Numerical Summary Measures
Marcello Pagano, Kimberlee Gauvreau in Principles of Biostatistics, 2018
While it may not make sense to compare standard deviations, it is possible to compare the variability among two or more sets of data representing different quantities with different units of measurement using a numerical summary measure known as the coefficient of variation. The coefficient of variation relates the standard deviation of a set of values to its mean; it is the ratio of s to multiplied by 100 and is, therefore, a measure of relative variability. Because the standard deviation and the mean share the same units of measurement, the units cancel out and leave the coefficient of variation a dimensionless number. The coefficient of variation for the FEV1 data is
Case Studies
Nicholas Stergiou in Nonlinear Analysis for Human Movement Variability, 2018
Recently, in addition to the study of various gait parameters, Amende et al. (2005) made an attempt to examine stride-to-stride variability in mouse models of Parkinson’s disease and Huntington’s disease. Measures of stride-to-stride variability were determined as the standard deviation and the coefficient of variation. The standard deviation reflects the dispersion about the average value for a parameter. The coefficient of variation was calculated from the equation: 100 × standard deviation/mean value. The motor speed was set to 34 cm/s for all mice. Approximately, 3 s of videography was collected for each walking mouse to provide more than seven sequential strides. Parkinson’s mice demonstrated significant gait disturbances, including shortened stride length, increased stride frequency, and increased stride-to-stride variability, symptoms characteristic of patients with Parkinson’s disease. Huntington’s mice demonstrated an increased forelimb stride-to-stride variability and a more open paw placement angle of the hindlimbs. Gait failure in Huntington’s mice resulted from an ability of the hindlimbs to engage in stepping while forelimb gait remained intact. Findings of Amende et al.’s study provide a basis for additional studies of gait measurements and their variability in mouse models of neurodegenerative diseases.
Control of breathing
Andrew M. Luks, Philip N. Ainslie, Justin S. Lawley, Robert C. Roach, Tatum S. Simonson in Ward, Milledge and West's High Altitude Medicine and Physiology, 2021
The range of HVR found in healthy sea level residents is wide. The coefficient of variation varies between 23 and 72% in different studies (Cunningham et al. 1964; Weil et al. 1970; Rebuck and Campbell 1974). Interestingly, on the basis of studies in pairs of monozygotic and dizygotic twins, HVR has been repeatedly shown to be heritable in a number of age groups spanning infancy to adulthood (MacLeod et al. 2013). Various groups of subjects at sea level have been shown to have lower HVRs than age-matched controls, for instance endurance athletes (Byrne-Quinn et al. 1971) and elite synchronized swimmers (Bjurstrom and Schoene 1987). With increasing age HVR becomes lower (Kronenberg and Drage 1973; Poulin et al. 1993). Alcohol (Sahn et al. 1974) and respiratory depressant drugs and anesthetics also inhibit HVR (Davis et al. 1982).
Effect of Seminar on Compassion on student self-compassion, mindfulness and well-being: A randomized controlled trial
Published in Journal of American College Health, 2018
Celine M. Ko, Fran Grace, Gilbert N. Chavez, Sarah J. Grimley, Emily R. Dalrymple, Lisa E. Olson
Participants were tested between 2 – 5PM, having been awake for a minimum of six hours prior to their appointment. The time of a participant's appointment was matched in time 1 and time 2. Saliva was collected using an oral swab (Salimetrics, State College, PA) after five minutes of listening to an mp3 of calming beach sounds. All saliva samples were stored at −20°C immediately after collection and later analyzed using the sAA kinetic enzyme assay kit (Salimetrics, State College, PA). The AgileReader™ ELISA Plate Reader (ACTgene, Inc., Piscataway, NJ) was used for the kinetic sAA assay. The average coefficient of variation on inter-assay replicates (non log-transformed values) was 9.6%. Coefficient of variation is defined as the standard deviation of replicates divided by the mean of replicates; it is a proportional measure of the precision of an assay. The manufacturer of this assay (Salimetrics) states that coefficient of variation values below 15% are acceptable.49
Orthotic shorts for improving gait and walking in multiple sclerosis: a feasibility study
Published in Disability and Rehabilitation, 2023
Nicola Snowdon, Sionnadh McLean, Hilary Piercy, Matthew A. Brodie, Jon Wheat
The GAITRite system used was the GAITRite 3.8, comprising a 5.18 m long walkway. The GAITRite provides excellent reliability for assessing most spatiotemporal gait parameters in MS [24]. Because step width is more variable, reliable assessment requires multiple passes of the GAITRite mat [25]. Each participant completed four passes of the mat at each test, providing a mean of 24 steps per test (SD 4.3; range 16–31). Participants were asked to walk at a comfortable but purposeful pace. They commenced walking 2 m before the start of the mat and finished each walk 2 m after the end of the mat. Mean values for gait speed were downloaded from the GAITRite software. Values of step length, step width. and stride time were downloaded for each step or stride and used to calculate means and variability. Variability was expressed as coefficient of variation and standard deviation.
Quality of extracellular vesicle images by transmission electron microscopy is operator and protocol dependent
Published in Journal of Extracellular Vesicles, 2019
L. G. Rikkert, R. Nieuwland, L. W. M. M. Terstappen, F. A. W. Coumans
Statistical analysis was performed in Prism 7.0 (GraphPad, La Jolla, California, USA). The coefficient of variation (%CV) is defined as the standard deviation divided by the mean times 100%. For each image, the number of EVs, the % cup-shape, the image quality and the background quality was evaluated. Statistical analysis was performed to determine whether observed differences between grids or between protocols can be explained by chance alone. Within each protocol, an analysis of variance (ANOVA) was applied to compare the five images for each grid. The student’s t-test was applied to compare the operator-selected images to the images taken at predefined locations. Between protocols, the student’s t-test was applied to compare the 15 images for each protocol. No significant differences (p > 0.05) are expected if the TEM image is not substantially affected by either the practise of operator image selection or the TEM preparation protocol.
Related Knowledge Centers
- Standard Score
- Statistical Dispersion
- Standard Deviation
- Analytical Chemistry
- Assay
- Psychology
- Neuroscience
- Quartile Coefficient of Dispersion
- Sample Size Determination
- Reliability Engineering