This article'slead sectionmay be too short to adequatelysummarize the key points. Please consider expanding the lead toprovide an accessible overview of all important aspects of the article.(November 2018)
Table of height and weight for boys over time. The growth curve model (also known as GMANOVA) is used to analyze data such as this, where multiple observations are made on collections of individuals over time.
Thegrowth curve model instatistics is a specific multivariate linear model, also known as GMANOVA (Generalized Multivariate Analysis-Of-Variance).[1] It generalizesMANOVA by allowing post-matrices, as seen in the definition.
Growth curve model:[2] LetX be ap×nrandom matrix corresponding to the observations,A ap×q withindesign matrix withq ≤ p,B aq×k parameter matrix,C ak×n between individual design matrix with rank(C) + p ≤ n and letΣ be apositive-definitep×p matrix. Then
defines the growth curve model, whereA andC are known,B andΣ are unknown, andE is a random matrix distributed asNp,n(0,Ip,n).
This differs from standardMANOVA by the addition ofC, a "postmatrix".[3]
Many writers have considered the growth curve analysis, among them Wishart (1938),[4] Box (1950)[5] and Rao (1958).[6] Potthoff and Roy in 1964;[3] were the first in analyzinglongitudinal data applying GMANOVA models.
GMANOVA is frequently used for the analysis of surveys, clinical trials, and agricultural data,[7] as well as more recently in the context of Radar adaptive detection.[8][9]
^Kollo, Tõnu; von Rosen, Dietrich (2005). ""Multivariate linear models" (chapter 4), especially "The Growth curve model and extensions" (Chapter 4.1)".Advanced multivariate statistics with matrices. Mathematics and its applications. Vol. 579. Dordrecht: Springer.ISBN978-1-4020-3418-3.
^Wishart, John (1938). "Growth rate determinations in nutrition studies with the bacon pig, and their analysis".Biometrika.30 (1–2):16–28.doi:10.1093/biomet/30.1-2.16.
^Ciuonzo, D.; De Maio, A.; Orlando, D. (2016). "A Unifying Framework for Adaptive Radar Detection in Homogeneous plus Structured Interference-Part I: On the Maximal Invariant Statistic".IEEE Transactions on Signal Processing.PP (99):2894–2906.arXiv:1507.05263.Bibcode:2016ITSP...64.2894C.doi:10.1109/TSP.2016.2519003.S2CID5473094.
^Seber, G. A. F.; Wild, C. J. (1989). ""Growth models (Chapter 7)"".Nonlinear regression. Wiley Series in Probability and Mathematical Statistics: Probability and Mathematical Statistics. New York: John Wiley & Sons, Inc. pp. 325–367.ISBN0-471-61760-1.
^Meade, Nigel (1984). "The use of growth curves in forecasting market development—a review and appraisal".Journal of Forecasting.3 (4):429–451.doi:10.1002/for.3980030406.
Kshirsagar, Anant M.; Smith, William Boyce (1995).Growth curves. Statistics: Textbooks and Monographs. Vol. 145. New York: Marcel Dekker, Inc.ISBN0-8247-9341-2.
Vonesh, Edward F.; Chinchilli, Vernon G. (1997).Linear and Nonlinear Models for the Analysis of Repeated Measurements. London: Chapman and Hall.{{cite book}}: CS1 maint: publisher location (link)