Error estimation and reduction with cross correlations
arXiv:1002.4517 · doi:10.1103/PhysRevE.81.066701
Abstract
Besides the well-known effect of autocorrelations in time series of Monte Carlo simulation data resulting from the underlying Markov process, using the same data pool for computing various estimates entails additional cross correlations. This effect, if not properly taken into account, leads to systematically wrong error estimates for combined quantities. Using a straightforward recipe of data analysis employing the jackknife or similar resampling techniques, such problems can be avoided. In addition, a covariance analysis allows for the formulation of optimal estimators with often significantly reduced variance as compared to more conventional averages.
arXiv comment16 pages, RevTEX4, 4 figures, 6 tables, published version
References in corpus (16)
- An efficient, multiple range random walk algorithm to calculate the density of states
- Critical Phenomena and Renormalization-Group Theory
- Multicanonical Ensemble: A New Approach to Simulate First-order Phase Transitions
- Quantum phase transitions
- Finite size effects on measures of critical exponents in d=3 O(N) models
- Multicanonical Chain Growth Algorithm
- A Monte Carlo study of leading order scaling corrections of phi^4 theory on a three dimensional lattice
- New Universality Class in three dimensions: the Antiferromagnetic model
- The Cluster Processor: New Results
- Exact Finite-Size Scaling and Corrections to Scaling in the Ising Model with Brascamp-Kunz Boundary Conditions
- Optimal Energy Estimation in Path-Integral Monte Carlo Simulations
- Cross-correlations in scaling analyses of phase transitions
- Zero-temperature phase of the XY spin glass in two dimensions: Genetic embedded matching heuristic
- Mean-value identities as an opportunity for Monte Carlo error reduction
- Genetic embedded matching approach to ground states in continuous-spin systems
- Monte Carlo study of the scaling of universal correlation lengths in three-dimensional O(n) spin models
Cited by in corpus (23)
- Pushing the Limits of Monte Carlo Simulations for the 3d Ising Model
- Glassy Chimeras could be blind to quantum speedup: Designing better benchmarks for quantum annealing machines
- Performance potential for simulating spin models on GPU
- Understanding population annealing Monte Carlo simulations
- Domain-wall excitations in the two-dimensional Ising spin glass
- Non-Standard Finite-Size Scaling at First-Order Phase Transitions
- Efficient simulation of the random-cluster model
- Estimating the Density of States of Frustrated Spin Systems
- Multicanonical analysis of the plaquette-only gonihedric Ising model and its dual
- High-resolution Monte Carlo study of the order-parameter distribution of the three-dimensional Ising model
- Critical behavior of the spin- Baxter-Wu model: Entropic sampling simulations
- Erratum: Glassy Chimeras Could Be Blind to Quantum Speedup. . . [Phys. Rev. X 4, 021008 (2014)]
- The phase diagram for the bisected-hexagonal-lattice five-state Potts antiferromagnet
- Two-dimensional dilute Baxter-Wu model: Transition order and universality
- Finite-size scaling of Monte Carlo simulations for the fcc Ising antiferromagnet: Effects of the low-temperature phase degeneracy
- Planar ordering in the plaquette-only gonihedric Ising model
- Transmuted finite-size scaling at first-order phase transitions
- Geometric clusters in the overlap of the Ising model
- Critical behavior of the three-state random-field Potts model in three dimensions
- Finite-Size Scaling at fixed Renormalization-Group invariant
- Improvement of Monte Carlo estimates with covariance-optimized finite-size scaling at fixed phenomenological coupling
- Universality in the two-dimensional dilute Baxter-Wu model
- Harnessing finite-size effects to gauge aging in the Ising model