• Using Benford’s law as an epidemiological tool for COVID-19 pandemic data analysis in Greece

    Kagkaras Odysseas1, Kariofylli Aikaterini-Danai2, Karpouzi Elisavet3, Koufopoulou Eirini4, Limnaios Dimitris5, Maneta Chrysa6

    1. Varvakeion Model High School, Mouson 29, 15452, Athens, Greece (E-mail: odysseaskagaras@gmail.com).
    2. Varvakeion Model High School, Mouson 29, 15452, Athens, Greece (E-mail: danaikariofylli@gmail.com).
    3. Varvakeion Model High School, Mouson 29, 15452, Athens, Greece (E-mail: elisavetkarpouzi@gmail.com).
    4. Varvakeion Model High School, Mouson 29, 15452, Athens, Greece (E-mail: renakouf6@gmail.com).
    5. Varvakeion Model High School, Mouson 29, 15452, Athens, Greece (E-mail: dimL05@outlook.com.gr).
    6. Varvakeion Model High School, Mouson 29, 15452, Athens, Greece (E-mail: chrysamaneta12@gmail.com).

    Abstract: Have you ever imagined that nature may not be as uniform as it looks? Or that it may have a tendency toward smaller numbers? At the end of the 19th century, triggered by an observation that in logarithm tables the earlier pages (with numbers that started with 1) were much more worn than the other ones, the idea of Benford’s law was born. According to the law, in collections of numbers from empirical data, the leading digit is more likely to be small. In sets that obey Benford’s law, for instance, the number 1 appears as the leading digit about 30% of the time, while the number 9 less than 5%. Hence, this paper aims to examine the peculiarity of Benford’s law and to apply it in the context of the critical health situation we are experiencing today, the COVID-19 pandemic, to verify the validity of case & death statistics with the criterion of whether they follow this natural anomaly. It should be mentioned that the cases that are taken at time intervals of one month may deviate from the law, while overall -when the sample size is large- they follow it at a satisfactory level. On top of that, during our research, we were faced with an illusion known to psychologists as “bias of equal probability” (Flehinger, 1966); in a nutshell, it is a human tendency to think that “real” probability implies uniformity. But does it?

    Keywords: Benford’s law, COVID-19, logarithms, epidemiology, Greece.

    Pages: 51 – 58 | Full PDF Paper