Loading...
Please wait, while we are loading the content...
Longa dependência em sequências de DNA : análise de flutuações destendenciadas, teorias das distribuições estáveis e de wavelets
| Content Provider | Semantic Scholar |
|---|---|
| Author | Linhares, Raquel Romes |
| Copyright Year | 2011 |
| Abstract | The method of detrended fluctuation analysis (DFA), proposed by Peng et al. (1994), is useful in revealing the extent of long-range dependence in time series. Since there is not a specific rule for the choice of the numbers of regressors in DFA method, we present here an asymptotic optimal choice. For a fractional Gaussian noise, we prove the exact and the asymptotic Gaussian distributions for the ĤDFA estimator. The most important parameter to estimate in a heavy-tailed data is the tail rate of decay α which determines the probability of occurrence of extreme values of the underlying distribution. Here we propose a novel estimator for α based on the empirical characteristic function and on the principal of wavelet shrinkage. Here we are interested in analyzing the long-range dependence in several DNA sequences, under the heavy-tail regime switching mechanism, proposed by Liu (2000). In this mechanism, if the duration of the regimes of a given time series has a heavy tail distribution with index parameter α ∈ (1, 2), then there is long-range dependence in this time series, and any functional transformation of the original time series preserving the property of finite variance, also preserves the property of long-range dependence. We also study the length distribution of coding and noncoding regions in DNA sequences. We conclude that all techniques presented in this paper to analyze longrange dependence in time series, involving concepts of detrended fluctuation analysis, heavy tail distributions and wavelet shrinkage, show the existence of long-range dependence in all DNA sequences studied here. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://www.lume.ufrgs.br/bitstream/handle/10183/86626/000823194.pdf?isAllowed=y&sequence=1 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |