Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 27 - SDNS Speed Session
Type: Contributed
Date/Time: Sunday, August 8, 2021 : 1:30 PM to 3:20 PM
Sponsor: Section on Statistics in Defense and National Security
Abstract #319146
Title: Models for Analysis of Coincidences
Author(s): Thomas Reed Willemain*
Companies: Smart Software, Inc.
Keywords: coincidences; time series; Bernoulli; logistic regression; false discovery rate; binary

The simultaneous occurrences of events in two binary time series may be attributed to simple chance or else may imply a substantive link between the sources of the two series. Bernoulli models can test the null hypothesis of chance coincidence when data are i.i.d. Logistic models can account for more complex binary time series having autocorrelation, trend and seasonality. However, when investigating multiple series for possible connections, even stringent tests can uncover a huge number of apparent relationships for investigation. In these cases, attention must be paid to the false discovery rate to avoid wasting time on false target pairs.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program