Explore chapters and articles related to this topic
Quantitative Evaluation of Human and Animal Studies
Published in W. H. Hallenbeck, K. M. Cunningham, Quantitative Risk Assessment for Environmental and Occupational Health, 1986
This discussion will be restricted to the statistical treatment of a dichotomous response variable, i.e., the proportion of subjects responding in the test and control groups. There are three ways to test the statistical significance of the difference between two proportions. One is the Fisher’s exact test based on the binomial distribution (Mattson, 1981). This test requires laborious calculations. The normal (Colton, 1974) and Poisson (Hays, 1981) approximations to the binomial distribution can be used whenever certain criteria are satisfied. If these criteria are satisfied, all three probability distributions will yield about the same result. The two approximate methods do not require laborious calculations.
Analysis of fatal fires in Norway over a decade, - a retrospective observational study
Published in Stein Haugen, Anne Barros, Coen van Gulijk, Trond Kongsvik, Jan Erik Vinnem, Safety and Reliability – Safe Societies in a Changing World, 2018
C. Sesseng, K. Storesund, A. Steen-Hansen
Statistical tests were conducted to test and examine apparent differences between sub-groups in the population. In all essentials non-parametric tests were employed, such as Mann-Whitney U-test, Fisher exact-test, chi-square test and regression analysis. For all analyses a significance limit of p ≤ 0.05 was employed. A p-value between 0.10 ≥ p > 0.05 is considered as a trend.
Partially-automated individualized assessment of higher education mathematics
Published in International Journal of Mathematical Education in Science and Technology, 2022
Students in groups A and B were asked to indicate their level of agreement with each of four statements, listed with numbers of responses in Table 5. Also in Table 5 are the p-values obtained for each Likert-type question when comparing the two groups via Fisher’s Exact Test. In each case, there is no evidence at the 5% level to reject the null hypothesis that the distribution of answers is independent of the group answering. Responses to two questions about copying, which were accompanied by a reminder that the questionnaire was anonymous, are given in Table 6. Again, p-values from Fisher’s Exact Test are listed in Table 6 and do not give evidence at the 5% level to reject the same null hypothesis.
User response to indoor thermal environment in female high school buildings in Oman
Published in Building Research & Information, 2022
Hanan Al-Khatri, Talal Etri, Mohamed B. Gadi
The different numbers of satisfied and comfortable students may create doubts regarding ASHRAE definition of thermal comfort, which is ‘that condition of mind which expresses satisfaction with the thermal environment and is assessed by subjective evaluation’ (ASHRAE, 2017, p. 9.1). Therefore, the independence between satisfaction and comfort levels was investigated applying Fisher exact test with a null hypothesis assuming independency. For ASHRAE and Bedford questionnaires in summer, the probabilities against hypothesis were 8.43E−23 and 1.56E−45, respectively. The corresponding values in winter were 3.94E−23 and 6.3E−22. Therefore, the null hypothesis was rejected as satisfaction and comfort were significantly related. This means that the variations in Figure 8 are mainly owing to sampling fluctuations.
Experimental design and RSM on the recovery of Ni (II) ions by ELM using TX-100 as a biodegradable surfactant
Published in Environmental Technology, 2022
Abdelkader Benderrag, Meriem Djellali, Boumediene Haddou, Mortada Daaou, Boumedienne Bounaceur
The experimental points for the Ni (II°) ions extraction according to Box–Behnken model are presented in Table 2. The analysis was performed to estimate the response function. The extraction efficiency was provided by the quadratic model as given by Equation (4). The model parameters were evaluated using the software ANOVA variance analysis. The aim of this statistical analysis was to determine the individual and interactive influences of the factors on Ni extraction yield. Consequently, coefficients were determined. Statistical significance was verified by Fisher's exact test. The model terms were selected or rejected according to the probability value with 94% confidence level. Finally, response surfaces were plotted in order to visualize the individual and interactive effects of independent variables. Therefore, optimal parameters of Ni membrane liquid extraction were determined.