Estimating missing observations in ANOVA

Autor:	J. F. Reynolds
Rok vydání:	1995
Předmět:	Mathematics (miscellaneous) Residual sum of squares Explicit formulae Applied Mathematics Statistics Analysis of variance Education Mathematics
Zdroj:	International Journal of Mathematical Education in Science and Technology. 26:895-901
ISSN:	1464-5211 0020-739X
DOI:	10.1080/0020739950260610
Popis:	It is well known that formulae exist for estimating missing observations in ANOVA. These formulae are derived by minimizing the residual sum of squares. The formulae apply to situations where there is a single missing observation. If there are two missing observations, the recommended procedure is to guess one of them, use the appropriate formula to estimate the other, then use the formula again to estimate the first, continuing iteratively until convergent estimates for the two missing observations are reached. The purpose of this note is to show that explicit formulae can be found for the two missing observations, which can therefore be calculated directly without the need for an iterative procedure.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a9326ce1378c75fc42e8f7d90a9a1d7b https://doi.org/10.1080/0020739950260610 Zobrazit plný text záznamu