Volume 1
A text-book of experimental psychology : with laboratory exercises / by Charles S. Myers.
- Charles Samuel Myers
- Date:
- 1911
Licence: Public Domain Mark
Credit: A text-book of experimental psychology : with laboratory exercises / by Charles S. Myers. Source: Wellcome Collection.
140/370 page 118
![The Mode.—The ‘mode’ is the value of that measurement which occurs more frequently than any other in a large series of observations. The Mean. — The ‘mean’ or ‘average1’ is obtained by dividing the sum of the values by the number of the indi¬ vidual observations. The reliability of the mean depends in the first place, on the number of the observations which have been made, and in the second place, on the variability of the individual values, that is, on the extent to which they each diverge from the mean. No reliance can be placed on a pub¬ lished mean unless it is accompanied by information on these two points. The variability of the individual values may be best expressed either by the ‘ mean variation ’ or by the ‘ standard deviation.’ The Mean Variation.—The ‘mean variation’ or the ‘mean variable error,’ commonly denoted by the letters in. v., is the mean of the individual variations from the mean, regardless of algebraic sign (exp. 85). The Standard Deviation. — The ‘standard deviation5 or the ‘ mean square error2 *,5 denoted by the letter <r, is the square root of the mean of the squares of the individual variations from the mean (exp. 85). [The Coefficient of Variation.—The deviations of individual data from their mean depend for their absolute size, not only on the uniformity of the experimental conditions, but on the absolute size of the mean. Thus a mean of 200 which has a standard deviation of 20 need not be less reliable than a mean of 100 which has a standard deviation of 10. Accordingly, a measure of relative dispersion is sometimes employed, the standard deviation being expressed as a percentage of the mean. This measure has been termed the ‘ coefficient of variation 5 (exp. 85).] [Significant Differences.—It is obvious that the mean of so small a series of observations as that with which we have 1 These terms are used throughout this book to refer to the arithmetic mean, but sometimes they are given a wider signification. 2 ‘ Root mean square error ’ is a more -accurate, though more cumbrous, expression.](https://iiif.wellcomecollection.org/image/b3135984x_0001_0140.jp2/full/800%2C/0/default.jpg)
