Virtual useR! 2024

Structural equation modeling (SEM) is often used to test theories, verify model measurement properties, and obtain unbiased estimates, a widespread modeling approach for composite hypotheses. However, power analysis is seldom considered in SEM studies to ensure the required sample size needed to achieve adequate power for detecting the hypothesized effect. This is due partly to the lack of a comprehensive SEM power analysis software package. The session introduces the intelligible semPower package that provides both global and local power analysis for establishing the power of a model and the specific hypothesis respectively. Three models will be illustrated. First, by varying the factor loadings of a confirmatory factor analysis model to determine power and sample size. Second, varying two loadings concurrently of a mediation model to determine the required sample size, and varying the covariance of a latent growth model to test for a local power analysis. The R syntax is illustrated to show the usefulness of using the package semPower, and graphing the model via the package semPlot. Users will find the syntax simple and can easily carry out power analysis for their studies.

Hybrid model is the most promising forecasting method by combining decomposition and deep learning techniques to improve the accuracy of time series forecasting. Each decomposition technique decomposes a time series into a set of intrinsic mode functions (IMFs), and the obtained IMFs are modelled and forecasted separately using the deep learning models. Finally, the forecasts of all IMFs are combined to provide an ensemble output for the time series. The prediction ability of the developed models are calculated in terms of evaluation criteria like root mean squared error,mean absolute percentage error and, mean absolute error.

Antimicrobial resistance (AMR) has become a major public health challenge in the 21st century, posing a global health crisis that jeopardizes modern medicine. The traditional time-series analysis methods such as the Auto-regressive moving average model has been used to analyze and forecast AMR rates. However, these methods are unsuitable when analyzing rates or proportions that feature zero or one. This study proposes a new time-series model called DeβARMA (Degenerate Beta Auto-regressive moving average) that fits data in the interval [0, 1) or (0, 1]. This model is designed to predict the rate of AMR and plan accordingly. Healthcare providers need to be alerted in real-time to the AMR rate patterns in their respective settings so that they can better anticipate changes in resistance rates over time and develop more effective anti-microbial management policies. Shiny is an exciting R programming tool for creating various applications such as exploratory data analysis, statistical inference, and regression analysis. This article highlights DeβARMA, a specialized tool for modeling time-series data with zeroes or ones, adeptly handling lag effects and regressor variables.

In this presentation we show how to model data from the closed unit interval [0, 1] using extended-support beta regression and heteroscedastic two-limit tobit models. In contrast to zero- and/or one-inflated beta regression, both approaches only require estimation of a single latent process that captures both the distribution of the inner observations and the point masses for observations on the boundaries at 0 and/or 1. The heteroscedastic two-limit tobit model does so by fitting a Gaussian distribution censored at 0 and 1 which is conveniently available in the R package "crch". Extended-support beta regression has recently been proposed and implemented in the development version of the "betareg" package. It contains both classic beta regression and heteroscedastic two-limit tobit as special cases, shifting between the two with just one additional parameter. Both approaches are illustrated by modeling reading accuracy scores of children and investments in an economic loss aversion experiment, respectively, discussing the models' relative (dis)advantages.

This session introduces participants to the Hodrick-Prescott filter, a data series smoothing technique frequently used in economics and finance, briefly explains the underlying mathematics and presents the easy-to-use hpfilter R package, which calculates both the one- and two-sided implementations of the filter. The HP filter is a mathematical tool used to smooth out short-term fluctuations in data and reveal underlying long-term trends. Popularized in the 1990s by economists Robert Hodrick and Edward Prescott, it has become a staple in fields like macroeconomics, real business cycle theory and finance. Participants will get a hands-on tour of the package and learn to apply the HP filter to a concrete use case in finance. They will learn how to compile the trend and cycle components from a financial time series, plot the results and succinctly interpret the findings.

Community detection in graphs has numerous applications from social networks to biology. However, the immense size of modern graphs makes it challenging to accurately detect communities. We set out to benchmark a variety of popular methods available in R to measure their accuracy and time complexity on synthetic and real datasets. Unsurprisingly, we found that less scalable algorithms tend to outperform more computationally efficient ones. To address this issue, we introduce two new variants of the Fast Label Propagation algorithm for clustering extremely large networks, both available in the SynExtend package for R. Our implementations offer accuracy comparable to less scalable approaches while providing linear-time computational scalability. Furthermore, we made it possible to apply our community detection algorithms outside of main memory, which permits community detection on graphs with billions of nodes using less than a gigabyte of RAM. These advances will help democratize scalable analyses by removing the need for expensive supercomputer resources. Together, this work both improves graph community detection and makes these analyses more accessible to researchers.