Bayesian inference for multistage and other incomplete designs

Following Maris, Bechger and San-Martin (2015), we develop a Markov chain - Monte Carlo method for Bayesian inference tailored to handle data collected in multistage and other incomplete designs. We illustrate its operating characteristics with simulated data, and provide a real application. To appear as: Koops, J. and Bechger, T. and Maris, G. (2021); Bayesian inference for multistage and other incomplete designs. In Research for Practical Issues and Solutions in Computerized Multistage Testing. Routledge, London.

The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures

Background We consider the design of stepped wedge trials with continuous recruitment and continuous outcome measures. Suppose we recruit from a fixed number of clusters where eligible participants present continuously, and suppose we have fine control over when each cluster crosses to the intervention. Suppose also that we want to minimise the number of participants, leading us to consider “incomplete” designs (i.e. without full recruitment). How can we schedule recruitment and cross-over at different clusters to recruit efficiently while achieving good precision? Methods The large number of possible designs can make exhaustive searches impractical. Instead we consider an algorithm using iterative improvements to hunt for an efficient design. At each iteration (starting from a complete design) a single participant – the one with the smallest impact on precision – is removed, and small changes preserving total sample size are made until no further improvement in precision can be found. Results Striking patterns emerge. Solutions typically focus recruitment and cross-over on the leading diagonal of the cluster-by-time diagram, but in some scenarios clusters form distinct phases resembling before-and-after designs. Conclusions There is much to be learned about optimal design for incomplete stepped wedge trials. Algorithmic searches could offer a practical approach to trial design in complex settings generally.

IMPROVING CONSTRUCTION PROJECT PERFORMANCE IN DEVELOPING COUNTRIES: CONTRACTOR APPROACH

Achieving project success remains the aim of every project sponsor. The sponsor engages different professionals in the built environment to this end. However, unforeseen factors modify agreed terms, causing delay and leading to loss of time and money. Delay causes an overrun of cost and time having a heavy financial burden on the client and other stakeholders involved in the project. Most times, the contractor is always the focus when this happens. At many other times, other stakeholders, who failed in their obligations, only surface after a study of the contract conditions is carried out. Thus, this study examines project performance in the construction industry in Nigeria, but from a contractor’s perspective. The study adopts a survey research design. A total number of 75 questionnaires were administered to contractors, who were members of the Federation of Construction Industry and other private sector organizations, but 37 were successfully retrieved and analyzed. The result shows that to improve construction project performance in developing countries, the following issues need to be tackled: design and installation issues, payment issues and construction difficulties arising from incomplete designs by consultants. The study recommends, among other solutions, the incorporation of contractors from the project planning phase and adoption of BIM, which is presently not prevalent in the industry.

An Existence Theory for Incomplete Designs

An incomplete pairwise balanced design is equivalent to a pairwise balanced design with a distinguished block, viewed as a ‘hole’. If there are v points, a hole of size w, and all (other) block sizes equal k, this is denoted IPBD((v;w), k). In addition to congruence restrictions on v and w, there is also a necessary inequality: v > (k − 1)w. This article establishes two main existence results for IPBD((v;w), k): one in which w is fixed and v is large, and the other in the case v > (k −1+∊)w when w is large (depending on ∊). Several possible generalizations of the problemare also discussed.

Some Holey Designs and Incomplete Designs for the Join Graph of and with a Pendent Edge

A-design of is a pair , where is the vertex set of and is a collection of subgraphs of , such that each block is isomorphic to and any two distinct vertices in are joined in exact (at most, at least) blocks of . In this paper, we will discuss some holey designs and incomplete designs for the join graph of and with a pendent edge for .