Search Results

A Monte Carlo Comparison of OLS Estimation Errors and Design Efficiencies in a Two‐Stage Stratified Random Sampling Procedure for a Contingent Valuation Study

Kyeongae Choe, William R. Parke, and Dale Whittington

in Valuing Environmental Preferences: Theory and Practice of the Contingent Valuation Method in the US, EU , and developing Countries

In many settings, a random sample may not be cost‐inefficient, so that a two‐stage stratified random sample is adopted in contingent valuation (CV) studies. The first stage comprises identifying a ... More

In many settings, a random sample may not be cost‐inefficient, so that a two‐stage stratified random sample is adopted in contingent valuation (CV) studies. The first stage comprises identifying a number of enumeration areas from which to sample households in the second stage. The Monte Carlo simulation, from a CV case study, suggests that increasing the second‐stage sample size within a limited number of enumeration areas selected at the first stage of sampling will result in a greater return in statistical and sampling design efficiency than will increasing the number of enumeration areas with a limited second‐stage sampling size. In both approaches, the marginal return diminishes as the number of sampling units increases.Less

Methodological Alternatives and Supplements to Random Sampling

Patrick Dattalo

in Strategies to Approximate Random Sampling and Assignment

This chapter begins with a discussion of external validity and sampling bias. Next, the rationale and limitations of RS as a way to maximize external validity and minimize sampling bias are ... More

This chapter begins with a discussion of external validity and sampling bias. Next, the rationale and limitations of RS as a way to maximize external validity and minimize sampling bias are presented. Then, the following alternatives and supplements to RS will be presented in terms of their assumptions, implementations, strengths, and weaknesses: (1) deliberate sampling for diversity and typicalness; and (2) sequential sampling. Deliberate sampling for diversity and typicalness and sequential sampling are methodological alternatives for RS.Less

Sampling and Measurement

Peter Lyons and Howard J. Doueck

in The Dissertation: From Beginning to End

This chapter examines participant selection, sampling design, sample size and sampling error; as well as the importance of statistical power, effect size, confidence levels, and confidence intervals. ... More

This chapter examines participant selection, sampling design, sample size and sampling error; as well as the importance of statistical power, effect size, confidence levels, and confidence intervals. Types of sampling, including probability and nonprobability sampling methods, are discussed in relation to both quantitative and qualitative research designs. The measurement properties of instruments including requirements of validity and reliability as well as issues in measurement with human measures (credibility, inquiry audits, and triangulation) are presented.Less

Populations with Regression Structure

Raymond L. Chambers and Robert G. Clark

in An Introduction to Model-Based Survey Sampling with Applications

When there is a single continuous auxiliary variable, it is often reasonable to assume a simple linear regression model relating this variable to the variable of interest. This chapter describes the ... More

When there is a single continuous auxiliary variable, it is often reasonable to assume a simple linear regression model relating this variable to the variable of interest. This chapter describes the use of regression population models in sample surveys. Proportional models, where the intercept is assumed to be zero, have a long history in survey sampling and are discussed first. Empirical best and best linear unbiased predictors are derived. The ratio model is a special case of the proportional model, and this leads to the well known ratio estimator. Models with intercepts are then discussed, including best estimators of totals. Sample designs are developed. Under the ratio model, the optimal design is to select only the units with the largest values of the auxiliary variable. However this would not be robust to departures from the ratio model. The problem of robust design is discussed in Chapter 8. Optimal design is also discussed for the linear model with intercept. The combination of regression and stratification is discussed. It is possible to assume the same regression or ratio relationship in every stratum, or to allow different coefficients in each stratum. Data from an agriculture survey are used to illustrate this choice.Less

Designing carnivore surveys

Luigi Boitani, Paolo Ciucci, and Alessio Mortelliti

in Carnivore Ecology and Conservation: A Handbook of Techniques

This chapter examines the challenges associated with planning and implementing a field survey on carnivores. Following the definition of the term ‘survey’, the main issues associated with the several ... More

This chapter examines the challenges associated with planning and implementing a field survey on carnivores. Following the definition of the term ‘survey’, the main issues associated with the several phases of a carnivore survey, such as the planning phase, the establishment of goals and objectives, and the optimal allocation of sampling effort, are discussed. Throughout the chapter, the focus is on the most relevant aspects of studying carnivores in the field, such as dealing with false absences through occupancy modelling, defining the target population and spatial extent of the survey, and implementing a probabilistic sampling scheme under the constraints of field methods commonly used to study carnivores.Less

The General Linear Population Model

Raymond L. Chambers and Robert G. Clark

in An Introduction to Model-Based Survey Sampling with Applications

All of the models discussed in chapters 3 through 6 are special cases of the correlated general linear population model. This chapter describes the general linear population model, and the correlated ... More

All of the models discussed in chapters 3 through 6 are special cases of the correlated general linear population model. This chapter describes the general linear population model, and the correlated general linear population model. These models allow for very general relationships between the variable of interest and a set of auxiliary variables, where auxiliary variables can consist of an arbitrary number of continuous and categorical variables. Empirical best and best linear unbiased predictors are described, and the predictors from earlier chapters are shown to be special cases. Questions of model choice and efficient sample design are also considered.Less

Basic concepts

David G. Hankin, Michael S. Mohr, and Ken B. Newman

in Sampling Theory: For the Ecological and Natural Resource Sciences

This chapter provides a conceptual, visual and non-quantitative presentation of the basic principles of sampling theory which are developed in formal quantitative fashion in subsequent chapters. ... More

This chapter provides a conceptual, visual and non-quantitative presentation of the basic principles of sampling theory which are developed in formal quantitative fashion in subsequent chapters. Included are summaries of (a) basic terminology used throughout the text (population, sample, estimator, estimate), (b) components of a sampling strategy (sampling frame, sampling design, estimator), (c) properties of estimators (bias, sampling variance, mean square error), and (d) sampling distribution of an estimator. Simple or familiar settings are used to illustrate the differences between simple frames (listings of population units from which a sample of units is selected) and complex frames (sampling units consist of groupings of population units), and to illustrate the different components of a sampling strategy. A bullseye target with associated dart throws is used to distinguish the important estimator properties of bias, sampling variance, and mean square error. The performances of randomized sampling procedures and purposive or judgment selection of “representative samples” are contrasted using two examples: (1) an historical contrast of estimated abundance of Oregon coastal coho salmon (Oncorhynchus kisutch) based on purposive representative reach surveys and on stratified random surveys, and (2) a repeatable classroom exercise pitting judgment sampling against simple random sampling for estimation of mean weight in a population of agates collected from northern California beaches.Less

Applications of Active Learning

Masashi Sugiyama and Motoaki Kawanabe

in Machine Learning in Non-Stationary Environments: Introduction to Covariate Shift Adaptation

This chapter describes real-world applications of active learning techniques: sampling policy design in reinforcement learning and wafer alignment in semiconductor exposure apparatus.

Working With Public-Use and Proprietary Datasets

Seth J. Schwartz

in The Savvy Academic: Publishing in the Social and Health Sciences

This chapter addresses work with regionally or nationally representative datasets, which are often used in disciplines like public health, sociology, demography, and political science. Some of these ... More

This chapter addresses work with regionally or nationally representative datasets, which are often used in disciplines like public health, sociology, demography, and political science. Some of these datasets are publicly available, whereas others are proprietary and can be accessed only by developing a formal proposal and paying a fee. The chapter lays out the types of claims and research questions that datasets are best equipped to support or address. Tips for using these datasets are provided, such as understanding the sampling strategy and the labeling of variables in the codebook. Challenges inherent in using public-use and proprietary datasets are also enumerated.Less

Capture, Restraint, and Euthanasia of Target Species

Johannes Foufopoulos, Gary A. Wobeser, and Hamish McCallum

in Infectious Disease Ecology and Conservation

Despite advances in noninvasive data collection, the practice of capturing wildlife provides a wealth of information and remains a fundamental component of wildlife disease and conservation studies. ... More

Despite advances in noninvasive data collection, the practice of capturing wildlife provides a wealth of information and remains a fundamental component of wildlife disease and conservation studies. Six principal considerations are discussed in the context of capturing wild animals for disease sampling, including: whether the captured animals are representative of the entire population and whether the biological samples are indicative of the physiology rather than the capturing method; whether capture techniques will influence the animal’s subsequent behavior or endanger the investigators; whether the chosen sampling frequency and magnitude are representative of the host population demographics and disease dynamics; and finally, how the capturing and sampling process can be continually improved.Less

NREGA’s Characteristics and the Methodology of the Study

Shylashri Shankar and Raghav Gaiha

in Battling Corruption: Has NREGA Reached India's Rural Poor?

It first discusses NREGA’s goals and the reviews of the scheme by policy makers and scholars. NREGA is a targeted program where instead of relying on an administrator to choose the beneficiaries, ... More

It first discusses NREGA’s goals and the reviews of the scheme by policy makers and scholars. NREGA is a targeted program where instead of relying on an administrator to choose the beneficiaries, NREGA expects beneficiaries to select themselves by creating incentives so that only the poor will participate in the scheme. In practice, however, the self- selection mechanism has been weakened in areas where NREGA wage was higher than the prevailing market wage, and by the low awareness among the beneficiaries of the scheme’s components. It then discusses the sample design and data collection The analysis draws upon five datasets—household (and a subset), ethnographic, panel, worksite, and individual beneficiary scheme—designed and collected by the authors from Rajasthan, Andhra Pradesh (AP), Madhya Pradesh (MP), and Tamil Nadu (TN). These four were chosen to ensure geographic and economic diversity.Less