The measurement of linkage in heredity / by K. Mather.

  • Kenneth Mather
Date:
[1938]
Catalogue details

Licence: Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)

Credit: The measurement of linkage in heredity / by K. Mather. Source: Wellcome Collection.

    26/152 (page 12)
    of one class and 20 of the other, an estimate of the frequency of gametes which give rise to the first kind of individual would be This is not J, but it must be considered as an estimate of J, because the family is in keeping with the backcross expectation, the deviation being ascribable to pure sampling error. Thus we require some measure of the confi dence which can be reposed in an estimate of some parameter. This is given by the standard error of the estimate, or very often by the variance , which is the square of the standard error. The variance and standard error are measures of the spread of the distribution of the estimate round its true value, the parameter, and so are measures of the precision with which the estimate is made. The method of maxi mum likelihood always has the maximum precision possible as measured by this means. These principles, outlined above for simple cases, are the bases of all methods of analysing genetical data. The frequency distribution, or such statistics as specify it, of some quantity or quantities are cal culated and are used in the test of the hypothesis. Complications may be introduced by complexities or shortcomings of the data, and the analysis may need to be complicated to accommodate such data, but the essentials of the methods remain the same.