China
Africa
Explore chapters and articles related to this topic
Statistics
Published in Paul L. Goethals, Natalie M. Scala, Daniel T. Bennett, Mathematics in Cyber Research, 2022
The field of inferential statistics enables one to make educated guesses about the numerical characteristics of large groups. The logic of sampling gives a way to test conclusions about the large group using only a small portion of its members. There are some basic terminologies in statistical methods: A population is the target, problem, or subject of interest. A population is generally represented as a more extensive set of data. It is the entire pool of data from which a statistical sample is drawn.A sample refers to the subset of the population that is being analyzed, typically represented in a smaller data set. A sample is drawn from a population. There are many sampling methods to select a sample set from a population; random and cluster sampling are two common sampling methods (Acharya, Prakash, Saxena, & Nigam, 2013). In random sampling, each sample has equal probability to be selected, whereas cluster sampling selects a predefined group in a population as the samples (Figure 9.2).A variable is a characteristic or property of interest from the population or sample.
The Thermal Comfort Survey
Published in Ken Parsons, Human Thermal Comfort, 2019
A decision must be taken on where, when, who and what to measure. Where to measure the environment and when to measure it are a matter of statistical sampling. This also applies to who to involve in the survey if it is not possible to involve all people who occupy the space. Samples must be representative and avoid bias. The environment will vary throughout a space and continuously with time. Depending upon the work, people will move throughout the space and over time (and personnel will change with shift work, for example). In general, the more places and times, the more valid the survey. As we are interested in thermal comfort, we should measure where the people are and at what times they are or could be. For a homogeneous distribution of people we could use a grid system. Measuring at workplaces is important and for a simple first survey, discrete measurements are often made (although continuous data logging techniques may be used for more detail of time variations). For a simple 1-day survey, measurements should include when and where complaints had been made, morning or afternoon or if possible both. A first request would be to obtain a scale plan of the ‘office’ and select measuring positions. Ankle, chest and head height measurements should be taken if local thermal discomfort (e.g. from draughts) is suspected. For subjective measures, it is better to ask people at their workstations how they feel ‘NOW’ rather than rely on memory of how they felt some time ago.
Project Control System
Published in Adedeji B. Badiru, Project Management, 2019
A sample is a subset of a population that is selected for observation and statistical analysis. Inferences are drawn about the population based on the results of the analysis of the sample. The reasons for using sampling rather than complete population enumeration are as follows: It is more economical to work with a sample.There is a time advantage to using a sample.Populations are typically too large to work with.A sample is more accessible than the whole population.In some cases, the sample may have to be destroyed during the analysis.
Loyalty and public transit: a quantitative systematic review of the literature
Published in Transport Reviews, 2022
Thiago Carvalho dos Reis Silveira, Cezar Augusto Romano, Tatiana Maria Cecy Gadda
Regarding sample size, a considerable group has less than 500 observations (9). In these cases, as questions are often designed based on a Likert scale, the data can be affected by multivariate normality issues (Hair, Black, Babin, & Anderson, 2014). Therefore, depending on the applied statistical technique, researchers should strive for larger samples sizes. In the remaining studies, 7 range from 500 to 1 K, 8 range from 1 K to 5 K, 1 range from 5 K to 10 K, 2 range from 10 K to 15 K, and 3 range from 50 K to 100 K. The samples over 10 K observations usually spam over multiple years and/or multiple cities. As expected, most studies consider public transit users only (21). However, we can also find those who try to examine a cross-section of the whole city population (9).
Estimation of environmental exposure: interpolation, kernel density estimation or snapshotting
Published in Annals of GIS, 2019
Xun Shi, Meifang Li, Olivia Hunter, Bart Guetti, Angeline Andrew, Elijah Stommel, Walter Bradley, Margaret Karagas
In this paper, to simplify the description, we use interpolation to refer to spatial interpolation. Interpolation is based on samples. Samples means that they are selected (sampled) from a much larger set of values (i.e. the value at each and every location in the study area). The reason for sampling is that we are not able to obtain and/or handle values of all locations in the study area, and thus, we intend to infer information about those unselected values (i.e. values at those un-sampled locations) based on the samples. This intention requires samples to be representative. Interpolation is one way to infer values at un-sampled locations based on values at sampled locations. Basically, interpolation is a weighted average calculation:
The categorization of amateur cyclists as research participants: findings from an observational study
Published in Journal of Sports Sciences, 2018
Jose Ignacio Priego Quesada, Zachary Y. Kerr, William M. Bertucci, Felipe P. Carpes
Sampling bias, originating from a sample not being representative of its intended target population, is of concern as it may limit the external validity of findings, affect the replicability of research protocols, augment types I and II statistical errors, and consequently affect the applicability of the results (Cooke & Jones, 2017; Shephard, 1998). Furthermore, an appropriate sample selection helps to ensure that the comparability among studies from the same target population can be maximized. Within the cycling population, there is a wide range of characteristics related to experience, fitness level, riding purpose, and cycling discipline, all of which can affect different parameters such as pedaling kinematics (Bini et al., 2016; Bini, Hume, & Kilding, 2014), patterns of muscle recruitment (Chapman, Vicenzino, Blanch, & Hodges, 2007, 2009), pedal forces (Candotti et al., 2007; García-López, Díez-Leal, Ogueta-Alday, Larrazabal, & Rodríguez-Marroyo, 2016) and physiological outcomes (Coyle et al., 1991; Lee, Martin, Anson, Grundy, & Hahn, 2002). Thus, it is imperative for researchers to carefully consider the characteristics of cyclists that they recruit for their studies.