Ashdown, Minnie;
Petrou, Giorgos;
(2024)
Development of a Directed Acyclic Graph through expert elicitation for Causal Inference in Built Environment Research.
In:
Proceedings of Building Simulation 2023: 18th Conference of IBPSA.
(pp. pp. 1183-1190).
IBPSA: Shanghai, China.
Preview |
Text
Ashdown_bs2023_1588.pdf Download (392kB) | Preview |
Abstract
System complexity within buildings research is high. Data are increasingly high dimensional with multiple physical and socio-technical processes driving their generation. Popular statistical methods of data analysis lack a structured procedure for incorporating intuition, limiting their potential for effect attribution in the study of buildings. This can be addressed through the use of a Directed Acyclic Graph (DAG); a graphical representation of expert knowledge and assumptions, through which interventions can be modelled, and causal assumptions are made explicit. This paper introduces the process of DAG development through expert elicitation, offering guidance to built environment researchers interested in causal modelling.
| Type: | Proceedings paper |
|---|---|
| Title: | Development of a Directed Acyclic Graph through expert elicitation for Causal Inference in Built Environment Research |
| Event: | 18th Conference of IBPSA |
| Location: | Shanghai, China |
| Dates: | 4th-6th September 2023 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.26868/25222708.2023.1588 |
| Publisher version: | https://doi.org/10.26868/25222708.2023.1588 |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Causal Inference, Expert Elicitation, Directed Acyclic Graph, Built Environment |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10181588 |
Archive Staff Only
 |
View Item |
