China 
Africa 
Explore chapters and articles related to this topic
Environmental Reconstruction of Watershed Vegetation Cover to Reflect the Impact of a Hurricane Event
Published in Ni-Bin Chang, Kaixu Bai, Multisensor Data Fusion and Machine Learning for Environmental Remote Sensing, 2018
The t-test was conducted on the null hypothesis that the mean difference of the two datasets is zero with alpha value of 0.05. Alpha value is also referred to significance level, that is, the probability of rejecting the null hypothesis when the null hypothesis is true. The t values for brightness, greenness, and wetness are 445.62, 331.26, and 204.11, respectively. All the t values are presented in their absolute values. The t-critical value for all three cases is 1.96. The t-critical values are determined using the alpha value and the degree of freedom values. Since t > t-critical and p < 0.05, the null hypothesis is rejected, that is, there is significant difference between the means of the two conditions. After calculations, we can surmise that there is a 19.21% change in pixel values for brightness; 46.51% change in greenness, and 13.47% difference in wetness when compared to pixel values of the before-landfall scenario. These significant differences in values conform to the tasseled cap plots that after hurricane landfall, there was significant change in the landscape which contributed to the dispersion of pixels, that is, change in the values of pixels. The Pearson correlation coefficient for the three transformations are also quite low, indicating a significant difference in the data pairs.
Analytic Formulas for Evaluating Generalization
Published in Richard M. Golden, Statistical Machine Learning, 2020
In practice, one checks if the estimated p-value is less than some critical value α which is called the significance level. This controls the magnitude of the Type 1 error. To control the magnitude of the Type 2 error, statistical tests are often designed so that the probability of the Type 2 error converges to zero as the sample size becomes large. If the null hypothesis is rejected at the α significance level, then the statistical test is said to be significant at the α significance level. A typical choice for the significance level is α = 0.05.
Mathematical Modeling and Statistical Inference
Published in Gerald L. Schneberger, Adhesives in Manufacturing, 2018
The established procedure is to choose a priori a critical level of significance to represent the dividing line between rejecting and not rejecting H0. This critical value is called the significance level of the test and is usually denoted by α. Stating it in the form of a decision rule, we write Decision Rule. Reject H0 if the significance level of the sample result is less than a; otherwise, do not reject H0.
Sensitivity analysis and optimization on effective parameters during chemical enhanced oil recovery (CEOR) using experimental design and numerical simulation
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2019
Ali Mohsenatabar Firozjaii, Majid Akbari, Ghassem Zargar
The sign of the main effect obtained from Eq. (2) shows the type of the effect by each factor. The effect of each parameter is shown on Tornado plot. More than, the interaction effect of two factors on oil RF is discussed in Parto plot also. It is important to determine that the estimated effect is correct or is random. Statistical significance of main and interaction effects can be estimated by hypothesis testing. It is a standard method of statistical inference that considers two opposite hypotheses. The null hypothesis assumes that the effect of a parameter is negligible and the reported value is due to the chance or any other reason except the role of the parameter itself. The alternative hypothesis assumes that the nonzero effects demonstrate the real effects of the parameter. It is common to determine the credibility of the null hypothesis with P values. P value describes how much it is probable that the null hypothesis is true. The critical value which is the criterion for accepting or rejecting the null hypothesis is called the significance level. If the P value is lower than the significance level, the null hypothesis is rejected. The null hypothesis is accepted when the P value is greater than the significance level. Significant level of = 0.001 is considered in this study.
Classification and benchmark of City Logistics measures: an empirical analysis
Published in International Journal of Logistics Research and Applications, 2018
Alberto De Marco, Giulio Mangano, Giovanni Zenezini
The significance level, which is typically equal to 0.05, represents a constant critical value. If the p-value is smaller than the given critical value, the null hypothesis is rejected and it can be concluded that the relationship is significant. On the contrary, if the p-value is greater than the critical value, the test fails to reject the null hypothesis and it can be concluded that there is not enough evidence to prove a significant relationship (Bhattacharya and De Sale 2002).