Attribute-Based Safety Risk Assessment. II: Predicting Safety Outcomes Using Generalized Linear Models

Behzad Esmaeili, Matthew R. Hallowell, Balaji Rajagopalan

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

One of the recent advancements in preconstruction safety management is the identification and quantification of risks associated with fundamental attributes of construction work environments that cause injuries. The goal of this paper is to test the validity of using these fundamental risk attributes to predict safety outcomes. The modeling approach required two steps, as follows: (1) a principal component analysis was performed on the safety attributes to reduce dimension of the data and remove collinearity among attributes (the principle component analysis provided insights into the relative importance of the various attributes and provided an orthogonal decomposition of the data), and (2) the leading principal components (which are orthogonal by definition) were used as potential predictors in a generalized linear model with a logit link function to model the probability of different accident categories. The predictive power was then assessed using a rank probability skill score, which quantified the probabilistic skill of the forecasts over the categories. The analysis shows strong predictive skill, making the models attractive for safety managers to use to skilfully forecast the probability of a safety incident given identifiable characteristics of planned work. Researchers in the technology domain may find these models useful in predicting safety outcomes during design, work packaging, and scheduling.

Original languageEnglish (US)
Article number04015022
JournalJournal of Construction Engineering and Management
Volume141
Issue number8
DOIs
StatePublished - Aug 1 2015

Fingerprint

Risk assessment
Principal component analysis
Safety
Generalized linear model
Packaging
Accidents
Managers
Scheduling
Decomposition

Keywords

  • Generalized linear models (GLMs)
  • Labor and personnel issues
  • Predictive models
  • Principal component analysis (PCA)
  • Safety risk management

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Industrial relations
  • Strategy and Management

Cite this

Attribute-Based Safety Risk Assessment. II : Predicting Safety Outcomes Using Generalized Linear Models. / Esmaeili, Behzad; Hallowell, Matthew R.; Rajagopalan, Balaji.

In: Journal of Construction Engineering and Management, Vol. 141, No. 8, 04015022, 01.08.2015.

Research output: Contribution to journalArticle

@article{4a73cf2e59ed449199dbeeaccdc0cc90,
title = "Attribute-Based Safety Risk Assessment. II: Predicting Safety Outcomes Using Generalized Linear Models",
abstract = "One of the recent advancements in preconstruction safety management is the identification and quantification of risks associated with fundamental attributes of construction work environments that cause injuries. The goal of this paper is to test the validity of using these fundamental risk attributes to predict safety outcomes. The modeling approach required two steps, as follows: (1) a principal component analysis was performed on the safety attributes to reduce dimension of the data and remove collinearity among attributes (the principle component analysis provided insights into the relative importance of the various attributes and provided an orthogonal decomposition of the data), and (2) the leading principal components (which are orthogonal by definition) were used as potential predictors in a generalized linear model with a logit link function to model the probability of different accident categories. The predictive power was then assessed using a rank probability skill score, which quantified the probabilistic skill of the forecasts over the categories. The analysis shows strong predictive skill, making the models attractive for safety managers to use to skilfully forecast the probability of a safety incident given identifiable characteristics of planned work. Researchers in the technology domain may find these models useful in predicting safety outcomes during design, work packaging, and scheduling.",
keywords = "Generalized linear models (GLMs), Labor and personnel issues, Predictive models, Principal component analysis (PCA), Safety risk management",
author = "Behzad Esmaeili and Hallowell, {Matthew R.} and Balaji Rajagopalan",
year = "2015",
month = "8",
day = "1",
doi = "10.1061/(ASCE)CO.1943-7862.0000981",
language = "English (US)",
volume = "141",
journal = "Journal of Construction Engineering and Management - ASCE",
issn = "0733-9364",
publisher = "American Society of Civil Engineers (ASCE)",
number = "8",

}

TY - JOUR

T1 - Attribute-Based Safety Risk Assessment. II

T2 - Predicting Safety Outcomes Using Generalized Linear Models

AU - Esmaeili, Behzad

AU - Hallowell, Matthew R.

AU - Rajagopalan, Balaji

PY - 2015/8/1

Y1 - 2015/8/1

N2 - One of the recent advancements in preconstruction safety management is the identification and quantification of risks associated with fundamental attributes of construction work environments that cause injuries. The goal of this paper is to test the validity of using these fundamental risk attributes to predict safety outcomes. The modeling approach required two steps, as follows: (1) a principal component analysis was performed on the safety attributes to reduce dimension of the data and remove collinearity among attributes (the principle component analysis provided insights into the relative importance of the various attributes and provided an orthogonal decomposition of the data), and (2) the leading principal components (which are orthogonal by definition) were used as potential predictors in a generalized linear model with a logit link function to model the probability of different accident categories. The predictive power was then assessed using a rank probability skill score, which quantified the probabilistic skill of the forecasts over the categories. The analysis shows strong predictive skill, making the models attractive for safety managers to use to skilfully forecast the probability of a safety incident given identifiable characteristics of planned work. Researchers in the technology domain may find these models useful in predicting safety outcomes during design, work packaging, and scheduling.

AB - One of the recent advancements in preconstruction safety management is the identification and quantification of risks associated with fundamental attributes of construction work environments that cause injuries. The goal of this paper is to test the validity of using these fundamental risk attributes to predict safety outcomes. The modeling approach required two steps, as follows: (1) a principal component analysis was performed on the safety attributes to reduce dimension of the data and remove collinearity among attributes (the principle component analysis provided insights into the relative importance of the various attributes and provided an orthogonal decomposition of the data), and (2) the leading principal components (which are orthogonal by definition) were used as potential predictors in a generalized linear model with a logit link function to model the probability of different accident categories. The predictive power was then assessed using a rank probability skill score, which quantified the probabilistic skill of the forecasts over the categories. The analysis shows strong predictive skill, making the models attractive for safety managers to use to skilfully forecast the probability of a safety incident given identifiable characteristics of planned work. Researchers in the technology domain may find these models useful in predicting safety outcomes during design, work packaging, and scheduling.

KW - Generalized linear models (GLMs)

KW - Labor and personnel issues

KW - Predictive models

KW - Principal component analysis (PCA)

KW - Safety risk management

UR - http://www.scopus.com/inward/record.url?scp=84951785883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951785883&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)CO.1943-7862.0000981

DO - 10.1061/(ASCE)CO.1943-7862.0000981

M3 - Article

AN - SCOPUS:84951785883

VL - 141

JO - Journal of Construction Engineering and Management - ASCE

JF - Journal of Construction Engineering and Management - ASCE

SN - 0733-9364

IS - 8

M1 - 04015022

ER -