029, R2=0.222) at the start of SPC, and number of lost molars (VASh, p=0.008, R2=0.222).It is realistic to obtain satisfactory oHRQoL and PROM values in most of the patients after 10 years of SPC. The identified factors may help to predict patient satisfaction in the long-term course of therapy.Systematic therapy of periodontally compromised patients provides values for oHRQoL and PROMs in a favorable range 10 years after therapy. This should encourage dentists to implement SPC in their daily routine.NCT03048045. 

https://link.springer.com/content/pdf/10.1007/s00784-023-04876-9.pdf

Luca Vogt

Papers

Statistics For Spatial Data

Oral health-related quality of life and patient-reported outcome measures after 10 years of supportive periodontal care