MATHEMATICAL MODELS IN SCIENCE: BRIDGING DIFFERENCES AND DISCOVERING COMMONALITIES

Various scientific disciplines, including biometrics, chemometrics, psychometrics, and econometrics, share a deep connection with statistics but often employ specialized applications. Effective communication across these interdisciplinary boundaries necessitates a common language, and mathematics serves as a universal bridge among the natural sciences. This article centers on the language of

Authors: Erik Magnus Johansen
Pages: 1-14
A COMPARATIVE ASSESSMENT OF TELBS ROBUST REGRESSION

Linear regression is a widely used statistical model for assessing the impact of explanatory variables on a response variable, with applications spanning across fields such as social sciences, environmental studies, and biomedical research. Conventionally, ordinary least squares (OLS) estimation has been the go-to method for regression analysis. However, the presence of outliers can

Authors: Sarah Elizabeth Thompson , David Allen Mitchell
Pages: 15-36
ANALYZING SEISMIC SIGNATURES: SDFA FOR DISCRIMINATING EXPLOSIONS AND EARTHQUAKES

The Smoothed Detrended Fluctuation Analysis (SDFA) method, introduced by Linhares in 2016, offers a valuable tool for characterizing long-range correlations in time series data. Building upon the foundations of Detrended Fluctuation Analysis (DFA) and the wavelet shrinkage procedure, SDFA computes statistical fluctuations measures, denoted as F(l), using varying window lengths (l). By

Authors: Carolina Silva
Pages: 37-43
NAVIGATING P-VALUES AND NULL HYPOTHESIS TESTS: INSIGHTS AND RECOMMENDATIONS

The American Statistical Association (ASA) has addressed the long-standing concerns surrounding conventional P-value hypothesis testing by formulating a set of six principles, outlined in a 2016 publication by Wasserstein and Lazar. These principles aim to clarify the proper definitions and applications of P-values in hypothesis testing, offering significant benefits to the scientific

Authors: Sarah Elizabeth Reynolds , Michael Jonathan Nguyen
Pages: 44-51
ADVANCEMENTS IN CONFIDENCE INTERVALS: A BETTER SOLUTION

Statistical inference often involves the construction of confidence intervals for binomial parameters, particularly the proportion (p). The most widely used approach is the Wald interval, which relies on sample proportion (p̂), sample size (n), and the quantile of the standard normal distribution (zα) to determine the interval. While seemingly straightforward, this method has limitations,

Authors: Rishi Kumar Subedi , James Alexander Issos
Pages: 54-56