Elegant mathematical proof of theorem and derivation of useful parameter, the Foos Coefficient of Covariance for use with ANOVA or other replicated data sets in both design and analysis phases of formal research.
Very elegant and useful theorem developed by Alan Foos. Proof that statistical differences between blocks (replications) can be expressed in terms of covariance of treatment pairs across blocks. An FCC for treatments can also be calculated by substitution of the treatment mean square in the formula. From this proof. the FCC, Foos coefficient of covariance is derived. The FCC is a useful parameter giving the average ratio of covariance to variance of treatments across bllocks, or indeed, not just treatments but any set of data across its replications. The FCC can therefore be used to measure the degree of uniformity across orthogonal sets of data. The FCC is 1 (100%) for perfect uniformity across replications, whether treatments or blocks, and 0 for totally random variation. FCC=1 is equivalent to p(F)=0 and FCC=0 is equivalent to p(F)=100. Herein is proof of the theorem and derivation of the FCC.
Our human genome is full of viruses similar to HIV-1. These have played an important role in human evolution and still play an important role in human embryology and day-to-day chemistry. Just how important are they to our evolution past and future?
Where do viruses, such as Ebola and HIV, come from and why they are so aggressive? This book changed tenets of evolutionary virology, developing the concepts of aggressive symbiosis and plague culling, which explain much of the horror of plague virus
