Finite-size effects on long-range correlations: implications for
analyzing DNA sequences
C-K. Peng, S.V. Buldyrev, A.L. Goldberger, S. Havlin, M. Simon, and
H.E. Stanley,
Jan Mrazek and Jaroslav Kypr
Physical Review E 47(5), 3730--3733 (1993).
Abstract
We analyze the fluctuations in the correlation exponents obtained
for noncoding DNA sequences. We find prominent sample-to-sample
variations as well as variations within a single sample in the
scaling exponent. To determine if these fluctuations may result from
finite system size, we generate correlated random sequences of
comparable length and study the fluctuations in this control
system. We find that the DNA exponent fluctuations are consistent
with those obtained from the control sequences having long-range
power-law correlations. Finally, we compare our exponents for
the DNA sequences with the exponents obtained from power-spectrum
analysis and correlation-function techniques, and demonstrate that the
original "DNA-walk" method is intrinsically more accurate
due to reduced noise.
