The Russian war in Ukraine increased Ukrainian language use on social media.

The use of language is innately political, often a vehicle of cultural identity and the basis for nation building. Here, we examine language choice and tweeting activity of Ukrainian citizens based on 4,453,341 geo-tagged tweets from 62,712 users before and during the Russian war in Ukraine, from January 2020 to October 2022. Using statistical models, we disentangle sample effects, arising from the in- and outflux of users on Twitter (now X), from behavioural effects, arising from behavioural changes of the users. We observe a steady shift from the Russian language towards Ukrainian already before the war, which drastically speeds up with its outbreak. We attribute these shifts in large part to users' behavioural changes. Notably, our analysis shows that more than half of the Russian-tweeting users switch towards Ukrainian with the Russian invasion. We interpret these findings as users' conscious choice towards a more Ukrainian (online) identity and self-definition of being Ukrainian.

COVID-19 and social media: Beyond polarization.

The COVID-19 pandemic brought upon a massive wave of disinformation, exacerbating polarization in the increasingly divided landscape of online discourse. In this context, popular social media users play a major role, as they have the ability to broadcast messages to large audiences and influence public opinion. In this article, we make use of openly available data to study the behavior of popular users discussing the pandemic on Twitter. We tackle the issue from a network perspective, considering users as nodes and following relationships as directed edges. The resulting network structure is modeled by embedding the actors in a latent social space, where users closer to one another have a higher probability of following each other. The results suggest the existence of two distinct communities, which can be interpreted as "generally pro" and "generally against" vaccine mandates, corroborating existing evidence on the pervasiveness of echo chambers on the platform. By focusing on a number of notable users, such as politicians, activists, and news outlets, we further show that the two groups are not entirely homogeneous, and that not just the two poles are represented. To the contrary, the latent space captures an entire spectrum of beliefs between the two extremes, demonstrating that polarization, while present, is not the only driver of the network, and that more moderate, "central" users are key players in the discussion.

Discussion on On the role of data, statistics and decisions in a pandemic: by Jahn et al (2022).

The authors make an important contribution presenting a comprehensive and thoughtful overview about the many different aspects of data, statistics and data analyses in times of the recent COVID-19 pandemic discussing all relevant topics. The paper certainly provides a very valuable reflection of what has been done, what could have been done and what needs to be done. We contribute here with a few comments and some additional issues. We do not discuss all chapters of Jahn et al. (AStA Adv Stat Anal, 2022. 10.1007/s10182-022-00439-7), but focus on those where our personal views and experiences might add some additional aspects.

[Mandatory Testing in Schools can Significantly Reduce Underreporting of COVID-19 Infections Among Students with in-Class Teaching Compared to Home Schooling]. / Reihentestungen an Schulen können die Dunkelziffer von COVID-19 Infektionen unter Schülern signifikant senken.

Aim of the study The aim of this was to study investigate the effectiveness of mandatory Covid-19 tests for in-classroom teaching in reopened schools as a containment measure in the pandemic. In Bavaria, mandatory testing at schools was implemented directly after the Easter vacations in 2021. For the first week after the vacations, this resulted in a natural experiment that allowed us to quantify the impact of the new testing strategy on reported Covid-19 cases.Methods We compared changes in the reported 7-day incidence of new infections between districts with in-classroom teaching at school and districts with closed schools. During the calendar week 15, districts with reported incidences below 100 were allowed to reopen schools and have in-classroom teaching if mandatory COVID-19 testing was performed at school with rapid antigen tests. We do not have data on the rapid test results; however, positive test results in the rapid antigen test were verified by a PCR test, and cases of positive PCR test results were reported at the district level by age groups. In the calendar weeks 13 and 14, all schools in Bavaria were closed due to Easter vacations. Taking into account a latency period of about 3-4 days and a reporting period of 1-2 days, this means that any additional increase in reported incidences for districts with in-class teaching and mandatory testing in the week after the vacation cannot be attributed to transmissions at schools, but reflects the reduction of underreporting due to the newly implemented testing strategy.Results Reported incidence increased by a factor of 6.6 for 5-11 year old and by 1.7 for 12-20 year old pupils in districts with in-classroom teaching and mandatory testing at schools. This increase was accompanied by a reduction in underreporting and was significant compared to districts with school closure. Given the situation of a natural experiment, this increase in the reported incidence among school children can be attributed to the testing strategy. For the same time period, no differences in reported incidences were found for the other age groups.Conclusion In-class teaching with mandatory testing in reopened schools changes the role of schools in the pandemic. Our analyses show that reopening schools with a mandatory testing approach is beneficial from an epidemiologic perspective as it can strongly reduce the dark figure of COVID-19 cases among children.

Regional now- and forecasting for data reported with delay: toward surveillance of COVID-19 infections.

Governments around the world continue to act to contain and mitigate the spread of COVID-19. The rapidly evolving situation compels officials and executives to continuously adapt policies and social distancing measures depending on the current state of the spread of the disease. In this context, it is crucial for policymakers to have a firm grasp on what the current state of the pandemic is, and to envision how the number of infections is going to evolve over the next days. However, as in many other situations involving compulsory registration of sensitive data, cases are reported with delay to a central register, with this delay deferring an up-to-date view of the state of things. We provide a stable tool for monitoring current infection levels as well as predicting infection numbers in the immediate future at the regional level. We accomplish this through nowcasting of cases that have not yet been reported as well as through predictions of future infections. We apply our model to German data, for which our focus lies in predicting and explain infectious behavior by district. Supplementary Information: The online version contains supplementary material available at 10.1007/s10182-021-00433-5.

On the interplay of regional mobility, social connectedness and the spread of COVID-19 in Germany.

Since the primary mode of respiratory virus transmission is person-to-person interaction, we are required to reconsider physical interaction patterns to mitigate the number of people infected with COVID-19. While research has shown that non-pharmaceutical interventions (NPI) had an evident impact on national mobility patterns, we investigate the relative regional mobility behaviour to assess the effect of human movement on the spread of COVID-19. In particular, we explore the impact of human mobility and social connectivity derived from Facebook activities on the weekly rate of new infections in Germany between 3 March and 22 June 2020. Our results confirm that reduced social activity lowers the infection rate, accounting for regional and temporal patterns. The extent of social distancing, quantified by the percentage of people staying put within a federal administrative district, has an overall negative effect on the incidence of infections. Additionally, our results show spatial infection patterns based on geographical as well as social distances.

A statistical model for the dynamics of COVID-19 infections and their case detection ratio in 2020.

The case detection ratio of coronavirus disease 2019 (COVID-19) infections varies over time due to changing testing capacities, different testing strategies, and the evolving underlying number of infections itself. This note shows a way of quantifying these dynamics by jointly modeling the reported number of detected COVID-19 infections with nonfatal and fatal outcomes. The proposed methodology also allows to explore the temporal development of the actual number of infections, both detected and undetected, thereby shedding light on the infection dynamics. We exemplify our approach by analyzing German data from 2020, making only use of data available since the beginning of the pandemic. Our modeling approach can be used to quantify the effect of different testing strategies, visualize the dynamics in the case detection ratio over time, and obtain information about the underlying true infection numbers, thus enabling us to get a clearer picture of the course of the COVID-19 pandemic in 2020.

Nowcasting fatal COVID-19 infections on a regional level in Germany.

We analyse the temporal and regional structure in mortality rates related to COVID-19 infections, making use of the openly available data on registered cases in Germany published by the Robert Koch Institute on a daily basis. Estimates for the number of present-day infections that will, at a later date, prove to be fatal are derived through a nowcasting model, which relates the day of death of each deceased patient to the corresponding day of registration of the infection. Our district-level modelling approach for fatal infections disentangles spatial variation into a global pattern for Germany, district-specific long-term effects and short-term dynamics, while also taking the age and gender structure of the regional population into account. This enables to highlight areas with unexpectedly high disease activity. The analysis of death counts contributes to a better understanding of the spread of the disease while being, to some extent, less dependent on testing strategy and capacity in comparison to infection counts. The proposed approach and the presented results thus provide reliable insight into the state and the dynamics of the pandemic during the early phases of the infection wave in spring 2020 in Germany, when little was known about the disease and limited data were available.

Exploring the statistical uncertainty in acceptable exposure limit values for hexavalent chromium exposure.

Exposure limit values give the exposure level at which an accepted (or acceptable) number of additional work related diseases are expected. The values are derived from dose-response curves and carry a large amount of uncertainty. In this paper we aim to quantify some of this uncertainty with statistical means. We explore the limit value issued by the European Chemical Agency (ECHA) for occupational exposure to hexavalent chromium, CR(VI). We investigate how the dose-response model and statistical estimation variability influences the data-based fixation of exposure limit values. We also look at the effect of measurement variation on the exposure level itself, where simulation techniques allow to quantify the uncertainty in statistical terms. We demonstrate that statistical uncertainty needs to be taken into account when fixing exposure limit values based on data.

Automated processing of webcam images for phenological classification.

Along with the global climate change, there is an increasing interest for its effect on phenological patterns such as start and end of the growing season. Scientific digital webcams are used for this purpose taking every day one or more images from the same natural motive showing for example trees or grassland sites. To derive phenological patterns from the webcam images, regions of interest are manually defined on these images by an expert and subsequently a time series of percentage greenness is derived and analyzed with respect to structural changes. While this standard approach leads to satisfying results and allows to determine dates of phenological change points, it is associated with a considerable amount of manual work and is therefore constrained to a limited number of webcams only. In particular, this forbids to apply the phenological analysis to a large network of publicly accessible webcams in order to capture spatial phenological variation. In order to be able to scale up the analysis to several hundreds or thousands of webcams, we propose and evaluate two automated alternatives for the definition of regions of interest, allowing for efficient analyses of webcam images. A semi-supervised approach selects pixels based on the correlation of the pixels' time series of percentage greenness with a few prototype pixels. An unsupervised approach clusters pixels based on scores of a singular value decomposition. We show for a scientific webcam that the resulting regions of interest are at least as informative as those chosen by an expert with the advantage that no manual action is required. Additionally, we show that the methods can even be applied to publicly available webcams accessed via the internet yielding interesting partitions of the analyzed images. Finally, we show that the methods are suitable for the intended big data applications by analyzing 13988 webcams from the AMOS database. All developed methods are implemented in the statistical software package R and publicly available in the R package phenofun. Executable example code is provided as supplementary material.

Mixture model to assess the extent of cross-transmission of multidrug-resistant pathogens in hospitals.

OBJECTIVE: Creation of a mixture model based on Poisson processes for assessment of the extent of cross-transmission of multidrug-resistant pathogens in the hospital. METHODS: We propose a 2-component mixture of Poisson processes to describe the time series of detected cases of colonization. The first component describes the admission process of patients with colonization, and the second describes the cross-transmission. The data set used to illustrate the method consists of the routinely collected records for methicillin-resistant Staphylococcus aureus (MRSA), imipenem-resistant Pseudomonas aeruginosa, and multidrug-resistant Acinetobacter baumannii over a period of 3 years in a German tertiary care hospital. RESULTS: For MRSA and multidrug-resistant A. baumannii, cross-transmission was estimated to be responsible for more than 80% of cases; for imipenem-resistant P. aeruginosa, cross-transmission was estimated to be responsible for 59% of cases. For new cases observed within a window of less than 28 days for MRSA and multidrug-resistant A. baumannii or 40 days for imipenem-resistant P. aeruginosa, there was a 50% or greater probability that the cause was cross-transmission. CONCLUSIONS: The proposed method offers a solution to assessing of the extent of cross-transmission, which can be of clinical use. The method can be applied using freely available software (the package FlexMix in R) and it requires relatively little data.

Using penalized splines to model age- and season-of-birth-dependent effects of childhood mortality risk factors in rural Burkina Faso.

Several previous studies have identified risk factors for childhood mortality in high risk areas, such as Sub-Saharan Africa. Among these are lifestyle factors related for example to nutrition or sanitation. Other factors are related to social class, ethnicity and poverty in general. Few studies have investigated a dependence of these factors by age and season of birth which is the focus in this study. We perform a survival analysis of 9121 children born between 1998 and 2001 in a rural area of western Burkina Faso. The whole population is under demographic surveillance since 1993. All cause mortality is used as the endpoint and follow-up information until the age of five years is available. Recently developed spline regression methods are used for the analysis. Ethnic group, religion, age of mother, twin status, sex, and distance to next health center are used as covariates all of which having a clear effect on survival in standard Cox regression analysis. With penalized spline regression, a more detailed risk pattern is observed. Ethnicity is more related to death at early age, as well as age of mother. The effect of the risk factors considered also appear to be related with season of birth.

A partial likelihood approach to smooth estimation of dynamic covariate effects using penalised splines.

Survival data are often modelled by the Cox proportional hazards model, which assumes that covariate effects are constant over time. In recent years however, several new approaches have been suggested which allow covariate effects to vary with time. Non-proportional hazard functions, with covariate effects changing dynamically, can be fitted using penalised spline (P-spline) smoothing. By utilising the link between P-spline smoothing and generalised linear mixed models, the smoothing parameters steering the amount of smoothing can be selected. A hybrid routine, combining the mixed model approach with a classical Akaike criterion, is suggested. This approach is evaluated with simulations and applied to data from the West of Scotland Coronary Prevention Study.

Modeling microarray data using a threshold mixture model.

An important goal of microarray studies is the detection of genes that show significant changes in expression when two classes of biological samples are being compared. We present an ANOVA-style mixed model with parameters for array normalization, overall level of gene expression, and change of expression between the classes. For the latter we assume a mixing distribution with a probability mass concentrated at zero, representing genes with no changes, and a normal distribution representing the level of change for the other genes. We estimate the parameters by optimizing the marginal likelihood. To make this practical, Laplace approximations and a backfitting algorithm are used. The performance of the model is studied by simulation and by application to publicly available data sets.

A smooth test in proportional hazard survival models using local partial likelihood fitting.

Proportional hazard models for survival data, even though popular and numerically handy, suffer from the restrictive assumption that covariate effects are constant over survival time. A number of tests have been proposed to check this assumption. This paper contributes to this area by employing local estimates allowing to fit hazard models in which covariate effects are smoothly varying with time. A formal test is derived to check for proportional hazards against smooth hazards as alternative. The test proves to possess omnibus power in that it is powerful against arbitrary but smooth alternatives. Comparative simulations and two data examples accompany the presentation. Extensions are provided to multiple covariate settings, where the focus of interest is to decide which of the covariate effects vary with time.