Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Loss Prevention Systems Effectiveness and Incidents Forecasting Using Statistical Tools

alomair, abdullah (2015) Loss Prevention Systems Effectiveness and Incidents Forecasting Using Statistical Tools. Master's Thesis, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Primary Text

Download (642kB)

Abstract

The objective of safety engineering interventions is to prevent injuries and to lower the direct costs (emergency, medical treatment and rehabilitation) and indirect costs (administrative, loss reputation) associated with them. The goal of this study is to find a mathematical relationship between injury prevention activities and occupational incidents. The study used historic data to optimize resources (i.e. man-hour) and allocate them to the appropriate interventions. The study used data from a Canadian power company collected between 2002 and 2004. Total intervention activity was used to forecast incidents but this yielded an unreliable model. Four main safety intervention categories were determined to study the effect of injury prevention activities on the occurrence of injuries and were used in establishing the model: Factor A -- safety awareness and motivational activities; Factor B -- skill development and training activities; Factor C -- new tools and equipment design methods and activities; and, Factor D -- equipment related activities these. Regression analysis was used to determine a relationship between the intervention factors and incident occurrence. This study used several different approaches for statistical analyses from the previous researches by investigating the best distribution fitting for incidents. Furthermore, this study checks the correlation between intervention activities themselves and the proper transformation based on the behavior of the incidents. A linear model using all factors as regressors yielded an insignificant result with a p-value of 0.9. A method using all possible regressor combinations was applied, but all the computed models yielded an insignificant result. Linear models based on a moving range regression of data points and also using natural logarithm transformation were formulated, but again, all of them yielded an insignificant model. After thorough analysis, the study concluded that a relationship between intervention factors and incident occurrence does not seem to exist.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
alomair, abdullahomairedu@gmail.com
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairHAIGHT, JOELJHAIGHT@pitt.eduJHAIGHT
Committee MemberVidic, Natasa S.nav9@pitt.eduNAV9
Committee MemberRajgopal, Jayantrajgopal@pitt.eduRAJGOPAL
Date: 11 September 2015
Date Type: Publication
Defense Date: 22 June 2015
Approval Date: 11 September 2015
Submission Date: 9 July 2015
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 51
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Industrial Engineering
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: safety incidents forecasting injury Poisson Distribution
Date Deposited: 11 Sep 2015 13:43
Last Modified: 15 Nov 2016 14:29
URI: http://d-scholarship.pitt.edu/id/eprint/25599

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item