Diagnosing Collinearity-influential Observation In Medical Multiple Regression

In the medical research, irregular points in regression may induce some problem which make regression equation become unstable, especially collinearity, it is troublesome and its adverse effects on least squares estimation are well known, when an observation in regression analysis has very large values on two or more predictor variables, artificial collinearities can be induced, observations may be create collinearity or mask collinearity, we have named the observations for collinearity-influential, so, diagnosing collinearity -influential are provided in order to regression analysis being correctly used in medical research. 1 .The definition, origin of main contents of collinearity is introduced briefly, including some traditional methods about diagnosing collinearity. 2.In the linear model, It is found that some observation playan important role, A state of collinearity is sometimes masked or created by one or two observations, In the paper, we introduced definition, origin of collinearity-influential points.3.We provided three measures that diagnosed collinearity-influential. The first measures is the collinearity influence of each row of X would be measured by the relative change in the condition number the results from its deletion. The second measures is the Trace-to-Det Ratio, The final measures is Leverage.4.In the paper, we used the two examples, through analyzing the examples, we found some observations induced or masked the collinearity. They has influenced regression equation analysis, but regression equation can't correctly express in the medical research.