### Table 1. State distributions of the components in the example network

2005

### Table 4. Distribution of component coverage assessments for CAS and CO topics

"... In PAGE 7: ... 4.2 Distribution of component coverage Table4 summarises the distribution of assessments with respect to the component coverage dimension. Looking at the totals, a noticeable difference is the relatively high ratio of exact coverage (16%) and the relatively low ratio of too large (7%) and too small (6%) assessments for CAS topics, compared with CO (10%, 22% and 20%, respectively).... ..."

### Table 3 Service component distributions

1999

"... In PAGE 7: ...he network. This means that they are rejected before the load balancing can have any effect. Therefore, nodes 1-5 only contain the USER component. Table3 shows the SC types on each node. 6.... ..."

Cited by 1

### Table 5 gives the distribution of pins in components and nets:

"... In PAGE 16: ... Table5 : Distribution of pins in components and nets... ..."

### Table 1: Prior distribution on number of components of mixture

"... In PAGE 8: ..., 1987) : Pn(K = k) = Z Pn(K = kj )p( ) d (8) I X i=1 Pn(K = kjti)wi; (9) where ti are the I nodes at which to evaluate Pn(K = kjti) and the wi are weights. Table1 shows the prior distribution on the number of components for a sample size of 200 and a Gamma(3,10) prior distribution on . The model above was run for a burn-in of 5000 cycles and then for a further 10,000 cycles to generate samples from the posterior distribution.... ..."

### Table 1: Posterior distribution of the number of components k.

2000

"... In PAGE 9: ...Some results For each set of data our results are based on 1,000,000 sweeps of the MCMC algorithm after a burn-in of 100,000 sweeps. Table1 shows the posterior distribution of the number of components k.... In PAGE 9: ...lose to the MLEs 0.037, 0.069, 0.0046 and 0.0092, respectively, found in Ryden et al. (1998). For the wind data, Table1 suggests k = 3. Francq and Roussignol (1997) proposed k = 2 but, as noted above, they used a somewhat di erent model.... In PAGE 9: ... For k = 5 the curve overlaps, however. For the magnetic dataset, Table1 again suggests k = 3 components. Francq and Roussignol (1997) proposed k = 2 with their MLE yielding a loglikelihood of about ?6101.... In PAGE 14: ... The re- sults are quite di erent from what is obtained modelling with HMMs. Figure 8 shows the posterior distributions for k, which are much more spread out than in Table1 . For the S amp;P 500 and wind data, there is even mass at k = 30, which was our kmax.... ..."

Cited by 28

### Table 42: The percentile error distribution among the components.

2002

### Table 52: The percentile error distribution among the components.

2002

### Table 62: The percentile error distribution among the components.

2002