Change Point Analysis in Average Ozone Layer Temperature Using Exponential Lomax Distribution

Authors: Amjad Abdullah, Amjad Yahya, Bushra Aljohani, Amani S. Alghamdi

Abstract:

Change point detection is an important part of data analysis. The presence of a change point refers to a significant change in the behavior of a time series. In this article, we examine the detection of multiple change points of parameters of the exponential Lomax distribution, which is broad and flexible compared with other distributions while fitting data. We used the Schwarz information criterion and binary segmentation to detect multiple change points in publicly available data on the average temperature in the ozone layer. The change points were successfully located.

Keywords: Binary segmentation, change point, exponential Lomax distribution, information criterion.

References:

[1] Montanez, G. D.; Amizadeh, S.; Laptev, N. Inertial hidden markov models: Modeling change in multivariate time series. AAAI-15. 2015, 10, 1819–1825.
[2] Chen, Jie; Arjun K. Gupta. Parametric statistical change point analysis: with applications to genetics, medicine, and finance, 2nd ed.; Birkh¨auser: Basel, Switzerland, 2011; pp. XIII, 273.
[3] Zhang, N. R.; Siegmund, D. O. A modified bayes information criterion with applications to the analysis of comparative genomic hybridization data. Biometrics. 2007, 63 22–32.
[4] Chernof f, H.; Zacks, S. Estimating the current mean of a normal distribution which is subjected to changes in time. Ann. Math. Stat. 1964, 35, 999–1018.
[5] Worsley, K. J. On the likelihood ratio test for a shift in location of normal populations. JASA. 1979, 74, 365–367.
[6] Kim, T.-H.; White, H. On more robust estimation of skewness and kurtosis. Finance Res. Lett. 2004, 1, 56–73.
[7] Ning, W.; Gupta, A. K. Change point analysis for generalized lambda distribution. Commun. Stat. Simul. Comput. 2009, 38, 1789–1802.
[8] Matteson, D. S.; James, N. A. A nonparametric approach for multiple change point analysis of multivariate data. JASA. 2014, 109, 334–345.
[9] Vostrikova, L. Detecting “disorder” in multidimensional random processes. Soviet Math. Dokl. 1981, 24, 55–59.
[10] Lomax, K. Business failures: Another example of the analysis of failure data. JASA. 1954, 49, 847–852.
[11] Devi, B.; Kumar, P.; Kour, K. Entropy of lomax probability distribution and its order statistic. IJSS. 2017, 12, 175–181.
[12] Al-Awadhi, S. A.; Ghitany, M. E. Statistical properties of Poisson-Lomax distribution and its application to repeated accidents data. J. Appl. Stat. Sci. 2001, 10, 365–372.
[13] Zubair, M.; Cordeiro, G. M.; Tahir, M. H.; Mahmood, M.; Mansoor, M. A study of logistic-lomax distribution and its applications. J. Prob. Stat. Sci. 2017, 15, 29–46.
[14] El-Bassiouny, A. H.; Abdo, N. F.; Shahen, H. S. Exponential lomax distribution Int. J. Comput. Appl. 2015, 121, 24–29.
[15] Ozone Level Detection Data Set. Available online:https://archive.ics.uci.edu/ml/datasets/Ozone+Level+Detection (accessed on 30 July 2021).
[16] bbmle: Tools for general maximum likelihood estimation. Available online:https://rdrr.io/rforge/bbmle/ (accessed on 31 July 2021).
[17] Hsu, D. A. Detecting shifts of parameter in gamma sequences with applications to stock price and air traffic flow analysis. JASA. 1979, 74, 31–40.
[18] Ngunkeng, G.; Ning, W. Information approach for the change-point detection in the skew normal distribution and its applications Seq. Anal. 2014, 33, 475–490.
[19] Basic Ozone Layer Science. https://www.epa.gov/ozone-layer-protection/basic-ozone-layer-science (accessed on 15 August 2021).