Talk:Generalized estimating equation

Statistics Low‑importance

	This article is within the scope of WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.StatisticsWikipedia:WikiProject StatisticsTemplate:WikiProject StatisticsStatistics articles
Low	This article has been rated as Low-importance on the importance scale.

Mathematics Low‑priority

	Mathematics portal This article is within the scope of WikiProject Mathematics, a collaborative effort to improve the coverage of mathematics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.MathematicsWikipedia:WikiProject MathematicsTemplate:WikiProject Mathematicsmathematics articles
Low	This article has been rated as Low-priority on the project's priority scale.

Formulation[edit]

Neither k nor $\beta$ are defined in this section. Though $\beta$ in particular may be commonly used to mean a particular regression parameter, these have to be defined or the mathematical formulation is just meaningless. Please define these terms for the readers of this page. Thanks. — Preceding unsigned comment added by Chafe66 (talk • contribs) 23:46, 13 April 2016 (UTC)[reply]

Thank you, @mark viking for adding definitions. Chafe66 (talk) 16:56, 12 May 2016 (UTC)[reply]

It's still missing plenty of definitions.

Y_{i}

is presumably the endogenous values being fit (but then why doesn't it have a

j

subscript?) and

N

is the number of subjects. But we don't have definitions of either of

k

,

\mu _{i}

. I suspect that there is some typo or omission in this equation given that

j,k

each occur only once. 165.123.230.45 (talk) 15:38, 9 October 2019 (UTC)[reply]

Is it semi-parametric? Other discussions linked to in this article (e.g. the stata command description) make it seem fully parametric. Stata describes it as requiring a full distributional assumption on the distribution and a fully specified link function -- thats parametric. R code manuals suggest the same -- requiring specification of a choice of distribution. Contrast with GLM seems to be more about changing the dependence assumptions between observations than about allowing for less in the way of distributional assumptions. — Preceding unsigned comment added by 143.231.249.133 (talk) 20:03, 31 March 2022 (UTC)[reply]