Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Just a note

In reality it is almost impossible to objectively quantify either the importance of, or your confidence in, an observation - so the best you can do is to apply a relative weighting. Inescapably, therefore, any results you obtain will reflect those preconceptions. However, in some situations weighting can be applied in terms of the number of observations each result represents.

When weighting series of observations, either temporal or spatial, you weight them according to their relative (presumed) contribution to the statistic in question. In these situations you usually want to substitute, say, the value of an observation in month X with the mean of a number of preceding or following monthly observations - all other observations having zero weight. Very often such a simple, all or nothing, weighting is too simplistic - and more complex weighting arrangements are required.