Statistical learning for turboshaft helicopter accidents using logistic regression

Autoři: Rachmat Subagia aff001;  Joseph Homer Saleh aff001;  Jared S. Churchwell aff001;  Katherine S. Zhang aff001
Působiště autorů: School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, United States of America aff001
Vyšlo v časopise: PLoS ONE 15(1)
Kategorie: Research Article
doi: 10.1371/journal.pone.0227334


The objective of this work is to advance the understanding of helicopter accidents by examining and quantifying the association between helicopter-specific configurations (number of main rotor blades, number of engines, rotor diameter, and takeoff weight) and the likelihood of accidents. We leverage a dataset of 8,338 turboshaft helicopters in the U.S. civil fleet and 825 accidents from 2005 to 2015. We use the dataset to develop a logistic regression model using the method of purposeful selection, which we exploit for inferential purposes and highlight the novel insights it reveals. For example, one important question for the design and acquisition of helicopters is whether twin-engine turboshaft helicopters exhibit a smaller likelihood of accidents than their single-engine counterparts, all else being equal. The evidence-based result we derive indicates that the answer is contingent on other covariates, and that a tipping point exists in terms of the rotor diameter beyond which the likelihood of accidents of twin-engines is higher (worse) than that of their single-engine counterparts. Another important result derived here is the association between the number of main rotor blades and likelihood of accidents. We found that for single-engine turboshaft helicopters, the four-bladed ones are associated with the lowest likelihood of accidents. We also identified a clear coupling between the number of engines and the rotor diameter in terms of likelihood of accidents. In summary, we establish important relationships between the different helicopter configurations here considered and the likelihood of accident, but these are associations, not causal in nature. The causal pathway, if it exists, may be confounded or mediated by other variables not accounted for here. The results provided here lend themselves to a rich set of interpretive possibilities, and because of their significant safety implications they deserve careful attention from the rotorcraft community.

Klíčová slova:

Aerodynamics – Critical care and emergency medicine – Engines – Polynomials – Rotors – Statistical data – Twins – Aviation


1. Churchwell JS, Zhang KS, Saleh JH. Epidemiology of helicopter accidents: Trends, rates, and covariates. Reliab Eng Syst Safe. 2018;180:373–84.

2. Saleh JH, Ray AT, Zhang KS, Churchwell JS. Maintenance and inspection as risk factors in helicopter accidents: Analysis and recommendations. PLOS One. 2019;14(2):e0211424. doi: 10.1371/journal.pone.0211424 30707734

3. Herrera I, Håbrekke S, Krakenes T, Hokstad P, Forseth U. Helicopter Safety Study 3. Trondheim, Norway: SINTEF Technology and Society; 2010. Report No. A15753.

4. Kråkenes T, Evjemo TE, Håbrekke S, Hoem ÅS. Helicopter Safety Study 3b. Trondheim, Norway: SINTEF Technology and Society; 2017. Report No. 2017:00079.

5. Hokstad P, Jersin E, Sten T. A risk influence model applied to North Sea helicopter transport. Reliab Eng Syst Safe. 2001;74(3):311–22.

6. Herrera IA, Hollnagel E, Håbrekke S. Proposing safety performance indicators for helicopter offshore on the Norwegian Continental Shelf. PSAM 10-Tenth Conference on Probabilistic Safety Assessment and Management; Seattle, WA, United States. 2010.

7. Vinnem J-E. Offshore Risk Assessment, Vol 2.: Principles, Modelling and Applications of QRA Studies: Springer; 2014.

8. Atkinson B, Irving P. An analysis of accidents Involving UK civil registered helicopters during the period 1976–1993. UK Civil Aviation Authority. 1995. Report No. CAA/913 V/14.

9. EHEST. EHEST Analysis of 2000–2005 European helicopter accidents. 2010.

10. National Transportation Safety Board. Commercial Emergency Medical Service Helicopter Operations. 1988. Report No. NTSB/SS-88/01.

11. National Transportation Safety Board. Special Investigation Report on Emergency Medical Services Operations. 2006. Report No. NTSB/SIR-06/01.

12. Bledsoe BE, Smith MG. Medical helicopter accidents in the United States: a 10-year review. Journal of Trauma Acute Care Surgery. 2004;56(6):1325–9.

13. Blumen IJ. A Safety Review and Risk Assessment in Air Medical Transport: Supplement to the Air Medical Physician Handbook: Air Medical Physician Association; 2002.

14. Altman DG, Royston P. The cost of dichotomising continuous variables. BMJ. 2006;332(7549):1080. doi: 10.1136/bmj.332.7549.1080 16675816

15. Austin PC, Brunner LJ. Inflation of the type I error rate when a continuous confounding variable is categorized in logistic regression analyses. Statistics in Medicine. 2004;23(7):1159–78. doi: 10.1002/sim.1687 15057884

16. Hosmer DW, Lemeshow S, Sturdivant RX. Applied logistic regression 3rd edition: John Wiley & Sons; 2013.

17. Royston P, Altman DG. Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling. Journal of the Royal Statistical Society: Series C. 1994;43(3):429–53.

18. Hosmer DW, Lemeshow S. Applied logistic regression 2nd edition: John Wiley & Sons; 2000.

19. Stukel TA. Generalized logistic models. Journal of the American Statistical Association. 1988;83(402):426–31.

20. Fox RG. The history of helicopter safety. International helicopter safety symposium; Canada. 2005. p. 1–17.

21. Knecht W, Smith J. Effects of Training School Type and Examiner Type on General Aviation Flight Safety. 2012. Report No. DOT/FAA/AM-13/4.

Článek vyšel v časopise


2020 Číslo 1