R software package eefAnalytics
Randomized control trials (RCTs) are commonly regarded as the ‘gold standard’ for evaluating educational interventions. Robust and appropriate analytical methods are required to analyse randomised control trials in education according to the study designs to provide useful metrics for intervention effectiveness. An R software package eefAnalytics is developed by the team at Durham Research Methods Centre in Durham University with robust analytical methods for evaluating educational interventions using randomised control designs. This package offers a flexible way to obtain relevant indicators about the effectiveness of educational interventions evaluated using a simple, cluster, or multisite randomised control trials. It provides analytical tools to perform sensitivity analysis using different methods (e.g. frequentist models with bootstrapping and permutations options, Bayesian models).This package can also be used more widely beyond education trials in other disciplines.
STATA module eefAnalytics
Analogous to the eefAnalytics R package, the STATA module for the same is developed by the team at DRMC. The aim of this STATA module is to support researchers using STATA software for analysing data from evaluations of educational interventions using a randomised controlled trial design. Frequentist models with bootstrapping and permutations options and Bayesian models are provided for analysing simple randomised trials, cluster randomised trials and multisite trials.
COMPLEX-IT
COMPLEX-IT is a case-based, mixed-methods platform for applied social inquiry into complex data/systems, designed to increase non-expert access to the tools of computational social science (i.e., cluster analysis, artificial intelligence, data visualisation, data forecasting, and scenario simulation). In particular, COMPLEX-IT aids applied social inquiry though a heavy emphasis on learning about the complex data/system under study, which it does by (a) identifying and forecasting major and minor clusters/trends; (b) visualising their complex causality; and (c) simulating scenarios for potential interventions. COMPLEX-IT is accessible through the web or can be run locally and is powered by R and the Shiny web framework.
Agent-based Modelling
Agent-based modelling is a complex systems method to simulate individuals making decisions based on their own characteristics, social influences and circumstances. Many people wanting to use agent-based modelling are sociologists, public health researchers, geographers, environmental scientists or other disciplinary based scientists who may not have programming experience or access to experienced agent-based modellers. This tutorial works through building a model of protective behaviour during an influenza epidemic. It uses NetLogo, which is freely available software specialised for agent-based modelling. As well as the Netlogo language and programming environment, the tutorial is intended to teach the way that agent-based models represent the world and good programming practices.
Compendium of Modelling Techniques
The Compendium of Modelling Techniques outlines and compares 14 different modelling methods for complex, real-world problems. The methods include qualitative aggregate models such as concept maps, quantitative aggregate models such as system dynamics, and individual based methods such as agent-based modelling. Each technique includes example uses, key attributes and reference material. The compendium was first published as Integration Insights number 12, May 2010, one of the earliest resources provided on the Integration and Implementation Sciences (i2S) website.
Automating Administration of an Application Review Procedure - a practical how-to-guide
Selection processes often lead to discrimination against underrepresented groups1. Reducing discrimination makes our institutions fairer and more equitable, and diversity in teams often contributes to producing better outcomes2. Working with the CES Transformation Fund, we have created an automated application review procedure: an applicant's anonymous content is sent for review first. Submission of this review automatically prompts delivery of a separate document containing identifiable content for review. This process helps to reduce identity-bias, while also enhancing the efficiency of the administrative process. It can enhance equality, diversity and inclusion for those you fund/employ, yet enable due consideration of important identifiable information. All that is required to use the automated process is access to Microsoft Office 365. The process uses the app, Power Automate - no prior experience with this app is required to implement the procedure.
/prod01/prodbucket01/media/durham-university/departments-/school-of-government-amp-int-affairs/31117-1.jpg)