Wavelet analysis is introduced as a tool for analyzing long-range dependence (LRD) in traffic data and for estimating the Hurst parameter H. The estimator is unbiased under general conditions and efficient under Gaussian assumptions. It is robust against deterministic trends and can detect and identify them. The estimator is compared with traditional methods like Whittle and is applied to Ethernet traffic data, revealing new features with implications for model selection. A study of mono versus multifractality is also performed, and stationarity with respect to H and deterministic trends is investigated. The wavelet-based estimator is efficient, computationally feasible, and robust against trends. It is shown to outperform traditional estimators in terms of bias and variance, especially in the presence of deterministic trends. The estimator is based on wavelet decomposition and uses the number of vanishing moments of the wavelet to reduce bias. It is compared with the discrete Whittle estimator, showing better performance in terms of bias and variance. The estimator is also shown to be robust against non-Gaussian data and to handle large data sets efficiently. The wavelet-based estimator is used to analyze Ethernet traffic data, revealing important features of the data and demonstrating its effectiveness in modeling LRD. The estimator is shown to be robust against deterministic trends and to provide accurate estimates of H. The analysis of Ethernet data using the wavelet-based estimator reveals important insights into the structure of the data and the behavior of LRD in traffic. The estimator is shown to be effective in detecting and identifying trends in the data and to provide accurate estimates of H. The wavelet-based estimator is compared with the discrete Whittle estimator and is shown to be more robust and accurate in the presence of deterministic trends. The estimator is also shown to be effective in handling non-Gaussian data and to provide accurate estimates of H. The analysis of Ethernet data using the wavelet-based estimator reveals important features of the data and the behavior of LRD in traffic. The estimator is shown to be effective in detecting and identifying trends in the data and to provide accurate estimates of H. The wavelet-based estimator is compared with the discrete Whittle estimator and is shown to be more robust and accurate in the presence of deterministic trends. The estimator is also shown to be effective in handling non-Gaussian data and to provide accurate estimates of H. The analysis of Ethernet data using the wavelet-based estimator reveals important features of the data and the behavior of LRD in traffic. The estimator is shown to be effective in detecting and identifying trends in the data and to provide accurate estimates of H. The wavelet-based estimator is compared with the discrete Whittle estimator and is shown to be more robust and accurate in the presence of deterministic trends. The estimator is also shown to be effective in handling non-Gaussian data and to provide accurate estimates of H.Wavelet analysis is introduced as a tool for analyzing long-range dependence (LRD) in traffic data and for estimating the Hurst parameter H. The estimator is unbiased under general conditions and efficient under Gaussian assumptions. It is robust against deterministic trends and can detect and identify them. The estimator is compared with traditional methods like Whittle and is applied to Ethernet traffic data, revealing new features with implications for model selection. A study of mono versus multifractality is also performed, and stationarity with respect to H and deterministic trends is investigated. The wavelet-based estimator is efficient, computationally feasible, and robust against trends. It is shown to outperform traditional estimators in terms of bias and variance, especially in the presence of deterministic trends. The estimator is based on wavelet decomposition and uses the number of vanishing moments of the wavelet to reduce bias. It is compared with the discrete Whittle estimator, showing better performance in terms of bias and variance. The estimator is also shown to be robust against non-Gaussian data and to handle large data sets efficiently. The wavelet-based estimator is used to analyze Ethernet traffic data, revealing important features of the data and demonstrating its effectiveness in modeling LRD. The estimator is shown to be robust against deterministic trends and to provide accurate estimates of H. The analysis of Ethernet data using the wavelet-based estimator reveals important insights into the structure of the data and the behavior of LRD in traffic. The estimator is shown to be effective in detecting and identifying trends in the data and to provide accurate estimates of H. The wavelet-based estimator is compared with the discrete Whittle estimator and is shown to be more robust and accurate in the presence of deterministic trends. The estimator is also shown to be effective in handling non-Gaussian data and to provide accurate estimates of H. The analysis of Ethernet data using the wavelet-based estimator reveals important features of the data and the behavior of LRD in traffic. The estimator is shown to be effective in detecting and identifying trends in the data and to provide accurate estimates of H. The wavelet-based estimator is compared with the discrete Whittle estimator and is shown to be more robust and accurate in the presence of deterministic trends. The estimator is also shown to be effective in handling non-Gaussian data and to provide accurate estimates of H. The analysis of Ethernet data using the wavelet-based estimator reveals important features of the data and the behavior of LRD in traffic. The estimator is shown to be effective in detecting and identifying trends in the data and to provide accurate estimates of H. The wavelet-based estimator is compared with the discrete Whittle estimator and is shown to be more robust and accurate in the presence of deterministic trends. The estimator is also shown to be effective in handling non-Gaussian data and to provide accurate estimates of H.