matlab曲线拟合sse等含义,Matlab曲线拟合SSE等含义.doc

Matlab曲线拟合SSE等含义.doc

使用过Matlab的拟合、优化和统计等工具箱的网友，会经常遇到下面几个名词SSE和方差、误差平方和The sum of squares due to errorMSE均方差、方差Mean squared errorRMSE均方根、标准差Root mean squared errorR-square确定系数Coefficient of determinationAdjusted R-squareDegree-of-freedom adjusted coefficient of determination下面我对以上几个名词进行详细的解释下，相信能给大家带来一定的帮助一、SSE和方差该统计参数计算的是拟合数据和原始数据对应点的误差的平方和，计算公式如下SSE越接近于0，说明模型选择和拟合更好，数据预测也越成功。接下来的MSE和RMSE因为和SSE是同出一宗，所以效果一样二、MSE均方差该统计参数是预测数据和原始数据对应点误差的平方和的均值，也就是SSE/n，和SSE没有太大的区别，计算公式如下三、RMSE均方根该统计参数，也叫回归系统的拟合标准差，是MSE的平方根，就算公式如下在这之前，我们所有的误差参数都是基于预测值y_hat和原始值y之间的误差即点对点。从下面开始是所有的误差都是相对原始数据平均值y_ba而展开的即点对全四、R-square确定系数在讲确定系数之前，我们需要介绍另外两个参数SSR和SST，因为确定系数就是由它们两个决定的1SSRSum of squares of the regression，即预测数据与原始数据均值之差的平方和，公式如下2SSTTotal sum of squares，即原始数据和均值之差的平方和，公式如下细心的网友会发现，SSTSSESSR，呵呵只是一个有趣的问题。而我们的“确定系数”是定义为SSR和SST的比值，故其实“确定系数”是通过数据的变化来表征一个拟合的好坏。由上面的表达式可以知道“确定系数”的正常取值范围为0 1，越接近1，表明方程的变量对y的解释能力越强，这个模型对数据拟合的也较好After using graphical s to uate the goodness of fit, you should examine the goodness-of-fit statistics. Curve Fitting Toolbox software supports these goodness-of-fit statistics for parametric models The sum of squares due to error SSE R-square Adjusted R-square Root mean squared error RMSEFor the current fit, these statistics are displayed in the Results list box in the Fit Editor. For all fits in the current curve-fitting session, you can compare the goodness-of-fit statistics in the Table of fits.Sum of Squares Due to ErrorThis statistic measures the total deviation of the response values from the fit to the response values. It is also called the summed square of residuals and is usually labeled as SSE.A value closer to 0 indicates that the model has a smaller random error component, and that the fit will be more useful for prediction.