### TABLE I SAMPLING-BASED ROADMAP OF TREES (SRT) ALGORITHM.

2005

Cited by 8

### TABLE III PARALLEL SAMPLING-BASED ROADMAP OF TREES (SRT) ALGORITHM.

2005

Cited by 8

### Table 1: Results, relative to the sample-based algorithm, on real data. Type means nu- merical or categorical data.

2002

"... In PAGE 7: ... Then the log-likelihoods of both trees were computed for the test fold. Table1 shows whether the 99% confidence interval for the log-likelihood difference indicates that either of the algorithms outperforms the other. In seven cases the MIST-based algorithm was better, while the sample-based version won in four, and there was one tie.... ..."

Cited by 14

### Table 1: Results, relative to the sample-based algorithm, on real data. Type means nu- merical or categorical data.

2002

"... In PAGE 7: ... Then the log-likelihoods of both trees were computed for the test fold. Table1 shows whether the 99% confidence interval for the log-likelihood difference indicates that either of the algorithms outperforms the other. In seven cases the MIST-based algorithm was better, while the sample-based version won in four, and there was one tie.... ..."

Cited by 14

### Table 1: Results, relative to the sample-based algorithm, on real data. Type means nu- merical or categorical data.

2002

"... In PAGE 7: ... Then the log-likelihoods of both trees were computed for the test fold. Table1 shows whether the 99% con dence interval for the log-likelihood difference indicates that either of the algorithms outperforms the other. In seven cases the MIST-based algorithm was better, while the sample-based version won in four, and there was one tie.... ..."

Cited by 14

"... In PAGE 7: ... Then the log-likelihoods of both trees were computed for the test fold. Table1 shows whether the 99% confidence interval for the log-likelihood difference indicates that either of the algorithms outperforms the other. In seven cases the MIST-based algorithm was better, while the sample-based version won in four, and there was one tie.... ..."

### Table 1 Results, relative to the sample-based algorithm, on real data. Type means numerical or categorical data.

"... In PAGE 11: ... Then the log-likelihoods of both trees were computed for the test fold. Table1 shows whether the 99% con dence interval for the log-likelihood difference indicates that either of the algo- rithms outperforms the other. In seven cases the MIST-based algorithm was better, while the sample-based version won in four, and there was one tie.... In PAGE 11: ... In other words, the edge usage value for an accelerated run is almost the same as the fraction of its run-time, to the run over the full data. As can be seen Table1 , many of these fractions are very small, making exact measurements impossible. Where it could be measured, this observation holds both for our synthetic and real data runs.... ..."

### Table 5.3: The posterior probabilities of the main e ects and interaction terms in the 5 runs variable selection comes \for free quot; when undertaking the analysis for prediction. Variable selection, itself, is a di cult problem and one that has received much attention in the literature. The BMARS method could be used in a similar way to the Gibbs sampling-based method outlined by George and McCulloch (1993) which is shown to identify good models using a stochastic search procedure.

### Table 16: Estimated values using acceptance sampling based on the simulation with Weak prior as sampling density. Marginal output density from the Real prior used as target density.

"... In PAGE 26: ... 1a the simulation results with the Weak prior were reused based on the density from the Real simulations. As shown in Table16 the resulting distribution of the in the resampled simulation runs were close to the results in the original Real simulation runs in Table 6 with mean 139.9 compared to 139.... In PAGE 29: ...The presented algorithm seems a good choice for generating samples from the post- model distribution. The very low success rate (less than 3%) shown in Table16 may serve as an argument for not including the parameter uncertainty when using simulation models. However, as the example illustrates the presented algorithm very rapidly ensures that the succes rate of costly simulation runs will be much higher.... ..."

### Table 6: The sampling-based DFA extractor proposed originally in Fanelli (1993).

2005

Cited by 10