Showing papers on "Sampling (statistics) published in 1970"
10,457 citations
TL;DR: In this paper, the authors present a survey of laboratory equipment and techniques, including glassware and other containers, chemicals and solutions, as well as their application in field safety and first aid.
Abstract: ................................................................................................. Introduction ......................................................................................... Part I. Sampling............................................................................ Site selection............................................................................. Surface water............................................................. Rivers and streams................................... Lakes and reservoirs........................... Ground water........................................................... . Frequency ................................................................................... Surface water.............................................................. Ground water.............................................................. Equipment ................................................................................ Containers .................................................................... Shipping cases..................... .................................... Samplers ......................................................................... Depth-integrating ..................................... Point ...................................................................... Special ................................................................ Accessories ....................................................... Identification and records........................................... Field safety and first aid......................................... Sample collection and treatment ..................... References ................................................................................ Part II. Laboratory equipment and techniques.. Glassware and other containers........................ Chemicals and solutions .............................................. Purity ............................................................................... Standard solutions.... ............................................. Nonstandard solutions........................................ Accuracy of measurement............................ Instrumental techniques......... ..................................... Visible and ultraviolet spectrophotometry ............................................................. Sensitivity ....................................................... Interferences .................................................. Emission and atomic-absorption flame spectrophotometry ........................................ Analytical procedures........................... Direct method..................................... Chelation-extraction method Standard-addition method .... Internal-standard method......... Interferences ................................................. lonization effects............................. Chemical effects............................... Matrix effects...................................... Spectral line effects...................... Polarography ............................................................. Interferences .................................................. pH ........................................................................................ Turbidity ...................................................................... Specific conductance........ .................................. Page
519 citations
TL;DR: In this article, the authors derived optimal strategies involving linear estimators under certain variance assumptions and compared them under various assumptions under a superpopulation model, and showed that the conventional ratio estimator is, in a certain natural sense, optimal.
Abstract: SUMMARY Problems of estimating totals in finite populations, when auxiliary information regarding variate values is available, are considered under some linear regression, 'super-population', models. Optimal strategies involving linear estimators are derived under certain variance assumptions and compared under various assumptions. For a model which seems to apply in many practical problems, the conventional ratio estimator is shown to be, in a certain natural sense, optimal, but for all models considered, the optimal sampling plans are purposive, i.e. nonrandom. With a squared error loss function, the strategy of using a probability proportional to size sampling plan and the Horvitz-Thompson estimator is shown to be inadmissible in many models for which the strategy seems 'reasonable' and in a particular model for which it is, in one sense, optimal. Some of the results concerning purposive sampling and the ratio estimator are supported by an empirical study.
393 citations
01 Feb 1970
TL;DR: The kinds of information obtainable from sample signatures are described, and considerations for developing algorithms based on such information are discussed, and a tutorial section is included for the purpose of giving the reader an intuitive feeling for the kinds of Information contained in a diffraction pattern and how it relates to the original photographic imagery.
Abstract: This paper describes diffraction-pattern sampling as a basis for automatic pattern recognition in photographic imagery; it covers: diffraction-pattern generation, diffraction-pattern/image-area relationships, diffraction-pattern sampling, algorithm development (using an interactive computer-graphic based facility), facility description, and experimental results which have been obtained over the last few years at General Motors' AC Electronics-Defense Research Laboratories, Santa Barbara, Calif. Sampling the diffraction pattern results in a sample signature--a different one for each sampling geometry. The kinds of information obtainable from sample signatures are described, and considerations for developing algorithms based on such information are discussed. A tutorial section is included for the purpose of giving the reader an intuitive feeling for the kinds of information contained in a diffraction pattern and how it relates to the original photographic imagery.
223 citations
Book•
01 Jun 1970
TL;DR: This chapter discusses estimation in measurement and sampling models, and discusses the role of significance in estimation, which plays in the development of statistical models.
Abstract: Preface Part I. Probability: 1. Probability models 2. Sampling 3. Product models 4. Conditional probability 5. Random variables 6. Special distributions 7. Multivariate distributions Part II. Statistics. Introduction to Statistics: 8. Estimation 9. Estimation in measurement and sampling models 10. Optimum methods of estimation 11. Tests of significance 12. Tests for comparative experiments 13. Concept of power Tables Selected answers to problems Index Example index.
145 citations
TL;DR: It is shown that any spectrum whatsoever can be recovered if \{t_n\} is a Poisson point process on the positive (or negative) half-axis and randomly jittered sampling at the Nyquist rate is alias free.
Abstract: The notion of alias-free sampling is generalized to apply to random processes x(t) sampled at random times t_n ; sampling is said to be alias free relative to a family of spectra if any spectrum of the family can be recovered by a linear operation on the correlation sequence \{r(n)\} , where r(n) = E[x(l_{m+n}) \overline{x(t_m)}] . The actual sampling times t_n need not be known to effect recovery of the spectrum of x(t) . Various alternative criteria for verifying alias-free sampling are developed. It is then shown that any spectrum whatsoever can be recovered if \{t_n\} is a Poisson point process on the positive (or negative) half-axis. A second example of alias-free sampling is provided for spectra on a finite interval by periodic sampling (for t \leq t_o or t \geq t_o ) in which samples are randomly independently skipped (expunged), such that the average sampling rate is an arbitrarily small fraction of the Nyquist rate. A third example shows that randomly jittered sampling at the Nyquist rate is alias free. Certain related open questions are discussed. These concern the practical problems involved in estimating a spectrum from imperfectly known \{ r(n) \} .
137 citations
TL;DR: In this article, a distinction is made between drift rate and drift density (the number of invertebrates passing a sampling point in unit time) and the relationship between the two variables can be expressed by a regression line.
Abstract: The first part of the paper reviews and criticises drift samplers. The samplers are divided into three broad categories: 1. Samplers without flow-meters (Fig. 1). 2. Samplers with flow-meters (Fig. 2). 3. Tube samplers (Fig. 3) and other more complex samplers. The second part of the paper considers some problems associated with drift sampling. As the volume of water flowing through a drift sampler increases, the size of the catch increases. The average relationship between the two variables can be expressed by a regression line (e.g. Fig. 5). A distinction is made between drift rate (the number of invertebrates passing a sampling point in unit time) and drift density (the number of invertebrates per unit volume of water). The relationship between drift rate and drift density is discussed. A summary is given of all the factors which affect drift density. The sampling efficiency of drift samplers is discussed, and the results of efficiency tests are described. As the performance and sampling efficiency of a drift sampler vary with local stream conditions, they must be thoroughly tested before the start of regular drift sampling. The study of the diel periodicity in invertebrate drift is discussed. The diel drift pattern greatly varies when different sampling periods are used (Fig. 6). The following statistical problems are discussed: 1. Temporal and spatial variations in drift rate and drift density, using Poisson series as a statistical model. 2. The estimation of total numbers drifting downstream. Total drift is estimated from drift rate when agreement with a Poisson series is accepted for samples across the stream. Total drift is estimated from drift density when agreement with a Poisson series is rejected, and the catches in a series of nets are proportional to the volumes of water sampled by the nets.
118 citations
TL;DR: The paper shows that Line's technique for correcting the ‘apparent’ half‐life is both questionable and impractical, and that a further factor—the growth of the number of contributors—needs to be allowed for in Vickery's analysis.
Abstract: Line's recently proposed technique for correcting the ‘apparent’ half‐life to allow for the rate of growth of the literature and Vickery's critical analysis of the proposal are both further analysed. Using the concept of utility and considering the sampling variances involved, the paper shows that Line's technique is both questionable and impractical, and that a further factor—the growth of the number of contributors—needs to be allowed for in Vickery's analysis. A collaborative empirical investigation is proposed.
85 citations
01 Jan 1970
TL;DR: In this paper, the relationship relationship between the strength and density of some types of rock and their relative robustness is discussed. But the relationship between these properties and the strength of the rock is not discussed.
Abstract: EQUATIONS DESCRIBING CORRELATION RELATIONSHIP BETWEEN ULTIMATE COMPRESSIVE STRENGTH OF SOME TYPES OF ROCK AND THEIR DENSITY AND POROSITY ARE GIVEN. THESE EQUATIONS PERMIT EVALUATING THE STRENGTH PROPERTIES OF ROCKS WITHOUT SAMPLING. THE VALUES OF ROCK DENSITY NEEDED FOR CALCULATIONS CAN BE DETERMINED BY USE OF SUBSURFACE NUCLEAR DEVICES DURING THE ENGINEERING INVESTIGATIONS. /AUTHOR/
82 citations
TL;DR: None of several samplers compared in limited tests in Lake Ontario gave realistic estimates of benthos in all substrates encountered, and there were indications that the tall Ekman grab was either not tall enough or too heavily weighted for use in soft sediments and that a small improvement in design could make both this an improvement.
Abstract: None of several samplers compared in limited tests in Lake Ontario gave realistic estimates of benthos in all substrates encountered. The Ponar and Shipek grabs, the only samplers that functioned i...
82 citations
Patent•
14 Sep 1970
TL;DR: Automatic sampling and reading equipment and methods for use in supplying biological samples to an automatic analyzer and correlating test results from the automated analyzer with the identity of the patient providing each sample are described in this paper.
Abstract: Automatic sampling and reading equipment and methods for use in supplying biological samples to an automatic analyzer and in correlating test results from the automatic analyzer with the identity of the patient providing each sample. The equipment successively indexes a tray of containers each having a biological specimen therein first to a sampling station where a probe withdraws a sample comprising a desired amount of specimen and later to a reading station where an encoded identification plate affixed to the adjacent container is electronically read. The reader at the reading station experiences relative displacement in respect to the identification plate being read, caused by the operation of a drive assembly, and hold-down or guard assembly is provided to insure an accurate reading during the indicated displacement. Withdrawn samples, separated by segments of air, water, and air, are delivered seriatim to the automatic analyzer which tests each sample. An output of the test results from the automatic analyzer in the form of a strip chart is correlated with a print out of the patient identification indicia sensed at the reading station so that the results of the tests are properly related back to the correct patient from whom a given specimen was originally taken. The probe is periodically purged, flushed or cleansed of residual sample by expelling water from the tip thereof into a discharge basin. Clean water is simultaneously displaced to the analyzer between samples, being insulated by air on each side as previously indicated. A mechanism is provided for discharging any clot or clogs from the probe which are experienced during operation of the sampling equipment. Also, a liquid level detector properly locates the probe in the sample.
TL;DR: In contrast to the relatively manageable situation of balanced data, the estimation of variance components from unbalanced data, of which balanced data are deemed to be simply a special case, has been studied in this paper.
Abstract: Estimation of variance components from data that are unbalanced (having unequal numbers of observations in the subclasses) has been referred to by Hartley [1967] as involving 'algebraic heroics.' Obtaining sampling variances can be described similarly. There is little or no difficulty with balanced data because then, with customary normnality assumptions, the sums of squares of an analysis of variance have independent X2-distributions, variance component estimators are linear functionis of these, and their variances are readily derived. Furthermore, as Graybill and Hultquist [1961] point out, these estimators (which are unbiased) also have minimum variance properties. In contrast to the relatively manageable situation of balanced data we consider here the estimation of variance components from unbalanced data, of which balanced data are deemed to be simply a special case. In particular we deal with the sampling variances of large sample maximum likelihood (ML) estimators. Before doing so, a brief review of the present status of sampling variances of other estimators is in order. For random (and mixed) models Henderson [1953] developed three methods of estimating variance components from unbalanced data of any crossed and/or nested classifications, the techniques of which have been further discussed in Searle [1968]. Sampling variances of the resulting estimators have been developed extensively for only one of these methods, Method 1, that is analogous to the analysis of variance method for balanced data. Furthermore, in all cases, sampling variances have been considered only in the case of random effects models (Model II of Eisenhart [1947]), and only on the basis of having normality assumptions as part of such models. Within
TL;DR: In this paper, a play-the-winner (PW) sampling rule was proposed for selecting the better binomial population with probability P* when the two singletrial probabilities of success, p and p', differ by at least A* where P* and i* are prescribed.
Abstract: The sequential allocation of treatments by an experimenter is considered for determining which of two binomial populations has the larger probability of success. Of particular interest in this study is a 'Play-the-Winner' (PW) sampling rule which prescribes that one continues with the same population after each success and one switches to the opposite population after each failure. The performance of the PW rule is examined for the selection problem, i.e. for selecting the better population with probability P* when the two singletrial probabilities of success, p and p', differ by at least A*, where P* and i\* are prescribed. A comparison is made between PW sampling and 'Vector-at-a-Time' (VT) sampling. In comparing results a criterion used is the expected number of failures that could have been avoided by using the better population throughout. It is shown for a particular common termination rule that with A* close to zero the PW sampling is superior to VT sampling if and only if I (p +p') > J. Other comparisons are also discussed.
TL;DR: In this paper, the Q-switched laser sampling of copper-zinc alloys has been investigated, where both vapor and liquid metal were produced in the sampling process, and it was demonstrated that the melting step was thermally equilibrated.
Abstract: A more detailed knowledge than is presently available of laser beam–target material interactions is required if pulsed lasers are to be used with maximum effectiveness as analytical sampling devices. To this end. the Q-switched laser sampling of copper–zinc alloys has been investigated. Both vapor and liquid metal were produced in the sampling process. Observations of the crater dimensions and appearance showed that ablation of molten metal was the predominant material removal mode. It was demonstrated that the melting step was thermally equilibrated. Vaporization proceeded via a sequence of events wherein the vapor composition was independent of laser parameters, and could be predicted from the liquid-solid equilibrium diagram for the copper–zinc system. The effect of laser sampling on a subsequent chemical analysis is illustrated.
TL;DR: In this article, it is hypothesized that the spatial occurrence of petroleum reservoirs can be represented by a Poisson process and that the sizes of the individual reservoirs are lognormally distributed.
Abstract: It is hypothesized that the spatial occurrence of petroleum reservoirs can be represented by a Poisson process and that the sizes of the individual reservoirs are lognormally distributed. The total petroleum reserves occurring in any unit of space of arbitrary size within a region can thus be represented as a sum of lognormal random variables where the number in the sum is determined by a Poisson process. These hypotheses are tested, and a sampling experiment is conducted to demonstrate the estimation procedure.
TL;DR: In this article, two MOS photomatrix configurations, voltage sampling and recharge sampling, have been compared with regard to sources of fixed-pattern noise in terms of peak-to-peak signal to FPN ratios.
Abstract: Two MOS photomatrix configurations, voltage sampling and recharge sampling, have been compared with regard to sources of fixed-pattern noise. Voltage sampling provides a high-amplitude low-impedance photosignal, with FPN primarily due to threshold variation in the amplifying MOST at each element. Recharge sampling is used for large high-yield rapidly scanned arrays, with FPN caused mostly by variations in spurious capacitive breakthrough. Production peak-to-peak signal to FPN ratios are 20:1 for voltage sampling and 50:1 for recharge sampling.
TL;DR: In this paper, a 29-storm sample of 1-minute rainfall rates was obtained with an Illinois network of 50 recording gages in 100 square miles during the warm seasons of 1952 and 1953.
Abstract: A 29-storm sample of 1-minute rainfall rates was obtained with an Illinois network of 50 recording gages in 100 square miles during the warm seasons of 1952 and 1953. These gages were equipped with enlarged orifices and 6-hour charts to provide nearly instantaneous spatial patterns of rainfall intensity on the network. The data were used to determine quantitative estimates of rainfall rate gradients, sampling errors in the measurement of mean areal rates, and spatial correlation patterns. The derived relations are considered first approximations for midwestern warm-season storms. It was concluded that the spatial variability of rainfall rates is frequently so great within and between convective storms that the rain gaging equipment and operational requirements for accurate rate measurements may be prohibitive for most users when sampling areas are 100 square miles or greater. Consequently it is recommended that the use of radar in combination with recording gages be investigated as a possible solution to the measurement problem.
TL;DR: Simulation studies for first GARP global experiment, discussing data redundancy, measured and derived data, sampling, etc as discussed by the authors, discussed data redundancy and data redundancy in data redundancy analysis.
Abstract: Simulation studies for first GARP global experiment, discussing data redundancy, measured and derived data, sampling, etc
TL;DR: In this article, the assumption of equal catchability of marked and unmarked animals in mark-recapture sampling is examined, and two approaches to this problem are discussed: statistically independent sampling procedures for marking and recapturing, and a new regression method is presented for multiple captures on a closed population.
Abstract: The assumption of equal catchability of marked and unmarked animals in mark—recapture sampling is examined. Violation of this assumption may come from two basic sources, heterogeneity or contagion, and both produce a bias in the estimate of population size. Two approaches to this problem are discussed. First, it is noted that bias can be avoided by statistically independent sampling procedures for marking and recapturing. Second, a new regression method is presented for multiple captures on a closed population, which combines mark—recapture with "simulated" removal and tests whether the assumption of equal catchability holds, regardless of the source of bias. Furthermore, if the ratio of catchabilities between unmarked and marked animals is constant over at least two successive samples, the method provides an estimate of population size even if the assumption of equal catchability does not hold. Two suggestions are made to supplement the regression method. First, noncapture sampling to obtain the ratio of...
TL;DR: The purpose of this preliminary communication is to report on concentrations of hemoglobin and of plasma iron as well as on hematocrit.
TL;DR: The design of sampling from finite populations is receiving increased attention in the statistical literature as mentioned in this paper, and a critical review of past studies and new developments and outlines areas meriting further study and research are presented.
Abstract: The design of sampling from finite populations is receiving increased attention in the statistical literature. This article presents a critical review of past studies and new developments and outlines areas meriting further study and research. Bayesian and non-Bayesian approaches are analyzed but are not offered in a normative manner. Both points of view and the extent to which they provide differences in survey sample design are discussed and examined. These differences are highlighted in stratification procedures, stratified sampling allocation, multivariate designs, and designs with varying inclusion probabilities.
TL;DR: Three methods of sampling skin bacteria were evaluated and it was found that in addition to actual differences in the skin flora populations of adjacent areas, there were significant differences in populations obtained by different sampling techniques and significant differences between individuals.
TL;DR: In this article, the authors developed a sampling procedure which for n > 4 and a linear trend has a smaller variance for the sample mean than 1 per stratum and for which an unbiased estimator of the variance is available.
Abstract: FOR populations arranged in natural order, say in increasing values of a concomitant variable, one common sampling scheme is to divide the population into strata and sample proportionately from each stratum. Variance of the sample mean is minimized (with the possible exception of finite corrections) if the population is divided into n strata and one unit selected from each. A second common procedure, particularly if the sampling is with unequal probabilities, is to sample systematically.t It is well known that if the y characteristic is composed of a linear trend plus random elements the 1-per-stratum design is more efficient than systematic sampling of the population in natural order. The disadvantage of both of these sampling schemes is, of course, that no unbiased estimator of variance is available. In this paper we develop a sampling procedure which for n > 4 and a linear trend has a smaller variance for the sample mean than 1 per stratum and for which an unbiased estimator of the variance is available.
TL;DR: In this article, the sediment sampling efficiency of two-dimensional slots in open channel was studied and a universal relation between the efficiency, the Froude number and the particle size was established for what is termed the bed load transport range.
Abstract: The sediment sampling efficiency of two-dimensional slots in open channel was studied. Eight fractions of sand and gravel were used ranging in size from 0.2 mm to 4.5 mm. A universal relation between the efficiency, the Froude number and the particle size was established for what is termed the bed load transport range. It was found that the sampling efficiency in this range decreases slightly with particle size and approaches one for large slots openings. The sampling efficiency of smaller particles, which do not move as bed load, was found to increase with particle size but remained smaller than one even for extremely large slot size to particle size ratios.