Centring in regression analyses: a strategy to prevent errors in statistical inference
Centring in regression analyses: a strategy to prevent errors in statistical inference
复制标题
DOI：
10.1002/mpr.170
复制
发表时间：
2004-01-01
影响因子：
3.1
通讯作者：
Blasey, CM
中科院分区：
文献类型：
--
作者：
Kraemer, HC;Blasey, CM
回归分析可能是医学研究中使用最广泛的统计工具。回归分析的集中很少出现在培训中，也不常在研究论文中报道。集中是为每个预测器选择一个参考值，并根据该参考值对数据进行编码，使估计和检验的每个回归系数都与研究问题相关的过程。在回归分析中使用非中心数据，即以原始分数格式输入预测因子的常见做法，往往会导致不一致和误导性的结果。不必要的定心代价很小，但必要时不定心的代价可能很大。因此，最好总是以回归分析为中心。我们提出一个简单的默认定心策略：(1)编码所有二进制自变量+1/2；(2)将所有有序自变量编码为与其中位数的偏差；(3)将具有m种可能响应的分类自变量的所有“虚拟变量”编码为1-1/m和-1/m，而不是1和0；(4)从中心预测器计算交互项。当没有令人信服的证据来集中时，使用这种默认策略可以防止统计推断中的大多数错误，并且它的常规使用使用户对集中问题敏感。
Regression analyses are perhaps the most widely used statistical tools in medical research. Centring in regression analyses seldom appears to be covered in training and is not commonly reported in research papers. Centring is the process of selecting a reference value for each predictor and coding the data based on that reference value so that each regression coefficient that is estimated and tested is relevant to the research question. Using non-centred data in regression analysis, which refers to the common practice of entering predictors in their original score format, often leads to inconsistent and misleading results. There is very little cost to unnecessary centring, but the costs of not centring when it is necessary can be major. Thus, it would be better always to centre in regression analyses. We propose a simple default centring strategy: (1) code all binary independent variables +1/2; (2) code all ordinal independent variables as deviations from their median; (3) code all 'dummy variables' for categorical independent variables having m possible responses as 1-1/m and -1/m instead of 1 and 0; (4) compute interaction terms from centred predictors. Using this default strategy when there is no compelling evidence to centre protects against most errors in statistical inference and its routine use sensitizes users to centring issues.