### Table 7-9. Final Sampling Design. (2 pages)

1996

"... In PAGE 48: ...1.1 Screening Method Alternatives Table7 -1 identifies all of the screening technologies that were considered to resolve each decision statement and the optional methods of implementing each technology. The table also summarizes the limitations associated with each screening technology and/or method of implementation and provides an estimated cost for implementation.... In PAGE 48: ... The table also summarizes the limitations associated with each screening technology and/or method of implementation and provides an estimated cost for implementation. Table7 -1. Summary of Screening Alternatives.... In PAGE 48: ...1.2 Sampling Method Alternatives Table7 -2 identifies the various types of media that need to be sampled to resolve each decision statement and alternative methods for collecting these samples. The table presents alternative... In PAGE 49: ... An estimated cost for the implementation of each sampling design has also been provided for comparison purposes. Table7 -2. Summary of Sampling Method Alternatives.... In PAGE 49: ...1.3 Implementation Design Table7 -3 presents the selected screening technology(s) and sampling method(s) for resolving each decision statement and a summary of the proposed implementation design. The table also provides the rationale for selected methods and design.... In PAGE 49: ... The table also provides the rationale for selected methods and design. Table7 -3. Selected Judgmental Design.... In PAGE 50: ...2.1 Data Collection Design Alternatives Table7 -4 identifies the statistical design alternatives (e.g.... In PAGE 50: ...able 7-4 identifies the statistical design alternatives (e.g., simple random, stratified random, and systematic) that were evaluated for each decision statement, as well as the selected design and the rationale for the selection. Table7 -4. Selected Statistical Design.... In PAGE 50: ...2.2 Mathematical Expressions for Solving Design Problems Table7 -5 identifies the statistical hypothesis test (e.g.... In PAGE 51: ...Rev. 0 7-4 Table7 -5. Statistical Methods for Testing the Null Hypothesis.... In PAGE 52: ...2.3 Select the Optimal Sample Size that Satisfies the Data Quality Objectives Table7 -6 presents the total number of samples required to be collected for each decision statement with varying error tolerances and varying widths of the gray region. The total number of samples was calculated using the statistical method identified in Table 7-4.... In PAGE 52: ....2.3 Select the Optimal Sample Size that Satisfies the Data Quality Objectives Table 7-6 presents the total number of samples required to be collected for each decision statement with varying error tolerances and varying widths of the gray region. The total number of samples was calculated using the statistical method identified in Table7 -4. As would be expected, the higher the error tolerances and wider the gray region, the smaller the number of samples that are required.... In PAGE 52: ...7 [EPA 1989]). As shown in Table7 -4, the fill material in 105-F FSB is considered analogous to waste site overburden, thus, the 100 Area SAP (DOE-RL 1998a) sampling strategy will be used. Table 7-6.... In PAGE 52: ...-Test (formula 6.7 [EPA 1989]). As shown in Table 7-4, the fill material in 105-F FSB is considered analogous to waste site overburden, thus, the 100 Area SAP (DOE-RL 1998a) sampling strategy will be used. Table7 -6. Sample Size Based on Varying Error Tolerances and LBGR.... In PAGE 53: ...2.4 Sampling Cost For varying error tolerances, and varying widths of the gray region, Table7 -7 presents the total cost for sampling and analyzing the number of samples identified in Table 7-6. As would be expected, the higher the error tolerances, the wider the gray region, the lower the sampling and analysis costs.... In PAGE 53: ...2.4 Sampling Cost For varying error tolerances, and varying widths of the gray region, Table 7-7 presents the total cost for sampling and analyzing the number of samples identified in Table7 -6. As would be expected, the higher the error tolerances, the wider the gray region, the lower the sampling and analysis costs.... In PAGE 53: ... Consult the appendices in the Remedial Design Report/Remedial Action Workplan for the 100 Area (DOE-RL 1998b) for the results of the trade-off analysis. Table7 -7. Sampling Cost Based on Varying Error Tolerances and LBGR.... In PAGE 53: ... It is important to consider trade-offs so contingency plans can be developed and the added value of selecting one set of considerations over another can be quantified. Table7 -8 identifies the sampling design that provides a balance between the known operational limitations and the ability to meet the DQOs. Once the sample design has been defined, the project may conduct a trade-off analysis to determine if the reused potential... In PAGE 54: ...Rev. 0 7-7 Table7 -8. Most Resource-Effective Data Collection Design.... In PAGE 54: ... If required, one or more outputs to DQO Steps 1 through 6 were modified to tailor the design to most efficiently meet all of the DQO constraints. For each decision statement, Table7 -9 presents a summary of the final statistical sampling design, the total number of samples to be collected. Sampling will be performed as described in Table 7-8.... In PAGE 54: ... Sampling will be performed as described in Table 7-8. Table7 -9. Final Sampling Design.... ..."

Cited by 2

### Table 1: In the form for probabilistic solutions, g(xj 1; : : :; n) is the probability density function (p.d.f.), which includes the assumptions upon which the statistical model is based. For the rule- based solutions, P is the set of predicates chosen, and the set of production rules.

"... In PAGE 4: ... The instrumentation B describes the basis func- tions that are to be employed to t the model to the observed data, and how they are to be com- bined. The possible functions can be neatly clas- si ed into ve broad groups: polynomial, harmo- nic, hyperbolic, probabilistic [26] and rule-based ( Table1 ). The process B generates a number of free parameters f ig (general examples of which are indicated in the table).... ..."

### Table 2: Table of Parameter Estimates for the Plant Data. The estimates (ergodic averages) are based upon the unconstrained prior and the permuted samples.

2005

"... In PAGE 26: ... We overlaid the histogram with a kernel density estimate (dashed). We can see from the Table2 , that (for the relabelled samples) component 1 is dominating component 2 (since =0.804).... ..."

Cited by 1

### Table 2 Two-tailed probabilities based upon the Sign Test that R2 values differ for the equations under consideration for the language groups

"... In PAGE 8: ... These were regarded as ties and the cases were not included in the analysis. The results are shown in Table2 . As may be seen, the Yule equation is statistically better in all cases as well as for all the language families.... In PAGE 9: ... The Zipf equation performs best with the miscellaneous group and worst with the Uralic languages. As shown in Table2 , though, the Yule equation provides the best fit for all four language groups. A better equation may be found in the future.... ..."

### Table 2. Computational models of language using probabilistic and statistical methodsa

"... In PAGE 2: ...earning; what is distinctive is the specific structures (e.g. trees, dependency diagrams) relevant for language. In computational linguistics, the practical challenge of parsing and interpreting corpora of real language (typi- cally text, sometimes speech) has led to a strong focus on probabilistic methods ( Table2 ). However, computational linguistics often parts company from standard linguistic www.... ..."

### Table 2. Computational models of language using probabilistic and statistical methodsa

"... In PAGE 2: ...earning; what is distinctive is the specific structures (e.g. trees, dependency diagrams) relevant for language. In computational linguistics, the practical challenge of parsing and interpreting corpora of real language (typi- cally text, sometimes speech) has led to a strong focus on probabilistic methods ( Table2 ). However, computational linguistics often parts company from standard linguistic www.... ..."

### Table 2. Performance of positional baseline, decision-based, and probabilistic systems (precision, recall, and F-measure). Probabilistic systems

2003

"... In PAGE 6: ... Even though these sets are inde- pendent, both contain sample essays from all prompt topics. Table2 compares the overall performance of the decision- and probabilistic- based systems to the positional baseline. Three of the four systems (decision-based, proba- bilistic-local, and probabilistic-global) signif- icantly outperform the baseline.... In PAGE 6: ...sed C5.0 for our voting models. Table 3 compares the positional baseline system, the best single system (that is, the decision-based system), and a voting system. For the single system, the results in Table 3 represent the same runs used in Table2 for the decision-based system Using the 10-fold cross-validation, the voting algorithm outperforms the baseline algorithm and the single system at both the category and overall system levels. Topic independence In a classroom, teachers can give students writing assignments on any topic.... ..."

Cited by 19

### Table 2: Segmentation by Race, Major, Cohort and Political Orientation

2007

"... In PAGE 9: ...orrelation is always positive -- it ranges from .22 at Rice to .58 at Baylor. Segmentation of the Social Networks Table2 shows that the friendship networks at the 10 Texas universities are segmented by race, major, cohort, and political orientation. A variety of definitions and measures of 12 Newman (2003) and Jackson (2006) report cluster coefficients ranging from .... In PAGE 10: ... The relative probability of friendship of blacks, for example, is given by: Number of pairs of blacks who are friends Total number of pairs of blacks Relative Probability of Friendship (black amp;black) = . Number of pairs of any students who are friends Total number of any pairs Table2 shows that students of the same race are more likely to form a friendship than students of different races. Most students are white/Hispanic and the probability that two white/Hispanic students form a friendship is similar to friendship formation of any two random students (unity).... In PAGE 11: ...Table2 documents the absolute segmentation. If friendships were formed randomly, the distribution of characteristics among the friends of any subset of students should equal the distribution in the population.... In PAGE 11: ... In general, minorities tend to have more diverse social networks. Table2 also documents segmentation by major, cohort, and political orientation. Students have at least twice as many friends from the same major than random friend assignment would generate.... ..."

### Table 1: Probabilistic Approaches

"... In PAGE 2: ...3 Word-based, Probabilistic Approaches The third category assumes at most whitespace and punctuation knowledge and attempts to infer MWUs using word combination probabilities. Table1 (see next page) shows nine commonly-used probabilistic MWU-induction approaches. In the table, f and P signify frequency and probability XX of a word X.... ..."

### Table 4 A comparison of the number of iterations required to meet tolerance based upon the step size in time

"... In PAGE 11: ... A comparison of the required number of layer iterations for convergence is given in Table 4. Table4 shows the number of layer iterations required to meet tolerance per time step as a function of the step size taken in time for each of the respective algorithms. In other words, Table 4 shows the number of iterations required to reach convergence in equations (4:1); (4:2:a) ? (4:2:b) and (4:4), respectively, based on the value of t in (3.... In PAGE 11: ... Table 4 shows the number of layer iterations required to meet tolerance per time step as a function of the step size taken in time for each of the respective algorithms. In other words, Table4 shows the number of iterations required to reach convergence in equations (4:1); (4:2:a) ? (4:2:b) and (4:4), respectively, based on the value of t in (3.3).... ..."