China
Africa
Explore chapters and articles related to this topic
A Corpus Based Quantitative Analysis of Gurmukhi Script
Published in Ayodeji Olalekan Salau, Shruti Jain, Meenakshi Sood, Computational Intelligence and Data Sciences, 2022
Gurjot Singh Mahi, Amandeep Verma
Mean is the measure of the center of distribution of central tendency (Barde and Barde 2012). Mean values in this paper are quantified for the two mentioned syntactic levels—words and sentences. Finding the word and sentence mean lengths is the fundamental approach used for studying the underlying syntactic structure of written texts by measuring the usage of characters and words, respectively. The calculated mean values of the word and sentence lengths are represented using symbols – and , and are calculated using Formulas 12.1 and 12.2:
Quantitative Methods for Analyzing Experimental Studies in Patient Ergonomics Research
Published in Richard J. Holden, Rupa S. Valdez, The Patient Factor, 2021
Kapil Chalil Madathil, Joel S. Greenstein
The median value is a better estimate of central tendency for studies with a large sample size and values dispersed as a skewed distribution. Sauro and Lewis (2016) recommend a method akin to calculating CI for percentiles to calculate the confidence intervals around the median value. Sauro and Lewis (2010, 2016) found that the geometric mean, as opposed to the arithmetic mean and mode, is a better estimate of the task time with a sample size of less than 25 participants. They illustrate the steps to compute the geometric mean and associated confidence intervals (Sauro & Lewis, 2016).
Norms and Scores
Published in Lucy Jane Miller, Developing Norm-Referenced Standardized Tests, 2020
For example, in the following 2 sets of scores both have a mean of 3. Set A: 1,2,2,3,3,3,4,4,5Set B: 1,1,1,2,3,4,5,5,5 However, graphically it is obvious that they are very different (see Figure 1). If only indicators of central tendency were provided, the two sets of data would not be adequately described. An indicator of the variability or dispersion of the scores is necessary.
The impact of chronotype on circadian rest-activity rhythm and sleep characteristics across the week
Published in Chronobiology International, 2021
Chris Brooks, Nina Shaafi Kabiri, Jaspreet Bhangu, Xuemei Cai, Eve Pickering, Michael Kelley Erb, Sanford Auerbach, Paolo Bonato, Tara L. Moore, Farzad Mortazavi, Kevin Thomas
Descriptive statistics were generated for all variables; unless otherwise stated, all descriptive values reported herein are “mean (standard deviation)” for continuous variables and “number (%)” for dichotomous, ordinal and categorical variables. Measures of central tendency consisted of means and medians for normally and non-normally distributed variables, respectively. Processed data were organized and arrayed using Excel 16.16.13 for Mac (Microsoft, Inc., Redmond, WA, USA). All statistical analyses were performed in Stata 16.0 for Mac (StataCorp, Inc., College Station, TX, USA). Normality of distributions was evaluated using skewness-kurtosis tests, and equality of variances between groups was evaluated using equal-variances test. Two-sample comparisons were conducted using two-sample t-tests for normally distributed samples with equal variances, Welch’s t-tests for normally distributed samples with unequal variances and Wilcoxon rank-sum tests for non-normally distributed samples with a significance threshold of p = 0.05.
Versatility in multiple mini-interview implementation: Rater background does not significantly influence assessment scoring
Published in Medical Teacher, 2020
Keith D. Baker, Roy T. Sabo, Meagan Rawls, Moshe Feldman, Sally A. Santen
Observational assessment is more complex than knowledge tests or attitude surveys, in that the rater introduces an additional source of variance due to rater errors or biases. These may weaken the quality of inferences one can make about observations (Downing and Haladyna 2004; Kogan et al. 2011). Assessments of individual knowledge, skills, abilities, or other characteristics often rely on human judgments prone to these biases, leading the assessment score to be based on factors other than the intended focus. Rater response biases have been consistently found to occur. For instance, central tendency occurs when raters try to avoid extreme positive or negative ratings; however, we do not feel that central tendency was a factor in our data, as the estimated means seem to indicate positive evaluations. Another common response bias is the halo effect, which occurs when ratings are based on only one positive or negative portion of a response rather than consideration of the entire response. These biases seem to impact the rater regardless of rater-specific characteristics or roles (Wexley and Youtz 1985; Murphy and Anhalt 1992).
Electrocardiographic left ventricular hypertrophy in relation to peripheral and central blood pressure indices in a Nigerian population
Published in Blood Pressure, 2020
Augustine N. Odili, Babangida S. Chori, Benjamin Danladi, Wen-Yi Yang, Zhen-Yu Zhang, Lutgarde Thijs, Fang-Fei Wei, Tim S. Nawrot, Tatiana Kuznetsova, Jan A. Staessen
For database management and statistical analysis, we used SAS software version 9.4. (SAS Institute, Cary, NC). We used means and standard deviation to express central tendency and spread of the data. For comparison of means and proportions, we used Student’s t-test and the χ2 statistic, respectively. Statistical significance was a p-value less than 0.05 on two-sided tests. We assessed associations using Pearson’s correlation coefficients and we used Steiger’s Z test in the pairwise comparison of correlation coefficients. We used multiple linear regression to adjust for confounders, while assessing the relation of Sokolow–Lyon QRS voltage with the central and peripheral blood pressure indices. Using multiple logistic regression models, we determined the odds ratio of having LVH associated with a one standard deviation higher central or peripheral blood pressure. Each central BP component is highly correlated with the corresponding peripheral component. To evaluate the association of Sokolow–Lyon QRS voltage with central and peripheral blood pressure indices, we first regressed each central BP index on the peripheral and derived the residuals, which represents the amount of variation in the central BP that could not be explained by the peripheral. We regressed the continuous and dichotomous indices of LVH on these residuals. The p values of the residuals test the hypothesis that the central BP index is associated with ECG LVH over and above the peripheral.