Digital Library
Close Browse articles from a journal
   next >>
     Journal description
       All volumes of the corresponding journal
         All issues of the corresponding volume
           All articles of the corresponding issues
                                       Details for article 1 of 10 found articles
  A Robust Measurement of Correlation in Dependent Time Series
Title: A Robust Measurement of Correlation in Dependent Time Series
Author: Kowalski, Axel
Enck, Paul
Musial, Frauke
Appeared in: Biological rhythm research
Paging: Volume 35 (2004) nr. 4-5 pages 299-315
Year: 2004-10
Contents: A special problem in behavioral sciences are time series where the data points of one series are dependent on the just prior values of the other series. The data structure may additionally exhibit an interdependence between the variables that changes over time. Pfanzagl's T provides a robust test of trend independence between such data sets. At the same time the applicability of Pearson's r can be extended by using the statistical considerations for T. For this purpose, the time series are transformed into binary series, consisting either of the values 1 or 0. These series may show distinct trend patterns of consecutive data points with the value 1 or with the value 0. Data points belonging to the same trend pattern are regarded as cohering values for any further mathematical operation applied. Based on the trend identifcation the T-value is derived, providing information on the coherent development of trend patterns in the two series. Additionally Pearson's r together with a modified sampling theory offers a standard measure of linear association between the time series. The procedures are described and a computer program is provided, combining Pfanzagl's T and Pearson's r with a bootstrap procedure for the statistical evaluation of the correlation coefficients.
Publisher: Taylor & Francis
Source file: Elektronische Wetenschappelijke Tijdschriften

                             Details for article 1 of 10 found articles
   next >>
 Koninklijke Bibliotheek - National Library of the Netherlands