Causal Analysis

This practical introduction is geared towards scientists who wish to employ Bayesian networks for applied research using the BayesiaLab software platform. Through numerous examples, this book illustrates how implementing Bayesian networks involves concepts from many disciplines, including computer science, probability theory, information theory, machine learning, and statistics. Each chapter explores a real-world problem domain, exploring aspects of Bayesian networks and simultaneously introducing functions of BayesiaLab. The book can serve as a self-study guide for learners and as a reference manual for advanced practitioners.

There is still a notable underperformance among many mega projects in East Africa. One result from this is waste that’s often reflected in cost and time over runs, health and safety issues, poor quality projects and over all, less value to clients among others. Waste among many project processes but more particularly in the concept design stage is identified in this report as a key element of overall project underperformance. The aim of this research is to develop a new contextual model to address current gaps in value adding processes and activities in mega projects in East Africa. 
As a first step, a critical discussion of current literature is presented to build a basis not only of the general understanding of waste as a concept in the concept design stage but also form a foundation for a theoretical framework of waste assessment and improvement within the early design stages. The models take the form of generic IDEF0, UML and Causal Models to draw understanding to current practice in industry. The revised framework takes into account survey data in helping identify these gaps in practice. Questionnaires were developed to assess the influence of important project success factors on waste within the concept design processes. Bottom level activities were used inform the basis for higher level activities in a bottom-up approach while higher level processes in turn inform important activities and interplays between higher level processes in the resultant models.
Research highlights the importance of the concept design stage in the overall project performance. The process is seen to involve a lot of dynamic information exchanges among project teams as well as potentially critical processes involving decision making activities that can influence a project’s full life cycle. The research also finds that there is still an insufficient level of collaboration among project stakeholders and a propensity for adversarial relationships among project professional. These two alongside poor project leadership and a lack of appreciation of important contribution of all project stakeholders to the success of mega projects; such as specialist consulting/contracting teams were identified as key waste generating factors. Although many new models and frameworks are now available to help in improvement and assessment of performance of construction projects, this research has found that success in these areas still very much depends on better contextual frameworks that take into account project and area specific success factors. The revised model can be a useful tool in addressing areas of value addition in many activities in the concept design stage by crucially identifying key waste generating processes and activities.

We describe the R package causalweight for causal inference based on inverse probability weighting (IPW). The causalweight package offers a range of semiparametric methods for treatment or impact evaluation and mediation analysis, which incorporates intermediate outcomes for investigating causal mechanisms. Depending on the method, identification relies on selection on observables assumptions or on instrumental variables when selection is on unobservables, approaches that may also be applied to tackle non-random outcome attrition and sample selection. Inference is based on the bootstrap.