### Table 1 Alternatives for Selected Features of Conjoint Analysis

2007

"... In PAGE 8: ...8 Current approaches for implementing a conjoint analysis project differ in terms of several features; some main features are: stimulus representation, formats of data collection, nature of data collection, and estimation methods. Table1 lays out some alternatives for these features. The approaches that are more commonly used are: ratings- based (or Full-profile) Conjoint Analysis; Choice-based Conjoint Analysis; Adaptive Conjoint Analysis; Self-explicated Conjoint Analysis.... In PAGE 9: ... I refer the reader to Green and Srinivasan (1978, 1990), Green and Carroll (1995), and Hauser and Rao (2003) for various details of these approaches. Insert Table1 about Here Typically, a linear, additive model is used to describe the evaluations (preferences) in a ratings-based conjoint study while a multinomial logit model is used to model the probability of choice of a profile for the choice-based conjoint studies. Undoubtedly, there are several variations of these basic models used in practice.... ..."

### Table 6 Sensitivity analysis of results as a function of scenario probabilities

1998

### Table 2. Constrained graph layout.

"... In PAGE 14: ... The constrained layout of Graph 1 to Graph 9, with the constraints imposed, are given in Figure 8. Table2 shows the time in seconds for each method to layout the constrained graph. Again, Model B is significantly faster than Model A and Model C is usually as fast as Model B.... ..."

### Table 1: Speci ed prior moments for the constrained-parameter example

1995

"... In PAGE 14: ... We now discuss how we assigned a prior distribution to these parameters that matched speci ed prior moments while satisfying the constraint. For the purposes of this article, we label the parameters x1; x2; x3; x4, with the constraint P4 j=1 xj = 1: The information from the literature search was summarized as prior means and standard deviations on the logarithms of the parameters, as displayed in Table1 . (Speci cation in terms of the logarithms makes sense for the lognormal distributions of the other parameters in the model.... In PAGE 14: ... In practice, the prior variances are low enough that specifying the mean and coe cient of variation on the untransformed scale of would give virtually identical results.) We rst construct a parametric family for the prior distribution of x, given hyperparameters , and then determine by matching to the eight transformed moments given in Table1 , using the algorithm of Section 4.2.... In PAGE 15: ...is acceptable, since the numbers in Table1 are only approximations based on a literature review. The most familiar model for variables that sum to 1 is the Dirichlet.... In PAGE 15: ... In computing the logarithm of the Dirichlet density and its derivative, we must compute the log-gamma function and its derivative, which are fortunately easy to calculate numerically using standard computer programs. We start the iteration at the point = (48; 20; 7; 25), which roughly ts the means and standard deviations in the rst column of Table1 . We proceed with twenty steps of simulation and Newton-Raphson with N = 2000, followed by one simulation of N = 10000 and three Newton-Raphson steps.... In PAGE 15: ... For a comparison, we ran another simulation, starting at the point = (240; 100; 35; 125). In both simulations, the moments had reached approximate convergence, but not to the desired moments in Table1 . For example, the standard deviation of x1 in the best method of moments t is log(1:07), compared to the desired value of log(1:2).... In PAGE 16: ...analytic form of the distribution of x. We start the iteration with the rst four components of (the means of the components of ) set to the values in the rst column of Table1 and the second four components (the standard deviations) set to the values in the second column of Table 1. We then apply the algorithm of Section 4.... In PAGE 16: ...analytic form of the distribution of x. We start the iteration with the rst four components of (the means of the components of ) set to the values in the rst column of Table 1 and the second four components (the standard deviations) set to the values in the second column of Table1 . We then apply the algorithm of Section 4.... ..."

Cited by 1

### Table 5-7: Summary for Offsets From Various offline Methods for State Route 26, Lafayette, Indiana (Cycle length = 120 seconds)

"... In PAGE 8: ...Figure Page 5-8 Comparison of offline offset design methods, Eastbound State Route 26 (Graph created with values from Table5 -7 through Table 5-11) .... In PAGE 8: ...Graph created with values from Table 5-7 through Table 5-11) ................90 5-9 Comparison of offline offset design methods, Eastbound State Route 26 (Graph created with values from Table5 -7 through Table 5-11) .... In PAGE 8: ...Graph created with values from Table 5-7 through Table 5-11) ................90 5-10 Comparison of offline offset design methods, Westbound State Route 26 (Graph created with values from Table5 -7 through Table 5-11).... In PAGE 8: ...Graph created with values from Table 5-7 through Table 5-11)..............91 5-11 Comparison of offline offset design methods, Westbound State Route 26 (Graph created with values from Table5 -7 through Table 5-11).... In PAGE 74: ... Subjective values are required for determining the arterial classification, as well as for the vehicle progression classifications provided in HCM Table 11-5. Table5 -1a and Table 5-1b show the HCM tables in which subjective values are required. Table 5-2 provides the HCM definitions for the progression adjustment factors (PF) for different arrival types.... In PAGE 74: ... Table 5-1a and Table 5-1b show the HCM tables in which subjective values are required. Table5 -2 provides the HCM definitions for the progression adjustment factors (PF) for different arrival types. These subjective requirements are explicitly acknowledged in the HCM, and the manual states that if knowledge of the intended signal timings and quality of progression are not available, no meaningful estimation of arterial level of service is possible, even on a planning level [NRC, 1997].... In PAGE 76: ... Table5 -1: Highway Capacity Manual Tables Requiring Subjective Values HCM TABLE 11-3. ARTERIAL CLASSIFICATION ACCORDING TO FUNCTIONAL AND DESIGN CATEGORIES FUNCTIONAL CATEGORY DESIGN CATEGORY PRINCIPAL ARTERIAL MINOR ARTERIAL High Speed design And control I Not Applicable Typical suburban Design and Control II II Intermediate Design II III or IV Typical urban Design III or IV IV (a) Arterial classification subjective values HCM TABLE 11-5.... In PAGE 77: ... Table5 -2: Highway Capacity Manual Definitions for Progression Adjustment Factors HIGHWAY CAPACITY MANUAL DESCRIPTIONS FOR PROGRESSION ADJUSTMENT FACTORS ARRIVAL TYPE DESCRIPTION FOR PROGRESSION ADJUSTMENT FACTOR 1 Dense platoon containing more than 80 percent of the lane group volume and arriving at the start of the red phase. This arrival type is representative of arterials that experience very poor progression quality as a result of conditions such as lack of overall network signal optimization.... In PAGE 78: ... However with advancements in traffic controller hardware functions to include actuated controls, the delay equation does not account for how variations in green splits affect the start of green times in modern coordinated-actuated controllers. Such variations in the start of green times directly impact the quality of progression (HCM PF Factors shown in Table5 -1) and the amount of delay experienced. However, the HCM has no procedure for estimating which PF Factors shall be used with design volumes or for the design of coordinated- actuated controller timings.... In PAGE 79: ...Furthermore, determining the quality of progression factor for the PF term of the HCM average intersection delay equation is a difficult task, even if observed in the field by an engineer. For existing arterial conditions, one analyst may conclude that current arterial signal timings are not facilitating progression and assign an arrival of type-2 ( Table5 -2). But, another analyst may conclude that because of platoon dispersion, vehicle progression for the exact same arterial resembles random arrivals and assign an arrival of type-3 (Table 5-2).... In PAGE 79: ... For existing arterial conditions, one analyst may conclude that current arterial signal timings are not facilitating progression and assign an arrival of type-2 (Table 5-2). But, another analyst may conclude that because of platoon dispersion, vehicle progression for the exact same arterial resembles random arrivals and assign an arrival of type-3 ( Table5 -2). Both of these arrival types are subjective values and are difficult to distinguish between one another in the field by technicians typically employed to do so.... In PAGE 80: ... An example of how slight discrepancies with both of the discussed issues impact an arterial level of service is provided. Table5 -3 and Table 5-4 show the quantitative calculations used to compute an arterial level of service for a hypothetical 0.2 mile suburban arterial section with slightly different values assigned to the g/c ratios and the quality of progression factors.... In PAGE 81: ...developed for accurately modeling the multitude of coordinated-actuated control parameters now in use on most modern traffic signal systems. Table5 -3: HCM Calculations for Average Control Delay per Vehicle on Arterial Approach SUMMARY OF ARTERIAL INTERSECTION DELAY ESTIMATES Arterial Description: 4 lane suburban arterial, 0.2 mile section, volume = 1500 vph Adjusted Saturation flow rate = 3000 vph, Unit extension of 2.... In PAGE 81: ...or X = 0.833 and X = 0.714 respectively. Table5 -4: HCM Calculations for Arterial Level of Service COMPUTATION OF ARTERIAL LOS WORKSHEET Arterial Description: 4 lane suburban arterial, 0.2 mile section, Volume = 1500 vph, Adjusted Saturation flow rate = 3000 vph, Unit extension of 2.... In PAGE 84: ...then tabulated to calculate the arterial cumulative delay and travel times with respect to intersection locations. See Table5 -5 for an example of arterial cumulative value calculations. Plots of these cumulative delay and travel times can provide insight on the performance of the system.... In PAGE 85: ... Additionally, although the graphic procedure discussed is limited to cumulative delay and travel times, similar graphic procedures can be expanded to include the number of stops or emission estimates for HC, CO, and NOX. Table5 -5: Cumulative Delay and Travel Times used to Construct Figure 5-4 and Figure 5-5 MID-DAY TRAFFIC S.R.... In PAGE 87: ... STEP 2: Data Calculations Individual link values are then used to compute the cumulative values for link lengths, travel times, and delay times at each of the node locations on the arterial. After these cumulative data are compiled, the averages ( Table5 -5, cols. 7 amp; 8), and standard deviations (Table 5-5, cols.... In PAGE 87: ... After these cumulative data are compiled, the averages (Table 5-5, cols. 7 amp; 8), and standard deviations ( Table5 -5, cols. 9 amp; 10) for the cumulative arterial measures of effectiveness (MOEs) are computed.... In PAGE 88: ... In contrast to current methods, this proposed performance evaluation procedure can provide a graphic comparison of different system plans to validate new proposed signal timings. As shown in Figure 5-6, Figure 5-7, and Table5 -6 ,a proposed arterial timing plan can be compared with an existing arterial timing plan through graphical and tabular analysis procedures to quantitatively illustrate that the proposed timing plan accomplishes the design objective of reducing delay and travel times. This comparison of alternate signal timing plans provides the designer a tool that illustrates the improvement of the proposed arterial signal timing plan over the existing arterial signal timing plan.... In PAGE 90: ... Table5 -6: Lane Group Comparison of Delay per Vehicle at Individual Intersection; State Route 26, Node 1 Lane Group Movements Existing Delay (sec/veh) Proposed Delay (sec/veh) Existing Level of Service Proposed Level of Service 41.4 38.... In PAGE 94: ... All offset setting methodologies were used with the intent to replicate how practicing engineers typically specify offsets for coordinated-actuated systems. Table5 -7 summarizes the offsets determined with each method and what offset setting technique was used within that package. Table 5-7: Summary for Offsets From Various offline Methods for State Route 26, Lafayette, Indiana (Cycle length = 120 seconds)... In PAGE 95: ...Cumulative results for measures of effectiveness consisting of travel time (sec/veh) and delay (per-min) for the arterial through movement for each timing strategy are provided in Table5 -8 through Table 5-12. Graphical performance summaries comparing the alternate offset timing strategies are shown in Figure 5-8 through Figure 5-11.... In PAGE 96: ... Table5 -8: Existing Offset Results LINK START END CUMM TRAVEL TIME (sec) STDEV CUMM TRAVEL TIME (sec) CUMM DELAY TIME (per-min) STDEV CUMM DELAY TIME (per-min) 101 1 32.6 1.... In PAGE 97: ... Table5 -9: Fine-Tuned Offset Results LINK START END CUMM TRAVEL TIME (sec) STDEV CUMM TRAVEL TIME (sec) CUMM DELAY TIME (per-min) STDEV CUMM DELAY TIME (per-min) 101 1 32.2 1.... In PAGE 98: ... Table5 -10: PASSER II-90 Offset Results LINK START END CUMM TRAVEL TIME (sec) STDEV CUMM TRAVEL TIME (sec) CUMM DELAY TIME (per-min) STDEV CUMM DELAY TIME (per-min) 101 1 32.1 0.... In PAGE 99: ... Table5 -11: SYNCHRO Offset Results LINK START END CUMM TRAVEL TIME (sec) STDEV CUMM TRAVEL TIME (sec) CUMM DELAY TIME (per-min) STDEV CUMM DELAY TIME (per-min) 101 1 32.1 1.... In PAGE 100: ... Table5 -12: TRANSYT-7F Offset Results LINK START END CUMM TRAVEL TIME (sec) STDEV CUMM TRAVEL TIME (sec) CUMM DELAY TIME (per-min) STDEV CUMM DELAY TIME (per-min) 101 1 31.4 0.... In PAGE 101: ...Cumulative Travel Time (State Route 26 (Eastbound)) (Earl Avenue to Creasy Lane) 0 50 100 150 200 250 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Time (s) Signal Location Fine-tuned Existing PASSER2 Offsets SYNCHRO TRANSYT 7F Posted Speed Limit Figure 5-8: Comparison of offline offset design methods, Eastbound State Route 26 (Graph created with values from Table5 -8 through Table 5-12) Cumulative Delay (State Route 26 (Eastbound)) (Earl Avenue to Creasy Lane) 0 100 200 300 400 500 600 700 800 900 1000 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Delay (person-min) Signal Location Fine-tuned Existing PASSER2 SYNCHRO TRANSYT 7F Figure 5-9: Comparison of offline offset design methods, Eastbound State Route... In PAGE 101: ...Cumulative Travel Time (State Route 26 (Eastbound)) (Earl Avenue to Creasy Lane) 0 50 100 150 200 250 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Time (s) Signal Location Fine-tuned Existing PASSER2 Offsets SYNCHRO TRANSYT 7F Posted Speed Limit Figure 5-8: Comparison of offline offset design methods, Eastbound State Route 26 (Graph created with values from Table 5-8 through Table 5-12) Cumulative Delay (State Route 26 (Eastbound)) (Earl Avenue to Creasy Lane) 0 100 200 300 400 500 600 700 800 900 1000 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Delay (person-min) Signal Location Fine-tuned Existing PASSER2 SYNCHRO TRANSYT 7F Figure 5-9: Comparison of offline offset design methods, Eastbound State Route 26 (Graph created with values from Table5... In PAGE 102: ...Cumulative Travel Time (State Route 26 (Westbound)) (Creasy Lane to Earl Avenue) 0 50 100 150 200 250 300 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Time (s) Signal Location Fine-tuned Existing PASSER2 SYNCHRO TRANSYT 7F Posted Speed Limit Figure 5-10: Comparison of offline offset design methods, Westbound State Route 26 (Graph created with values from Table5 -8 through Table 5-12) Cumulative Delay (State Route 26 (Westbound)) (Creasy Lane to Earl Avenue) 0 200 400 600 800 1000 1200 1400 1600 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Delay (person-min) Signal Location Fine-tuned Existing PASSER2 SYNCHRO TRANSYT 7F Figure 5-11: Comparison of offline offset design methods, Westbound State... In PAGE 102: ...Cumulative Travel Time (State Route 26 (Westbound)) (Creasy Lane to Earl Avenue) 0 50 100 150 200 250 300 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Time (s) Signal Location Fine-tuned Existing PASSER2 SYNCHRO TRANSYT 7F Posted Speed Limit Figure 5-10: Comparison of offline offset design methods, Westbound State Route 26 (Graph created with values from Table 5-8 through Table 5-12) Cumulative Delay (State Route 26 (Westbound)) (Creasy Lane to Earl Avenue) 0 200 400 600 800 1000 1200 1400 1600 0 1000 2000 3000 4000 5000 6000 7000 Linear Distance Along Corridor (ft) Delay (person-min) Signal Location Fine-tuned Existing PASSER2 SYNCHRO TRANSYT 7F Figure 5-11: Comparison of offline offset design methods, Westbound State Route 26 (Graph created with values from Table5... In PAGE 103: ... To accommodate left turning vehicles from upstream intersections, an online algorithm should attempt to keep the average start of green as low as possible in relation to downstream intersections while also accounting for downstream queues that may impede progression. Table5 -13 through Table 5-15 provide statistical significance summaries comparing the fine-tuning offset... In PAGE 104: ... Table5 -13: State Route 26 statistical significance summary; Fine-tuned offsets versus PASSER-II 90 offsets Measure of Effectiveness FINE TUNED PASSER II-90 Percent Reduction Calculated t-statistic Test statistic for 95% C.I.... In PAGE 104: ...078 -1.688 (#) Standard deviation; n1 = n2 = 20 replications Table5 -14: State Route 26 statistical significance summary; Fine-tuned offsets versus SYNCHRO offsets Measure of Effectiveness FINE TUNED SYNCHRO Percent Reduction Calculated t-statistic Test statistic for 95% C.I.... In PAGE 105: ... Table5 -15: State Route 26 statistical significance summary; Fine-tuned offsets versus TRANSYT-7F Measure of Effectiveness FINE TUNED PASSER II-90 Percent Reduction Calculated t-statistic Test statistic for 95% C.I.... ..."

### Table 3.1 Results for Algorithm 2.2 and the modified projection method on linearly constrained variational inequality problems.

1999

Cited by 20

### Table 2: Timings for fast and direct velocity evaluation methods with NT trian- gles. Asterisks denote timings obtained by extrapolation for the direct method.

"... In PAGE 31: ...6 Numerical results We now present numerical results which show that our algorithm achieves con- siderable speedups over direct evaluation. Table2 gives the result of fast and direct velocity evaluations for uniformly distributed random vortices in [?1; 1]2 with random ! values uniformly distributed on [?1; 1]. We take q = 0:2 and = 10?3, which requires p = 10 with r = 1.... ..."

### Table 1: Prices computed by alternative methods under the 2-factor GBM model

2000

"... In PAGE 13: ... 4.2 Computational Results Table1 documents the spread option prices across a range of strikes under the two factor Geo- metric Brownian motion model [22], computed by three di erent techniques: one-dimensional integration (analytic), the fast Fourier Transform and the Monte Carlo method. The values for the FFT methods shown are the \lower quot; prices, computed over , regions that approach the the true exercise region from below and are therefore all less than the analytic price in the rst column.... ..."

Cited by 5

### Table 3 Results obtained with the register allocation tool. Not constrained Constrained

"... In PAGE 16: ... Register allocation. Table3 shows the results obtained from the register allocation tool. Two di erent runs are shown : Not constrained : In the rst run, all registers in the architecture (cf.... In PAGE 17: ...together with the nal machine cycle count1 for one sample period of the system, is shown in Table3 (middle column). Constrained : In the second run, the capacity of the registers is constrained to one.... In PAGE 17: ... In this case the data routing algorithm selects alternative routing paths, such as memory spills, and introduces a partial sequentialisation of the cdfg, in order to comply with the register constraints. The results are shown in Table3 (right column). Memory spills and sequence edges are by preference inserted in non-critical control ow blocks in the cdfg, such as outer loops and non-critical branches, so that only a small increase of the total machine cycle count is obtained.... ..."

### Table 1: Analysis of general, unconstrained variance vs. nested, constrained variance models

2004

"... In PAGE 5: ... The Baye- sian Information Criterion (BIC) [19] was used for model choice. For both datasets examined, the nested models had considerably higher BIC values than the general mod- els, regardless of the kind of error model ( Table1 ), indi- cating that the nested models, with fewer parameters, are preferable. Computation time for analysis of published data sets var- ied across models (Table 1).... In PAGE 5: ... For both datasets examined, the nested models had considerably higher BIC values than the general mod- els, regardless of the kind of error model (Table 1), indi- cating that the nested models, with fewer parameters, are preferable. Computation time for analysis of published data sets var- ied across models ( Table1 ). Computation using additive models (AV, AC, AU) was more rapid than computation using multiplicative models.... In PAGE 11: ... The Bayesian Information Criterion for model selection can be used to choose between models that invoke distinct error variances or coefficients of variation for each node as characterized by genotype, environment, and developmental state, and the nested models that invoke a single variance or CV for all nodes. The values of the BIC for the relatively small studies exam- ined here ( Table1 ) clearly support analysis with the nested models that invoke a single variance or CV. In addition to direct assessment of the fit of the model to the data, power to detect known differences may guide model choice.... In PAGE 11: ... Overall, a model incorporated an assumption of small additive error terms and a single error CV for all nodes (model AC) had the greatest power to detect differences in gene expression level. In practice, model AC was also the fastest computa- tionally ( Table1 ), perceptibly requiring fewer tuning steps to find an appropriate jump size for the generation of posterior distributions by Markov Chain Monte Carlo. If variances are generally proportional to their expression levels, then the constrained CV models (AC and MC) per- tain.... ..."