Sample size design and empirical research based on PPS and stratified sample survey

Author(s):  
Ma Shi-xiao ◽  
Dong Wen-yan ◽  
Wang Tong ◽  
Xi Qiu-hong
2017 ◽  
Vol 25 (4) ◽  
pp. 465-482 ◽  
Author(s):  
Marcel Fafchamps ◽  
Julien Labonne

We discuss a statistical procedure to carry out empirical research that combines recent insights about preanalysis plans (PAPs) and replication. Researchers send their datasets to an independent third party who randomly generates training and testing samples. Researchers perform their analysis on the training sample and are able to incorporate feedback from both colleagues, editors, and referees. Once the paper is accepted for publication the method is applied to the testing sample and it is those results that are published. Simulations indicate that, under empirically relevant settings, the proposed method delivers more power than a PAP. The effect mostly operates through a lower likelihood that relevant hypotheses are left untested. The method appears better suited for exploratory analyses where there is significant uncertainty about the outcomes of interest. We do not recommend using the method in situations where the treatment are very costly and thus the available sample size is limited. An interpretation of the method is that it allows researchers to perform direct replication of their work. We also discuss a number of practical issues about the method’s feasibility and implementation.


2020 ◽  
pp. 28-63
Author(s):  
A. G. Vinogradov

The article belongs to a special modern genre of scholar publications, so-called tutorials – articles devoted to the application of the latest methods of design, modeling or analysis in an accessible format in order to disseminate best practices. The article acquaints Ukrainian psychologists with the basics of using the R programming language to the analysis of empirical research data. The article discusses the current state of world psychology in connection with the Crisis of Confidence, which arose due to the low reproducibility of empirical research. This problem is caused by poor quality of psychological measurement tools, insufficient attention to adequate sample planning, typical statistical hypothesis testing practices, and so-called “questionable research practices.” The tutorial demonstrates methods for determining the sample size depending on the expected magnitude of the effect size and desired statistical power, performing basic variable transformations and statistical analysis of psychological research data using language and environment R. The tutorial presents minimal system of R functions required to carry out: modern analysis of reliability of measurement scales, sample size calculation, point and interval estimation of effect size for four the most widespread in psychology designs for the analysis of two variables’ interdependence. These typical problems include finding the differences between the means and variances in two or more samples, correlations between continuous and categorical variables. Practical information on data preparation, import, basic transformations, and application of basic statistical methods in the cloud version of RStudio is provided.


2016 ◽  
Vol 15 (1) ◽  
pp. 61-84
Author(s):  
Angel Christy Praveena ◽  
Kumari S Santhosh

This paper attempts to reveal the impact of modern digital business models on the changing buyer behavior of the tech savvy consumers. An empirical research was undertaken with a sample size of 100 and the responses are analyzed to give an overview on the major factors that influence buyers to shift from traditional or conventional shopping. The study reveals that more and more people prefer online shopping over conventional shopping. Present investigation reveals that consumers have an overall positive image towards digitalization while making a purchase


Turyzm ◽  
2019 ◽  
Vol 29 (2) ◽  
pp. 69-79 ◽  
Author(s):  
Ewa Malchrowicz-Mośko ◽  
Joanna Poczta

The aim of the study is to to examine the motivations for participating in a half-marathon among two groups of runners, local running in their place of residence and sports tourists, and to evaluate the differences between them. With the increase in the popularity of ‘running tourism’ the question becomes important as it encourages runners to engage in physical activity outside their everyday place of residence. Freyer and Gross’s (2002) four types of motivation for participation in sports events was the basis for the development of the author’s questionnaire. The empirical research (sample size=346) then recognized these motives for participation. The article also presents a review of the literature on such motivations in mass running events. Results indicate that both group of respondents, residents of the place where the half-marathon was organised and sports tourists, have different forms of motivation. The greatest relevance for sports tourists turned out to be motivation for sensation-seeking but for local runners it was the result, and this confirms that sports tourists travel generally in search for strong emotions and sensations.


Archeological, archival, and geomorphologic investigations were conducted for the proposed Pharr-Reynosa International Bridge Project in Hidalgo County, Texas, by Prewitt and Associates, Inc. from October 12-27, 1992. The purposes of these investigations were to locate and record any cultural resources within the project area, determine their eligibility for listing on the National Register of Historic Places and designation as State Archeological Landmarks, and to provide an overview of the Holocene geomorphic history of the project area. The geomorphic history of the project area suggests that the Rio Grande has experienced continuous channel aggradation from the end of the Pleistocene to ca. 1000 B.P. Climatic changes and diminishing sediment loads led to channel incision around 1000 B.P., forming a low late Holocene terrace and resulting in increased sinuosity and a decreased channel width-to-depth ratio. The investigations included a stratified sample survey of approximately 162 hectares (400 acres) and the excavation of 16 backhoe trenches and 14 shovel tests. A total of 10 sites, consisting of 10 historic and 2 prehistoric components, were documented. Six standing architectural properties, each consisting of a structure or groups of structures, also were documented. Four of the sites (41HG153, 41HG155, 41HG156, and 41HG158) are considered to be potentially eligible for listing on the National Register of Historic Places and for designation as State Archeological Landmarks. Two of the architectural properties - the Carmichael and Sorenson farmsteads - also may be eligible for listing on the National Register. The four potentially eligible sites consist of four historic and two prehistoric components. The historic components date from the Texas Republic period to the early twentieth century, representing the establishment and development of the EI Capote Ranch community. The two prehistoric components (41HG153 and 41HG158), of which only 41HG153 is potentially eligible, represent Late Prehistoric and unknown prehistoric components, respectively.


2014 ◽  
Vol 2014 ◽  
pp. 1-7
Author(s):  
Atta Ullah ◽  
Javid Shabbir ◽  
Zawar Hussain ◽  
Bander Al-Zahrani

In practical utilization of stratified random sampling scheme, the investigator meets a problem to select a sample that maximizes the precision of a finite population mean under cost constraint. An allocation of sample size becomes complicated when more than one characteristic is observed from each selected unit in a sample. In many real life situations, a linear cost function of a sample sizenhis not a good approximation to actual cost of sample survey when traveling cost between selected units in a stratum is significant. In this paper, sample allocation problem in multivariate stratified random sampling with proposed cost function is formulated in integer nonlinear multiobjective mathematical programming. A solution procedure is proposed using extended lexicographic goal programming approach. A numerical example is presented to illustrate the computational details and to compare the efficiency of proposed compromise allocation.


2021 ◽  
Vol 8 (4) ◽  
pp. 75-81
Author(s):  
J Duraichamy ◽  
T T Karthik

In developing countries like India both men and women are working for survival; in this tight schedule, packaged instant foods make their cooking process easy and saves time. Packaged instant food products simplify the cooking process and speed ups the cooking. Nowadays, every supermarket shelf is filled with instant food products. As customers are willing to buy more, so it is important to analyze their opinion regarding packed instant food. In a study, an attempt ah been made to analyze the customer’s level of opinion towards packaged instant food. The objective of the study is to analyze the opinion of the customers towards packaged instant food products. A sample survey was conducted in Madurai city; the sample size is 45. The questionnaire has been used to collect primary data from the respondents. SPSS software is used to analyze the data statistics.


2014 ◽  
Vol 34 (8) ◽  
pp. 1080-1122 ◽  
Author(s):  
Naga Vamsi Krishna Jasti ◽  
Rambabu Kodali

Purpose – The purpose of this paper is to review the existing literature on empirical research in lean manufacturing (LM). It provides a critical assessment of empirical research methodology of 178 research articles published from 1990 to 2009. Design/methodology/approach – The article reviewed a set of 178 empirical research articles in LM research with respect to empirical research design and its related facets. The 236 empirical research articles which are published in 70 journals during 1990-2009 are collected from four major management science publishers, namely, Emerald Online, Science Direct, Springer Link and Taylor & Francis. In total 178 research articles published in 24 journals are selected for critical review of empirical research methodology in LM. The approach for the critical review of 178 empirical research articles in LM is based on empirical research approach given by Flynn et al. (1990). The critical review discusses the current status of empirical research in LM and future directions. Findings – It is concluded from the analysis of the results that: the number of empirical research articles in LM is increasing at a faster pace than ever before; theory building and theory verification articles are equally advanced; the researchers have also unexplored various aspects of empirical research such as importance of triangulation of data, alternate research designs other than survey and case studies; contextual focus is mostly on the manufacturing industry; more focus required on other aspects of empirical research such as collecting the samples from developing and undeveloped countries, larger sample size, longitudinal data collection methods. Finally, it concludes that there is a need of LM frameworks, which gives the stepwise process to remove all kinds of wastes from any organization. Originality/value – To the knowledge of the authors, it is the first of its kind attempt to critically review the empirical research articles in LM. The review analysis entirely focussed on descriptive statistics of empirical research in LM. The sample size is one of the unique features of this research as the number of shortlisted articles is 178 in 24 journals published over a time span of 20 years (1990-2009).


2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 6591-6591 ◽  
Author(s):  
Hartmut Link ◽  
Josef Nietsch ◽  
Markus Kerkmann ◽  
Petra Angelika Ortner ◽  

6591 Background: Primary G-CSF prophylaxis after chemotherapy is recommended in evidence based guidelines (GL), if the risk of febrile neutropenia (FN) is high (≥20%), or intermediate (≥ 10% - 20%) in case of risk factors. The aim was to evaluate, if G-CSF is used as proposed by GL, to identify determinants of GL implementation and adherence. Methods: The sample size was calculated at 2% of the incidence of malignant lymphoma, breast and lung cancer in Germany. Pts who had received 3-9 cycles of chemotherapy with a FN risk ≥10% between 5/2011 to 4/2012 were documented retrospectively. Results: 286 lymphoma, 666 lung cancer and 976 breast cancer pts were collected from 87 hospitals and 59 oncology practices with 195 physicians participating. Adherence to GL was higher in physicians up to 10 than over 10 years of experience. Conclusions: The adherence to and acceptance of GL for G-CSF may not be sufficient. Patient risk factors are underestimated therefore resulting in a possible underuse of G-CSF. Physicians may underestimate FN risk in pts who have an intermediate risk of FN and they overestimate their adherence to the GL. [Table: see text]


Sign in / Sign up

Export Citation Format

Share Document