China
Africa
Explore chapters and articles related to this topic
Artificial Intelligence Basics
Published in Subasish Das, Artificial Intelligence in Highway Safety, 2023
All components in any field of analysis consist of a ‘population.’ Sampling includes selecting some part of a population that can provide a representative estimate of something about the whole population. A sample requires being representative of the population to obtain statistical reliability. Sampling design has two broad categories: probability sampling and non-probability sampling. In scientific research, probability sampling is mostly used. Unrestricted sampling infers sampling methods that consider taking a random sample at large from a population. The other sampling methods consider some local or global restrictions to make sampling more robust. These methods are known as restricted sampling. Figure 18 shows different kinds of sampling methods, including probability and non-probability sampling.
Inference
Published in Julian J. Faraway, Linear Models with Python, 2021
A sample of convenience is where the data are not collected according to a sampling design. In some cases, it may be reasonable to proceed as if the data were collected using a random mechanism. For example, suppose we take the first 400 people from the phone book whose names begin with the letter P. Provided there is no ethnic effect, it may be reasonable to consider this a random sample from the population defined by the entries in the phone book. Here we are assuming the selection mechanism is effectively random with respect to the objectives of the study. The data are as good as random. Other situations are less clear-cut and judgment will be required. Such judgments are easy targets for criticism. Suppose you are studying the behavior of alcoholics and advertise in the media for study subjects. It seems very likely that such a sample will be biased, perhaps in unpredictable ways. In cases such as this, a sample of convenience is clearly biased in which case conclusions must be limited to the sample itself. This situation reduces to the following case.
Decision-Making and Monitoring Strategies in Natural Resource Management and Conservation
Published in Yeqiao Wang, Terrestrial Ecosystems and Biodiversity, 2020
Brian D. Gerber, Perry J. Williams
Probability-based sampling methods assume the underlining spatial process of interest is fixed, but randomness is introduced in sample selection using a probability sampling design. A probability sampling design consists of both a sampling frame, a set of all elements in the population of interest, and a probability measure defined on the frame; a systematic method for assigning a probability to the selection of any subset (i.e., any sample) from the frame. The statistical properties (e.g., unbiased-ness) of the estimators used to make inference on the population are based entirely on the probability measure that defines the design. For this reason, inference from probability-based sampling methods is often referred to as design-based inference. The objective of design-based inference is to quantify a population parameter of interest. Typically, these include summary statistics such as the mean, total, variance, or proportion. Probability-based sampling methods are one of the most common and widely used sampling methods in natural resources. When probability-based sampling designs are combined with the appropriate estimators, investigators obtain objective, unbiased estimates of the population. Both [26] and [28] provide in-depth discussion of probability-based sampling methods and numerous extensions.
COVID-19 and people's continued trust in eHealth systems: a new perspective
Published in Behaviour & Information Technology, 2023
Ahmed Ibrahim Alzahrani, Hosam Al-Samarraie, Atef Eldenfria, Joana Eva Dodoo, Xue Zhou, Nasser Alalwan
We examined the influence of service quality factors on individuals’ continued trust in eHealth services during the COVID-19 pandemic. The identified factors from the literature (reliability, tangibility, efficiency, content quality, responsiveness, assurance, empathy and hedonic benefits) were employed to construct a structured set of questions. This study applied a convenience sampling design to select the respondents. The selection of respondents was in part determined by the inclusion criteria (availability or accessibility and willingness to respond). In addition, we had no access to all respondents with experience in using eHealth services during the COVID-19 pandemic, and hence, a smaller but representative sample of users was obtained.