Search NASA⌕ Search

SEARCH · Search NASA

Results for “small sample size”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS1984

Statistical Analysis Techniques for Small Sample Sizes

The small sample sizes problem which is encountered when dealing with analysis of space-flight data is examined. Because of such a amount of data available, careful analyses are essential to extract the maximum amount of information with acceptable accuracy. Statistical analysis of small samples is described. The background material necessary for understanding statistical hypothesis testing is outlined and the various tests which can be done on small samples are explained. Emphasis is on the underlying assumptions of each test and on considerations needed to choose the most appropriate test for a given type of analysis.

Navard, S. E.↗
NASA NTRSDate not supplied

Assessing Risk Due to Small Sample Size in Probability of Detection Analysis Using Tolerance Intervals

Small sample size (e.g.6-30) poses risk in results of probability of detection (POD) analysis using tolerance intervals. This method is also called as the limited sample or LS POD. The analysis is performed either during NDE procedure qualification or for assessment of reliability of an NDE procedure. The risk is primarily due to sampling error. Smaller samples are not likely to be random to the population or representative of the population. The small samples are likely to be biased. Biased samples have smaller standard deviation compared to the population. POD analysis with small biased sample can lead to overestimation of POD. Many sampling schemes are available in statistics to mitigate sampling risk. Primary objective of POD analysis is to determine a decision threshold from signal response measurements of a sample such that it is less than or equal to population decision threshold for 90% POD. Sampling error implies that this NDE reliability condition is violated. One of sampling types is called a representative sample. Representative samples reduce variance in POD estimates but also reduce magnitude of the error. Sampling sensitivity analysis for some sampling types is performed here using repetitive random sampling or Monte Carlo method. Six sampling types are considered for comparison. Some of the sampling types are similar to drawing a representative sample. LS POD model assumes random sampling. Therefore, random sampling is used as a basis for comparison with each sampling type. The sampling types used in the analysis are, A. Nominal and worst-case sampling, B. Worst-case sampling, C. Nominal case sampling, D. Random sampling, E. Random target, and sub-target sampling. F. Nominal target and sub-target sampling. Results of Monte Carlo simulation indicate that type F sampling can mitigate sampling risk and is also more practical to implement. Type A sampling may also mitigate the sampling risk, but it may be less practical to implement.

Ajay M Koshti↗
DOE OSTI2016

Global Sensitivity Analysis with Small Sample Sizes: Ordinary Least Squares Approach

A new version of global sensitivity analysis is developed in this paper. This new version coupled with tools from statistics, machine learning, and optimization can devise small sample sizes that allow for the accurate ordering of sensitivity coefficients for the first 10-30 most sensitive chemical reactions in complex chemical-kinetic mechanisms, and is particularly useful for studying the chemistry in realistic devices. A key part of the paper is calibration of these small samples. Because these small sample sizes are developed for use in realistic combustion devices, the calibration is done over the ranges of conditions in such devices, with a test case being the operating conditions of a compression ignition engine studied earlier. Compression ignition engines operate under low-temperature combustion conditions with quite complicated chemistry making this calibration difficult, leading to the possibility of false positives and false negatives in the ordering of the reactions. So an important aspect of the paper is showing how to handle the trade-off between false positives and false negatives using ideas from the multiobjective optimization literature. The combination of the new global sensitivity method and the calibration are sample sizes a factor of approximately 10 times smaller than were available with our previous algorithm.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2014

Comparing Server Energy Use and Efficiency Using Small Sample Sizes

This report documents a demonstration that compared the energy consumption and efficiency of a limited sample size of server-type IT equipment from different manufacturers by measuring power at the server power supply power cords. The results are specific to the equipment and methods used. However, it is hoped that those responsible for IT equipment selection can used the methods described to choose models that optimize energy use efficiency. The demonstration was conducted in a data center at Lawrence Berkeley National Laboratory in Berkeley, California. It was performed with five servers of similar mechanical and electronic specifications; three from Intel and one each from Dell and Supermicro. Server IT equipment is constructed using commodity components, server manufacturer-designed assemblies, and control systems. Server compute efficiency is constrained by the commodity component specifications and integration requirements. The design freedom, outside of the commodity component constraints, provides room for the manufacturer to offer a product with competitive efficiency that meets market needs at a compelling price. A goal of the demonstration was to compare and quantify the server efficiency for three different brands. The efficiency is defined as the average compute rate (computations per unit of time) divided by the average energy consumption rate. The research team used an industry standard benchmark software package to provide a repeatable software load to obtain the compute rate and provide a variety of power consumption levels. Energy use when the servers were in an idle state (not providing computing work) were also measured. At high server compute loads, all brands, using the same key components (processors and memory), had similar results; therefore, from these results, it could not be concluded that one brand is more efficient than the other brands. The test results show that the power consumption variability caused by the key components as a group is similar to all other components as a group. However, some differences were observed. The Supermicro server used 27 percent more power at idle compared to the other brands. The Intel server had a power supply control feature called cold redundancy, and the data suggest that cold redundancy can provide energy savings at low power levels. Test and evaluation methods that might be used by others having limited resources for IT equipment evaluation are explained in the report.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Spatio-Temporal Surrogates for Interaction of a Jet with High Explosives: Part I - Analysis with a Small Sample Size

Computer simulations, especially of complex phenomena, can be expensive, requiring high-performance computing resources. Often, to understand a phenomenon, multiple simulations are run, each with a different set of simulation input parameters. These data are then used to create an interpolant, or surrogate, relating the simulation outputs to the corresponding inputs. When the inputs and outputs are scalars, a simple machine learning model can suffice. However, when the simulation outputs are vector valued, available at locations in two or three spatial dimensions, often with a temporal component, creating a surrogate is more challenging. In this report, we use a two-dimensional problem of a jet interacting with high explosives to understand how we can build high-quality surrogates. The characteristics of our data set are unique - the vector-valued outputs from each simulation are available at over two million spatial locations; each simulation is run for a relatively small number of time steps; the size of the computational domain varies with each simulation; and resource constraints limit the number of simulations we can run. We show how we analyze these extremely large data-sets, set the parameters for the algorithms used in the analysis, and use simple ways to improve the accuracy of the spatio-temporal surrogates without substantially increasing the number of simulations required.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Small-Sample Estimator Decisions – Certainly Uncertain in Human Spaceflight at NASA

Within statistics when estimating means, we rely heavily on the Central Limit Theorem (CLT) to aid in our inference, however in cases where the CLT does not apply we begin to be strongly limited in our choices. If a violation to the CLT comes in the form of small samples and unknown population variance, yet we maintain the assumption of normality, the use of t-distributions is perfectly valid. We explore cases where population normality is not assumed, where sample sizes are small, and where some actionable estimate of the central tendency of a distribution is needed such as for spaceflight operational decisions. Here we identify different scenarios based on measures taken from spaceflight, characterizing performance of estimators of central tendency within our set of simulations. We examine bias and variability of standard estimators of central tendency as they apply to varying small sample sizes and varying population distributions. Further work in this area is needed to develop a framework or set of guidelines for individuals set in these situations. Even with limited information, decisions need to be made.

Central Tendency↗
NASA NTRS1995

Designing for Small Volume Assembly of Advanced Electronics Packages

We describe a general methodology to Design for Producibility and Reliability (DFPAR) for very small volume production runs. In cases where the entire volume for fabrication is less than five products, traditional Statistical Process Control (SPC) is inadequate due to reliance on statistics of much larger volumes and the Central Limit Theorem. Data acquisition for process parameter estimation from such a small sample size is difficult; however, it is critical to producing high reliability product.

Central Limit Theorem statistics high reliability ↗
DOE OSTI2017

Improvements to sample processing and measurement to enable more widespread environmental application of tritium

Previous measurements have demonstrated the wealth of information that tritium (T) can provide on environmentally relevant processes. We present modifications to sample preparation approaches that enable T measurement by proportional counting on small sample sizes equivalent to 120 mg of water and demonstrate the accuracy of these methods on a suite of standardized water samples. This enhanced method should provide the analytical flexibility needed to address persistent knowledge gaps in our understanding of T behavior in the environment.

low background↗
DOE OSTI2017

Is There a Disk of Satellites around the Milky Way?

The “disk of satellites” (DoS) around the Milky Way is a highly debated topic with conflicting interpretations of observations and their theoretical models. We perform a comprehensive analysis of all of the dwarfs detected in the Milky Way and find that the DoS structure depends strongly on the plane identification method and the sample size. In particular, we demonstrate that a small sample size can artificially produce a highly anisotropic spatial distribution and a strong clustering of the angular momentum of the satellites. Moreover, we calculate the evolution of the 11 classical satellites with proper motion measurements and find that the thin DoS in which they currently reside is transient. Furthermore, we analyze two cosmological simulations using the same initial conditions of a Milky-Way-sized galaxy, an N -body run with dark matter only, and a hydrodynamic one with both baryonic and dark matter, and find that the hydrodynamic simulation produces a more anisotropic distribution of satellites than the N -body one. Our results suggest that an anisotropic distribution of satellites in galaxies can originate from baryonic processes in the hierarchical structure formation model, but the claimed highly flattened, coherently rotating DoS of the Milky Way may be biased by the small-number selection effect. These findings may help resolve the contradictory claims of DoS in galaxies and the discrepancy among numerical simulations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Solving the sample size problem for resource selection functions

Abstract Sample size sufficiency is a critical consideration for estimating resource selection functions (RSFs) from GPS‐based animal telemetry. Cited thresholds for sufficiency include a number of captured animals and as many relocations per animal N as possible. These thresholds render many RSF‐based studies misleading if large sample sizes were truly insufficient, or unpublishable if small sample sizes were sufficient but failed to meet reviewer expectations. We provide the first comprehensive solution for RSF sample size by deriving closed‐form mathematical expressions for the number of animals M and the number of relocations per animal N required for model outputs to a given degree of precision. The sample sizes needed depend on just 3 biologically meaningful quantities: habitat selection strength, variation in individual selection and a novel measure of landscape complexity, which we define rigorously. The mathematical expressions are calculable for any environmental dataset at any spatial scale and are applicable to any study involving resource selection (including sessile organisms). We validate our analytical solutions using globally relevant empirical data including 5,678,623 GPS locations from 511 animals from 10 species (omnivores, carnivores and herbivores living in boreal, temperate and tropical forests, montane woodlands, swamps and Arctic tundra). Our analytic expressions show that the required M and N must decline with increasing selection strength and increasing landscape complexity, and this decline is insensitive to the definition of availability used in the analysis. Our results demonstrate that the most biologically relevant effects on the utilization distribution (i.e. those landscape conditions with the greatest absolute magnitude of resource selection) can often be estimated with much fewer than animals. We identify several critical steps in implementing these equations, including (a) a priori selection of expected model coefficients and (b) regular sampling of background (pseudoabsence) data within a given definition of availability. We discuss possible methods to identify a priori expectations for habitat selection coefficients, effects of scale on RSF estimation and caveats for rare species applications. We argue that these equations should be a mandatory component for all future RSF studies.

Street, Garrett M.↗
DOE OSTI2024

On the uncertainty of long-period return values of extreme daily precipitation

Methods for calculating return values of extreme precipitation and their uncertainty are compared using daily precipitation rates over the Western U.S. and Southwestern Canada from a large ensemble of climate model simulations. The roles of return-value estimation procedures and sample size in uncertainty are evaluated for various return periods. We compare two different generalized extreme value (GEV) parameter estimation techniques, namely L-moments and maximum likelihood (MLE), as well as empirical techniques. Even for very large datasets, confidence intervals calculated using GEV techniques are narrower than those calculated using empirical methods. Furthermore, the more efficient L-moments parameter estimation techniques result in narrower confidence intervals than MLE parameter estimation techniques at small sample sizes, but similar best estimates. It should be noted that we do not claim that either parameter fitting technique is better calibrated than the other to estimate long period return values. While a non-stationary MLE methodology is readily available to estimate GEV parameters, it is not for the L-moments method. Comparison of uncertainty quantification methods are found to yield significantly different estimates for small sample sizes but converge to similar results as sample size increases. Finally, practical recommendations about the length and size of climate model ensemble simulations and the choice of statistical methods to robustly estimate long period return values of extreme daily precipitation statistics and quantify their uncertainty.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Compact X-band split electron linac for cabinet-size small-sample irradiators

Many small-scale industrial radiation facilities rely on hazardous radioisotope-based gamma ray irradiators, which are being gradually replaced by alternative technologies, such as particle accelerators. RadiaBeam has developed a compact, cabinet-size, 3 MeV electron-linac-based irradiator to match the penetration of Co-60 and provide high irradiation throughput. Here the linac utilizes X-band RF power to reduce size, employs an innovative split-linac approach to lower costs, and features a novel X-ray conversion target geometry that spreads the beam out across the target, providing a low dose uniformity ratio. In this paper, we discuss the accelerator design, fabrication, and test results.

43 PARTICLE ACCELERATORS↗
DOE OSTI2026

Data for "Quantifying the Propagation of Parametric Uncertainty on Flux Balance Analysis"

In the repository are example scripts that perform uncertainty injection and propagation to flux balance analysis with outputs for a small sample size (for demonstration purpose only). For proper analysis, user should download the scripts and run for a large sample size (e.g., 10,000 samples). If you use the scripts, please cite the following Metabolic Engineering article: “Quantifying the propagation of parametric uncertainty on flux balance analysis” (https://doi.org/10.1016/j.ymben.2021.10.012) There are two subdirectories: /uncFBA/uncBiom: injection of normally distributed noise to biomass precursor coeffcients and ATP maintenance (growth-associated ATP maintenance (GAM) and non-growth associated ATP maintenance (NGAM)) /uncFBA/uncRHS: departure from steady-state by adding noise drawn from normal distribution to the RHS terms of mass balance constraints

Metabolomics↗
DOE OSTI2015

Development of a broadband reflectivity diagnostic for laser driven shock compression experiments

Here, a normal-incidence visible and near-infrared shock wave optical reflectivity diagnostic was constructed to investigate changes in the optical properties of materials under dynamic laser compression. Documenting wavelength- and time-dependent changes in the optical properties of laser-shock compressed samples has been difficult, primarily due to the small sample sizes and short time scales involved, but we succeeded in doing so by broadening a series of time delayed 800-nm pulses from an ultrafast Ti:sapphire laser to generate high-intensity broadband light at nanosecond time scales. This diagnostic was demonstrated over the wavelength range 450–1150 nm with up to 16 time displaced spectra during a single shock experiment. Simultaneous off-normal incidence velocity interferometry (velocity interferometer system for any reflector) characterized the sample under laser-compression and also provided an independent reflectivity measurement at 532 nm wavelength. The shock-driven semiconductor-to-metallic transition in germanium was documented by the way of reflectivity measurements with 0.5 ns time resolution and a wavelength resolution of 10 nm.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2022

U Metal Oxidation with Steam (U)

The Savannah Rive National Laboratory 9SRNL) is evaluating a method to produce uranium oxide (UO 2 ) from uranium metal using steam. The typical methods for making UO 2 yield powders with particle-size ranges of 1 to 50 micron. The goal of the steam oxidation is to produce a depleted uranium (DU) product with a larger particle size that can be used as a surrogate for testing physical and mechanical process techniques to refine uranium and/or plutonium bearing residues. Several studies in the literature indicated that reactions between uranium metal and steam will yield UO 2 as fine powders in the 160 to 500 °C range, but granular materials form above 500°C. Above 880 °C, a hard compact scale forms on the U metal. Furthermore, sintering of UO 2 occurs at about 1300 °C, but it has been stated that the presence of steam enhances the sintering characteristics of UO 2 . Initial studies into the oxidation of DU metal in an atmosphere of argon and steam have been completed. Oxidation of depleted uranium metal in Ar/steam at 600, 710, 700, and 830 °C yielded at UO 2 product with little or no impurity at each temperature. Although not enough sample was available to perform sieve analysis for particle size distribution, SEM images reveal that a significant volume fraction of the products at 710, 770, and 830 °C exceeds 100 microns. The material produced at 600 °C was too fine for programmatic needs. Questions associated with the UO 2 include morphology of product, mechanical strength of the particles, and performance in milling operations. The size of the samples produced in these tests did not allow for quantitative assessment of particle size of mechanical strength. A qualitative assessment of the particles formed at 710, 770, and 830 °C was that the samples produced at 710 and 770 °C were friable, and the sample produced 830 °C had more mechanical strength. Sintering of the samples in Ar/steam at 970 °C appeared to increase the strength of the particles without changing their general particle size characteristics. Due to the small sample sizes, the increase in strength could not be quantified. If the sintering at 970 °C is inadequate, higher sintering temperatures in Ar/steam can be evaluated. Future work will increase scale of the steam oxidation conditions which yield the most-favorable particle-size distributions with sufficient mechanical strength for programming usage. Further consideration will be given to oxidation temperature, steam addition to the reaction vessel, U metal pretreatment, and sintering conditions after oxidation. The UO 2 production could involve a two-step process where particles are formed in steam at lower temperatures (700-850 °C) and then sintered in Ar/steam at elevated temperatures (950-1200 °C). Larger samples (50-100 g each) will provide sufficient UO 2 product for sieve analysis and assessment of mechanical strength relatives to subsequent milling operations.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
NASA NTRS1976

On the role of dimensionality and sample size for unstructured and structured covariance matrix estimation

The experimental observation that a surprisingly small sample size vis-a-vis dimension is needed to achieve good signal-to-interference ratio (SIR) performance with an adaptive predetection filter is explained. The adaptive filter requires estimates as obtained by a recursive stochastic algorithm of the inverse of the filter input data covariance matrix. The SIR performance with sample size is compared for the situations where the covariance matrix estimates are of unstructured (generalized) form and of structured (finite Toeplitz) form; the latter case is consistent with weak stationarity of the input data stochastic process.

Morgera, S. D.↗