Limited Sensitivity Analysis Research Articles

Seismic damage analysis of shallow buried subway station in clayey sand soil under mainshock-aftershock earthquakes

During earthquake events, a mainshock may trigger a number of following aftershock earthquakes in a short time. Usually, structures will be damaged to a certain extent by the mainshock, and aftershocks can further exacerbate the damage to structures, making post-disaster rescue and rehabilitation extremely challenging. Yet, most of research on seismic performance of underground structures only considered the single mainshock, ignoring the effect of aftershocks. In this study, a nonlinear numerical model of the shallow buried shallow subway station in clayey sand soil under mainshock-aftershock sequences was constructed to replicate the damage evolution process of underground structures. A limited numerical sensitivity analysis was performed considering the influences of the magnitude of mainshock and aftershock intensity. The results indicate that the damage of subway station is closely related to the magnitude of mainshock intensity. The aftershocks might cause more serious incremental damage to underground structures and secondary displacement of the site, potentially lead to collapse of the subway station, when the mainshock magnitude is greater. With the superposition of the mainshock and aftershock, the relative horizontal displacement of the subway station could reach the inter-story drift limit value. Therefore, the aftershock should be taken into account for seismic safety design of shallow underground structures.

Experimental investigation on 3D printed lightweight sandwich structures for energy absorption aerospace applications

One of the ongoing challenges in aeronautics is the development of increasingly lighter structures. This has become a crucial goal because structural lightening means improving aircraft performance in terms of speed, manoeuvrability, fuel efficiency, and at the same time reducing manufacturing and service costs. The aerospace industry continues to focus more and more on this goal and every improvement in technology and materials can bring significant advantages in performance, efficiency, and safety of aircraft. The present work is part of this framework, as it analyses the feasibility of achieving very high weight reduction in sandwich panels using a new manufacturing approach. It introduces an experimental limited sensitivity analysis on the mechanical responses of composite sandwich structures for shock-absorption applications lightened by appropriately setting a specific additive manufacturing process parameter: the infill value. The investigated sandwich structures are characterised by a core Designed for Additive Manufacturing (DfAM) in order to maximise their performance in terms of energy-to-weight ratio and damping of impact loads. The material chosen for the inner part of the sandwich structure (core and internal face sheets) is polypropylene (PP) while the external face sheets are in Carbon Fibre Reinforced Polymers (CFRP).By comparing the post-impact responses at 20 J impact of three sandwich configurations with the same external shape but different material layer densities related to different setting of the infill parameter in the frame of the printing process, the work proves that this approach leads to lightening of this specific sandwich structures by up to 28% and at the same time improves their structural effectiveness in terms of energy absorption characteristics.The comparison was made by relating specific absorption indices, force-time and force-displacement graphs and CT scans.

Numerical Assessment on the Fatigue Behavior of Composite Open‐Hole Tensile Specimens

AbstractThis paper deals with the fatigue failure of composite coupon characterized by circular hole and subjected to tensile cyclic loading conditions. A limited sensitivity analysis has been performed to study the onset and propagation of intralaminar damages, in terms of fibers and matrix failure. The residual strength material properties degradation model, proposed by Shokrieh and Lessard, has been implemented in the FEM code ANSYS Mechanical and employed to study the damages induced by stress concentrations and assess the effects of the stacking sequence and the geometrical parameters on the fatigue damage.

Seismic Interaction of Adjacent Structures on Liquefiable Soils: Insight from Centrifuge and Numerical Modeling

In urban environments, structures are often built in close proximity to each other. Seismic coupling and structure-soil-structure interaction (SSSI) are known to affect system accelerations, settlement, and tilt with consequential impact on structural damage. Yet, the extent and nature of these interactions are poorly understood, particularly on ground susceptible to liquefaction. In this paper, we use dynamic centrifuge and numerical modeling of isolated and neighboring, similar and dissimilar, shallow-founded structures on layered, level, saturated, and liquefiable soils to provide insight into (1) the mechanisms of SSSI; and (2) the relative influence of key parameters on system performance. Fully-coupled, nonlinear finite-element analyses of the centrifuge experiments indicated that in addition to a comprehensive calibration of the soil constitutive model parameters, use of higher-order elements and a sufficiently large domain size in three dimensions (3D) were critical ingredients to predicting the general trends in system response compared to centrifuge recordings. A limited numerical sensitivity analysis was performed subsequently. The results identified the key parameters affecting SSSI as spacing between the two foundations (S) in relation to their width (W) as well as the contact stress and geometry of the neighboring foundation-structure system. SSSI slightly decreased the permanent settlement of structures at the expense of a notable increase in their permanent tilt, particularly when S≤W. The foundation’s spectral accelerations were observed to amplify at shorter periods when near a taller and heavier building at S≤W/3, which was attributed to the added confinement. Increasing the uniform thickness of the critical liquefiable layer increased both adjacent structures’ permanent settlement, while not affecting their residual tilt or SSSI. Importantly, the impact of SSSI on foundation tilt and accelerations remained significant for building spacings exceeding 2.5W. The results point to the importance of considering the impact of SSSI on structure’s key engineering demand parameters and the urgent need for improved guidelines when assessing and treating liquefaction in urban settings.

A methodological framework for model selection in interrupted time series studies

Interrupted time series (ITS) is a powerful and increasingly popular design for evaluating public health and health service interventions. The design involves analyzing trends in the outcome of interest and estimating the change in trend following an intervention relative to the counterfactual (the expected ongoing trend if the intervention had not occurred). There are two key components to modeling this effect: first, defining the counterfactual; second, defining the type of effect that the intervention is expected to have on the outcome, known as the impact model. The counterfactual is defined by extrapolating the underlying trends observed before the intervention to the postintervention period. In doing this, authors must consider the preintervention period that will be included, any time-varying confounders, whether trends may vary within different subgroups of the population and whether trends are linear or nonlinear. Defining the impact model involves specifying the parameters that model the intervention, including for instance whether to allow for an abrupt level change or a gradual slope change, whether to allow for a lag before any effect on the outcome, whether to allow a transition period during which the intervention is being implemented, and whether a ceiling or floor effect might be expected. Inappropriate model specification can bias the results of an ITS analysis and using a model that is not closely tailored to the intervention or testing multiple models increases the risk of false positives being detected. It is important that authors use substantive knowledge to customize their ITS model a priori to the intervention and outcome under study. Where there is uncertainty in model specification, authors should consider using separate data sources to define the intervention, running limited sensitivity analyses or undertaking initial exploratory studies.

Large Scale Tertiary CO2 EOR in Mature Water Flooded Norwegian Oil Fields

A technical-economical model for a large-scale infrastructure combining CO2 EOR and aquifer storage has been used to construct a scenario including 23 Norwegian Continental Shelf oil fields that have been identified as potential candidates for CO2 flooding. In the injection scenario, 70 million tonnes of CO2 is injected annually over 40 years. A limited sensitivity analysis has been performed. The EOR potential for continuous CO2 injection is estimated to be between 276 and 351 million Sm3. This corresponds to 5.9 and 7.6% of the oil originally in place depending on the oil price (low/high: 40/120 USD/bbl), the cost of CO2 that the oil producers must pay for all stored CO2 (low/high: 0/50 USD/tonne) and well costs (low/high 25/42 million USD/well). In addition to transportation costs through the main pipeline (8 USD/tonne) specific costs for aquifer deposition also applies (8 USD/tonne). CO2 mass balance calculations show that more CO2 is stored in the oil reservoirs during tertiary flooding compared to the CO2 formed by combustion of the produced oil. The CO2 footprint becomes even more negative when the CO2 stored in aquifers is included in the calculations.

An integrated ecological modeling system for assessing impacts of multiple stressors on stream and riverine ecosystem services within river basins

We demonstrate a novel, spatially explicit assessment of the current condition of aquatic ecosystem services, with limited sensitivity analysis for the atmospheric contaminant mercury. The Integrated Ecological Modeling System (IEMS) forecasts water quality and quantity, habitat suitability for aquatic biota, fish biomasses, population densities, productivities, and contamination by methylmercury across headwater watersheds. We applied this IEMS to the Coal River Basin (CRB), West Virginia (USA), an 8-digit hydrologic unit watershed, by simulating a network of 97 stream segments using the SWAT watershed model, a watershed mercury loading model, the WASP water quality model, the PiSCES fish community estimation model, a fish habitat suitability model, the BASS fish community and bioaccumulation model, and an ecoservices post-processer. Model application was facilitated by automated data retrieval and model setup and updated model wrappers and interfaces for data transfers between these models from a prior study. This companion study evaluates baseline predictions of ecoservices provided for 1990–2010 for the population of streams in the CRB and serves as a foundation for future model development.

Multiple input describing function analysis of non-classical aileron buzz

This paper focuses on the computational study of nonlinear effects of unsteady aerodynamics for non-classical aileron buzz. It aims at a comprehensive investigation of the aileron buzz phenomenon under varying flow parameters using the describing function technique with multiple inputs. The limit cycle oscillatory behavior of an asymmetrical airfoil is studied initially using a CFD-based numerical model and direct time marching. Sharp increases in limit cycle amplitude for varying Mach numbers and angles of attack are investigated. An aerodynamic describing function is developed in order to estimate the variation of limit cycle amplitude and frequency with Mach number and angle of attack directly, without time marching. The describing function results are compared to the amplitudes and frequencies predicted by the CFD calculations for validation purposes. Furthermore, a limited sensitivity analysis is presented to demonstrate the potential of the approach for aeroelastic design.

Evaluation of uncertainty in the well-to-tank and combustion greenhouse gas emissions of various transportation fuels

Growing concern over climate change has created pressure on the oil and gas industry to reduce their greenhouse gas emissions (GHG). There have been multiple well-to-tank+combustion (WTT+C) studies that have examined various crude oils in an attempt to determine their GHG emission intensities. The majority of these studies published deterministic point estimates with a limited sensitivity analysis. Due to the variation in results between studies and the lack of uncertainty analysis the usefulness of these studies to policy makers and industry representatives is limited. The goal of this study is to expand on the previous literature by identifying a range of WTT+C emissions for crude oils from Saudi Arabia, Venezuela, and Iran. First, the previously published FUNdamental ENgineering PrinciplEs-based ModeL for Estimation of GreenHouse Gases in Conventional Crude Oils (FUNNEL-GHG-CCO) was used to perform a WTT+C analysis of the crudes GHG emissions. Then a Monte Carlo simulation was carried out using existing literature to define input distributions for the key inputs. The resulting gasoline WTT+C GHG emission ranges are 113.6–138.5 (Venezuela High Steam), 101.6–109.9 (Venezuela Low Steam), 101.1–109.2 (Sirri, Iran), and 95.3–99.9gCO2eq/MJ (Saudi Arabia). This result indicates that even when uncertainty is taken into account the Venezuelan high steam crude clearly has higher emissions than the Saudi Arabia crude. The results of this study will give policy makers and industry representatives a better understanding of how the WTT+C GHG emissions vary between various crude oils.

Paucity and Inconsistency: A Systematic Review and Critique of Budget Impact Analyses of Disease-Modifying Therapies for Multiple Sclerosis in the UK and the Implications for Policy in the UK.

Budget impact analysis (BIA) has become an essential part of economic evaluation within health technology assessment. Several disease-modifying therapies (DMTs) are now available for the treatment of multiple sclerosis (MS). This study sought to identify the inputs and assumptions used in existing BIAs for DMTs in the UK, and the uncertainty and variation in these, to allow critique within the context of UK policy. MEDLINE and the Economic Evaluations Database from the Cochrane Library were searched systematically on 15December 2014 to identify BIAs of DMTs licensed for MS in the UK. In addition, the National Institute for Health and Care Excellence (NICE) and National Health Service (NHS) England websites were searched for relevant publications and grey literature searching was undertaken. Sources and assumptions from the included analyses were extracted, compared and critiqued. The database searches produced 115 de-duplicated results. An additional 12 results were identified from the NICE and NHS England websites. No BIAs of DMTs for MS in the UK were identified in the literature. All ten included studies were from the NICE website, comprising manufacturer submissions for each DMT and corresponding NICE costing templates. There are considerable uncertainties in the inputs and assumptions used in the BIAs, but limited sensitivity analyses were undertaken. Data limitations were not highlighted in the results, failing to present the uncertainty in the results to users clearly. It is to be welcomed that NICE has recently consulted on a process change to allow additional critique of the costing templates.

A Numerical Assessment of Fibre Bridging Influence on Composite Panels Skin-stringer Debonding

Numerical simulations on stiffened composite panels have been performed in order to investigate the influence of fibre bridging phenomenon on the onset and on the evolution of skin-stringer debonding. A novel numerical procedure for delamination growth simulation, implemented in ANSYS® FEM code by Ansys Parametric Design Language and enhanced to take into account GIc variations related to the fibre bridging phenomenon, has been used to numerically simulate the skin-stringer separation. Indeed, fibre-reinforced composites can develop high fibre bridging under mode I (peeling) delamination growth due to the additional resistance to crack opening offered by delaminated fibres, leading to a significant increase of mode I critical strain energy release rate. Within the present paper, a limited sensitivity analysis is presented to assess the influence of geometrical parameters of stiffened composite panels on the fibre bridging relevance in skin-stringer debonding in terms of debonded area.

Valuing the Economic Costs of Allergic Rhinitis, Acute Bronchitis, and Asthma from Exposure to Indoor Dampness and Mold in the US.

Two foundational methods for estimating the total economic burden of disease are cost of illness (COI) and willingness to pay (WTP). WTP measures the full cost to society, but WTP estimates are difficult to compute and rarely available. COI methods are more often used but less likely to reflect full costs. This paper attempts to estimate the full economic cost (2014$) of illnesses resulting from exposure to dampness and mold using COI methods and WTP where the data is available. A limited sensitivity analysis of alternative methods and assumptions demonstrates a wide potential range of estimates. In the final estimates, the total annual cost to society attributable to dampness and mold is estimated to be $3.7 (2.3–4.7) billion for allergic rhinitis, $1.9 (1.1–2.3) billion for acute bronchitis, $15.1 (9.4–20.6) billion for asthma morbidity, and $1.7 (0.4–4.5) billion for asthma mortality. The corresponding costs from all causes, not limited to dampness and mold, using the same approach would be $24.8 billion for allergic rhinitis, $13.5 billion for acute bronchitis, $94.5 billion for asthma morbidity, and $10.8 billion for asthma mortality.

Two-dimensional reactive transport modeling of the alteration of a fractured limestone by hyperalkaline solutions at Maqarin (Jordan)

Two-dimensional reactive transport modeling of the Maqarin Eastern Springs site, a natural analogue for the alteration of a fractured limestone by high-pH Portland cement waters, has been performed using the CrunchFlow code. These 2D calculations included transport by advection–dispersion–diffusion along a single fracture and diffusion in the wall rock. Solute transport was coupled to mineral dissolution and precipitation. A limited sensitivity analysis evaluated the effect of different values of primary mineral surface areas, flow velocity and sulfate concentration of the inflowing high-pH solution.Major secondary minerals include ettringite–thaumasite, C–S–H/C–A–S–H and calcite. C–S–H/C–A–S–H precipitation is controlled by the dissolution of primary silicates. Ettringite precipitation is controlled by diffusion of sulfate and aluminum from the wall rock to the fracture, with aluminum provided by the dissolution of albite. Calcite precipitation is controlled by diffusion of carbonate from the wall rock. Extents of porosity sealing along the fracture and in the fracture-wall rock interface depend on assumptions regarding flow velocity and composition of the high-pH solution. The multiple episodes of fracture sealing and reactivation evidenced in the fracture infills were not included in the simulations. Results can qualitatively reproduce the reported decrease in porosity in the fractures and in the wall rock next to the fractures. Instances of porosity increase next to fractures caused by carbonate dissolution were not reproduced by the calculations.

Effect of medical thromboprophylaxis on mortality from pulmonary embolus and major bleedingy.

Several studies have failed to discover a beneficial effect of medical thromboprophylaxis on mortality. To examine the relative influence of acute fatal pulmonary embolism (PE) and fatal major haemorrhage on overall mortality in medical patients treated with low molecular weight heparin (LMWP) for prophylaxis. The author compared deaths from the above factors using data from a recent Cochrane Collaboration meta-analysis. Data from trials satisfying the criteria of the Cochrane analysis plus additional exclusions to avoid bias were pooled to produce point estimates of mortality from PE and major bleeds to estimate net mortality benefit. Estimates were then subject to limited sensitivity analysis based on reported epidemiological data. Reported PE and major bleeds were 0.44 per cent and 0.27 per cent, respectively. The corresponding case-specific mortality rates were 30.8 per cent and 12.8 per cent and the relative risk reduction (RRR) for PE was 23.2 per cent. Estimated deaths from major bleeds exceeded PE deaths avoided by a small margin (3/100,000 patients given prophylaxis). This excess increased to 30/100,000 when more plausible literature values for PE case fatality rates were applied. Medical thromboprophylaxis has a finely balanced effect on mortality but may increase it. Such an effect would explain the failure to discover a mortality benefit from medical thromboprophylaxis. Further work, including a formal meta-analysis and additional clinical studies, is required to confirm this picture.

The Use of PBPK Models to Inform Human Health Risk Assessment: Case Study on Perchlorate and Radioiodide Human Lifestage Models

Physiologically-based pharmacokinetic (PBPK) models are often submitted to or selected by agencies, such as the U.S. Environmental Protection Agency (U.S. EPA) and Agency for Toxic Substances and Disease Registry, for consideration for application in human health risk assessment (HHRA). Recently, U.S. EPA evaluated the human PBPK models for perchlorate and radioiodide for their ability to estimate the relative sensitivity of perchlorate inhibition on thyroidal radioiodide uptake for various population groups and lifestages. The most well-defined mode of action of the environmental contaminant, perchlorate, is competitive inhibition of thyroidal iodide uptake by the sodium-iodide symporter (NIS). In this analysis, a six-step framework for PBPK model evaluation was followed, and with a few modifications, the models were determined to be suitable for use in HHRA to evaluate relative sensitivity among human lifestages. Relative sensitivity to perchlorate was determined by comparing the PBPK model predicted percent inhibition of thyroidal radioactive iodide uptake (RAIU) by perchlorate for different lifestages. A limited sensitivity analysis indicated that model parameters describing urinary excretion of perchlorate and iodide were particularly important in prediction of RAIU inhibition; therefore, a range of biologically plausible values available in the peer-reviewed literature was evaluated. Using the updated PBPK models, the greatest sensitivity to RAIU inhibition was predicted to be the near-term fetus (gestation week 40) compared to the average adult and other lifestages; however, when exposure factors were taken into account, newborns were found to be populations that need further evaluation and consideration in a risk assessment for perchlorate.

Design of Caprock Integrity in Thermal Stimulation of Shallow Oil-Sands Reservoirs

Summary Stakeholders in in-situ oil-sands development take caprock-integrity issues seriously. The industry is faced with the challenge of determining an optimal operating pressure in the reservoir where, in general, the pressure should stay significantly low to ensure the caprock integrity while being significantly high for enhanced oil production and economics. This paper presents a comprehensive work program on the subject for a shallow oil-sands play. Caprock integrity considers the induced stress and deformation in a caprock during the thermal stimulation of an oil-sands reservoir. A minifrac-test program is undertaken to define the original in-situ stress state. Laboratory tests are carried out to measure the deformation and strength properties. Simulations are run to calculate the induced stresses and evaluate them against the mechanical strength. This paper describes some important quality-control issues for these activities. For the minifrac tests, multiple cycles and use of flowback are promoted for enhanced efficiency and accuracy. Laboratory tests are recommended on whole cores in a drained condition at a slow strain rate. Numerical simulations should use site-specific and laboratory-measured material properties. On the basis of the limited sensitivity analyses, the thermal expansion coefficient of the reservoir and Young's modulus of the caprock are found to significantly affect the caprock deformation and/or induced stresses.

Time-Series Analyses of Air Pollution and Mortality in the United States: A Subsampling Approach

Background: Hierarchical Bayesian methods have been used in previous papers to estimate national mean effects of air pollutants on daily deaths in time-series analyses.Objectives: We obtained maximum likelihood estimates of the common national effects of the criteria pollutants on mortality based on time-series data from ≤ 108 metropolitan areas in the United States.Methods: We used a subsampling bootstrap procedure to obtain the maximum likelihood estimates and confidence bounds for common national effects of the criteria pollutants, as measured by the percentage increase in daily mortality associated with a unit increase in daily 24-hr mean pollutant concentration on the previous day, while controlling for weather and temporal trends. We considered five pollutants [PM10, ozone (O3), carbon monoxide (CO), nitrogen dioxide (NO2), and sulfur dioxide (SO2)] in single- and multipollutant analyses. Flexible ambient concentration–response models for the pollutant effects were considered as well. We performed limited sensitivity analyses with different degrees of freedom for time trends.Results: In single-pollutant models, we observed significant associations of daily deaths with all pollutants. The O3 coefficient was highly sensitive to the degree of smoothing of time trends. Among the gases, SO2 and NO2 were most strongly associated with mortality. The flexible ambient concentration–response curve for O3 showed evidence of nonlinearity and a threshold at about 30 ppb.Conclusions: Differences between the results of our analyses and those reported from using the Bayesian approach suggest that estimates of the quantitative impact of pollutants depend on the choice of statistical approach, although results are not directly comparable because they are based on different data. In addition, the estimate of the O3-mortality coefficient depends on the amount of smoothing of time trends.

Effect of Oil Composition on Chemical Dispersion of Crude Oil

Effects of oil composition on dispersion effectiveness (defined as the mass fraction of oil entrained as droplets in the water column) and droplet-size distribution were investigated using baffled-flask mixing systems. The composition of oil samples used in dispersion experiments was systematically manipulated by varying the relative concentrations of the saturates, aromatics, resins, and asphaltenes (SARA) fractions. Forward stepwise linear regression was used with a generalized linear model that included main effects and two-factor interactions to evaluate the effects of oil composition on chemical dispersion. Limited sensitivity analysis was used to determine whether the significant effects were strongly dependent on the specific combination of responses observed in these experiments or insensitive to small changes within the range of variation that was observed. The concentration of the aromatics fraction and the saturates–resins interaction exerted statistically significant, positive effects on dispersion effectiveness (p<0.05). Regardless of composition, the droplet-size distributions observed in these experiments were multimodal consisting of small- (<7 μm), medium- (7–20 μm), and large-sized (>20 μm) droplets. Higher concentrations of the saturates fraction favored the entrainment of floating oil as small and medium-sized droplets, whereas the aromatics–asphaltenes interaction reduced the amount of oil present as small droplets. Aromatics–asphaltenes interaction increased the overall diameter of mean volume (DMV) of the dispersed oil droplets, and the saturates–asphaltenes interaction reduced it.

Calibração de modelo para a simulação de vazão e de fósforo total nas sub-bacias dos Rios Conrado e Pinheiro - Pato Branco (PR)

O desenvolvimento de modelos hidrológicos capazes de predizer o impacto de fontes difusas de poluição e do uso e ocupação do solo na qualidade das águas superficiais e subterrâneas tem auxiliado o estudo de agroecossistemas. Com esse objetivo, foi utilizado o modelo SWAT 2005 (Soil and Water Assessment Tool) para avaliar sua sensibilidade na predição da vazão e do fluxo de massa do P total. O estudo foi realizado em duas microbacias hidrográficas contíguas, dos rios Conrado e Pinheiro, afluentes do rio Pato Branco, localizadas nos municípios de Pato Branco e Mariópolis, no Estado do Paraná. Foram utilizados dados climatológicos do período 1979/2006 e dados observados de vazão e concentração de P total dos anos 2004/2005 de duas estações de monitoramento, localizadas na parte inferior do curso principal dos rios Conrado e Pinheiro. Utilizou-se a interface AvSWAT-X, com o SIG ArcView 3.3® e a extensão Spatial Analyst 2.0®, para entrada e manipulação dos dados. As médias anuais e mensais observadas de vazão e P total foram comparadas aos dados simulados. O Coeficiente de Eficiência de Nash-Sutcliffe (COE) foi utilizado para avaliar a eficiência do modelo. A modelagem foi melhorada com a associação de análise de sensibilidade, autocalibração e calibração manual, verificando-se que, com frequência de amostragem regular, o modelo SWAT 2005 realizou de forma aceitável as simulações de vazão e de exportação de P total. Já com frequência de amostragem irregular e pequeno número de dados, os procedimentos de análise de sensibilidade e de autocalibração não foram eficientes na calibração do modelo SWAT 2005 para a simulação de vazão e exportação de P total. Foram encontrados diferentes níveis de sensibilidade entre as duas estações, refletindo as desigualdades entre as Unidades de Resposta Hidrológica. A distribuição mensal simulada das exportações de P mostrou a heterogeneidade da aplicação do nutriente ao longo do ano.

A Designed Screening Study with Prespecified Combinations of Factor Settings

ABSTRACT In many applications, the experimenter has limited options about what factor combinations can be chosen for a designed study. Consider a screening study for a production process involving five input factors whose levels have been previously established. The goal of the study is to understand the effect of each factor on the response, a variable that is expensive to measure and results in destruction of the part. From an inventory of available parts with known factor values, we wish to identify a best collection of factor combinations with which to estimate the factor effects. Though the observational nature of the study cannot establish a causal relationship involving the response and the factors, the study can increase understanding of the underlying process. The study can also help determine where investment should be made to control input factors during production that will maximally influence the response. Because the factor combinations are observational, the chosen model matrix will be nonorthogonal and will not allow independent estimation of factor effects. In this manuscript we borrow principles from design of experiments to suggest an “optimal” selection of factor combinations. Specifically, we consider precision of model parameter estimates, the issue of replication, and abilities to detect lack of fit and to estimate two-factor interactions. Through an example, we present strategies for selecting a subset of factor combinations that simultaneously balance multiple objectives, conduct a limited sensitivity analysis, and provide practical guidance for implementing our techniques across a variety of quality engineering disciplines.