Application of circular statistics to life science data

Year 2019, Volume: 6 Issue: 3, 63 - 72, 30.03.2019

Yıldırım Demir , Ömer Cevdet Bilgin

https://doi.org/10.17546/msd.507582

Abstract

Objective: The aim of the study was to explain circular statistics and hypothesis tests with life science data. The accuracy of the statistical method used in scientific research is related to the data structure and scale type. Therefore, scale types and data structures should be well defined. It is possible to frequently come across circular data in many different scientific fields such as medicine, biology and physics. These data are usually obtained by compass or clock. Compass; the flight direction of any animal that is released, the direction of the wind or the direction of current in the ocean, clock; the birth time of infants, the time of crisis, circadian rhythms or biological rhythms can be shown as examples. Apart from the clock, such data may also be obtained by a scale that expresses a time such as day, month and year. Material and Methods: The data related to 179 normal deliveries that took place in Yüzüncü Yıl University Medical Faculty Hospital in 2008 were used. Circular data analysis was performed using the NCSS2007 statistical package program. Results: The times of birth of infants show a uniform distribution. No significant difference at a significance level of 5% was found between the times of birth according to gender. Conclusion: It has been stated that circular data cannot be analyzed by the analysis methods developed for linear data due to several reasons. If circular data are analyzed by linear statistical methods, inaccurate or nonsense results usually emerge. Therefore, it was emphasized that appropriate statistical methods should be used.

Keywords

Circular data analysis, circular statistics, statistics, Von Mises

References

• 1. Lai MK.. Some Results on the Statistical Analysis of Directional Data. Master thesis, University of Hong Kong, Hong Kong Pokfulam, 1994.
• 2. Mardia KV, Jupp PE. Directional Statistics. John Willey and Sons. Inc., Chichester. 2000.
• 3. Jammalamadaka SR, SenGupta A. Topics in Circular Statistics. London: World Scientific; 2001. p.322.
• 4. Mahan RP. Circular Statistical Methods: Applications in Spatial and Temporal Performance Analysis. DTIC-ADA240751, Virginia, 53s. 1991.
• 5. Hintze JL. 2007. Circular Data Analysis. ss 927-955. Hintze, J.L. NCSS Help System, Published by NCSS, Utah 2823s. 2007.
• 6. Hussin AG, Jalaluddin JF, Mohamed İ. Analysis of Malaysian Wind Direction Data Using AXIS. Journal of Applied Science Research, 2006, 2(11): 1019-1021.
• 7. Ser G. Directional Data Analysis and An Application. Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi; Yıl: 2014 Cilt: 24 Sayı: 2; 121-126. 2014.
• 8. Berens P. CircSat: A MATLAB Toolbox for Circular Statistics. Journal of Statistical Software, 2009, 31: 1-21..
• 9. Fisher NI. Statistical Analysis of Circular Data. Cambridge University Press, New York, 277s. 1993.
• 10. Mardia KV. Statistics of Directional Data. Academic Press. Inc., London, 357s. 1972.
• 11. Brunsdon C, Corcoran J. Using circular statistics to analyse time patterns in crime incidence. Computers, Environment and Urban Systems, 2006, 30: 300-319..
• 12. Gaile GL, Burt JE. Directional Statistics. Concepts and Techniques in Modern Geography, London, 39s. 1980.
• 13. Peker KÖ, Bacanlı S. Descriptive Statistical Methods Applied to Circular Data and A Meteorological Application. Anadolu University Journal of Science and Technology, 2004, 5: 115-122.
• 14. Zar JH. Biostatistical Analysis. Prentice Hall, New Jersey, 944s. 2010.
• 15. Wheeler S, Watson GS. A distribution-free two-sample test on a circle. Biometrika, 1964,.51: 256-257.