Tag: statistics
A parametric framework for multidimensional linear regression
While Ordinary Least Squares regression establishes fundamental concepts in data analysis, it requires the independent variable to be error-free and the error term to be constant. Dr Stanley Luck, statistics consultant and founding member of Vector Analytics LLC in the US, has developed an innovative parametric framework for multidimensional linear regression. This provides a more general framework for establishing measurement […]
Read More… from A parametric framework for multidimensional linear regression
Structured expert judgment using the Classical Method
When complex decisions must be made while data is unavailable, structured expert judgment can be used to combine uncertainty distributions resulting from experts’ assessments. Roger Cooke, the Chauncey Starr Senior Fellow at Resources for the Future, and Emeritus Professor at Delft University of Technology, created the well-known Classical Model to quantify uncertainty using expert opinion. Together with Dr Tina Nane, […]
Read More… from Structured expert judgment using the Classical Method
Nonoverlap proportion and the point-biserial association problem
Dr Stanley Luck, a statistics consultant and founding member of Vector Analytics LLC, has developed a novel algorithm for cloud computing technology. Dr Luck demonstrates the use of his improved CART association algorithm in a high-dimensional search problem of nursing home performance, based on the publicly accessible Nursing Home Compare (NHC) database. The results highlight the importance of constructing a […]
Read More… from Nonoverlap proportion and the point-biserial association problem
Statistics in the era of COVID-19: Measuring lockdowns with doubling time
The key to understanding SARS-CoV-2 (COVID-19) transmission is understanding the exponential growth of viral transmissions. The problem is that the concept of exponential growth is challenging for many to understand and interpret, including policymakers who need to make quick and informed decisions. Dr Biljana Stangeland, Executive Director/Chief Scientific Officer at Alv B, Norway, has been using doubling time – the […]
Read More… from Statistics in the era of COVID-19: Measuring lockdowns with doubling time
To Test, Or Not To Test – The COVID-19 Question
Dr Cristina Isabel Ibarra-Armenta is a lecturer at the Autonomous University of Sinaloa and UNICAF University. Dr Moisés Alejandro Alarcon-Osuna is a lecturer at the University of Guadalajara, and a member of the Mexican System of National Researchers from CONACYT (National Council for Science and Technology). Their research focuses on econometrics, regional analysis, and policy and technology change. In a […]
Read More… from To Test, Or Not To Test – The COVID-19 Question
ILLMO: A new platform for interactive statistics
Jean-Bernard Martens, a Full Professor on Visual Interaction with the Department of Industrial Design of the Eindhoven University of Technology, Netherlands, has developed ILLMO (Interactive Log Likelihood MOdeling), a statistical modelling tool that provides an interactive environment offering an intuitive and interactive approach to statistics. Scientists and researchers, including those who are not specialists in statistics, can access modern statistical […]
Read More… from ILLMO: A new platform for interactive statistics
Regression models using parametric pseudo-observations
The statistical analysis of survival data is the focus of research being carried out by Martin Nygård Johansen, a biostatistician at Aalborg University Hospital, Denmark, and his colleagues. Some patients’ actual survival times are not observed during a clinical study and are said to be censored. This research offers a new way to transform such time-to-event data into a dataset without censoring. […]
Read More… from Regression models using parametric pseudo-observations
Consciously calculating unconscious bias: The role of dichotomous valuation
Like with any choice, when faced with data selection, people are influenced by their own biases. A new research paper by econometric expert Dr Xingwei Hu of the International Monetary Fund evaluates how people subconsciously view different variables and the way this influences their decision-making. By assessing decisions through dichotomous valuation, Dr Hu is able to show the extent to […]
Read More… from Consciously calculating unconscious bias: The role of dichotomous valuation
#SocialScience: Mining Twitter for Social and Behavioural Research
A disaster strikes, somewhere in the world. Within minutes there are millions rushing to their screens, letting out their thoughts and feelings. This makes Twitter, along with other social platforms, a rich and timely resource for social and behavioural research. Surprisingly, however, it is a lot less utilised in the social sciences compared with other fields. Tweeters don’t reflect the […]
Read More… from #SocialScience: Mining Twitter for Social and Behavioural Research
An integrated toolkit for high-dimensional complex and time series data analysis
Big data can be too large and complex for traditional methods and conventional software packages to deal with. Dr Fang Han, Assistant Professor in Statistics at the University of Washington, Seattle, is meeting this challenge head on. He is creating an integrated statistical toolkit comprising robust statistical procedures, including distribution-free inference and rank-based methods, which can be applied to high-dimensional […]
Read More… from An integrated toolkit for high-dimensional complex and time series data analysis