Abstract
Loss of data from an experiment can diminish the accuracy of estimation of a treatment mean in two ways, by reducing (1) the number of observations on which the mean is based, and (2) the efficiency of estimation. It is assumed that the design was initially orthogonal, and that missing plot values are to be substituted in the usual way. Taylor1 has studied the effect of missing plots on the standard errors of the differences of treatment means in randomized block designs ; recently I needed to know the effect on the errors of the means themselves.
This is a preview of subscription content, access via your institution
Access options
Subscribe to this journal
Receive 51 print issues and online access
$199.00 per year
only $3.90 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
Similar content being viewed by others
References
Taylor, J., Nature, 162, 262 (1948).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
PEARCE, S. Loss of Information brought about by Loss of Data. Nature 184, 1826 (1959). https://doi.org/10.1038/1841826a0
Issue date:
DOI: https://doi.org/10.1038/1841826a0
