AN ANALYSIS OF TRANSFORMATIONS
AN ANALYSIS OF TRANSFORMATIONS
复制标题
DOI：
10.1111/j.2517-6161.1964.tb00553.x
复制
发表时间：
1964-01-01
影响因子：
5.8
通讯作者：
COX, DR
中科院分区：
文献类型：
--
作者：
BOX, GEP;COX, DR
在数据分析中，经常假设观测值sy1，y2，...，yn独立地服从正态分布，方差为常数，期望值由一个参数集θ的线性模型确定。在本文中，我们作出限制较少的假设，这样一个正常的，同方差的，线性模型是适当的一些适当的变换后，已被应用到他们的。通过计算似然函数和相关的后验分布来推断变换和线性模型的参数。正态性、同方差性和可加性对变换的贡献被分离。本方法的关系，以较早的程序寻找转换进行了讨论。并以实例说明了该方法。
In the analysis of data it is often assumed that observationsy1,y2, …,ynare independently normally distributed with constant variance and with expectations specified by a model linear in a set of parameters θ. In this paper we make the less restrictive assumption that such a normal, homoscedastic, linear model is appropriate after some suitable transformation has been applied to they's. Inferences about the transformation and about the parameters of the linear model are made by computing the likelihood function and the relevant posterior distribution. The contributions of normality, homoscedasticity and additivity to the transformation are separated. The relation of the present methods to earlier procedures for finding transformations is discussed. The methods are illustrated with examples.