REGRESS_ywyuan_新浪博客

 REGRESS Multiple linear regression using least squares.​

使用最小二乘法多元线性回归。

1.  B = REGRESS(Y,X)

 returns the vector B of regression coefficients in the    linear model Y = X*B.  X is an n-by-p design matrix, with rows corresponding to observations and columns to predictor variables.  Y is an n-by-1 vector of response observations.     ​

返回返回线性模型Y=X*B的拟合系数矢量B。X是一个设计的 n x p 的矩阵，它的行对应观测值，列对应预测值。Y是一个n x 1的观测的响应向量。

2. [B,BINT] = REGRESS(Y,X)

returns a matrix BINT of 95% confidence    intervals for B.    

返回一个矩阵BINT，代表着矩阵B 95%的置信区间。 

3. [B,BINT,R] = REGRESS(Y,X)

returns a vector R of residuals.   ​

返回残差矢量R

4. [B,BINT,R,RINT] = REGRESS(Y,X)

returns a matrix RINT of intervals that can be used to diagnose outliers.  If RINT(i,:) does not contain zero,    then the i-th residual is larger than would be expected, at the 5%    significance level.  This is evidence that the I-th observation is an    outlier.    ​

返回一个可以诊断异常值的区间--矩阵RINT，如果RINT的第 i 行没有0，那么第 i 行的残差比预期的5%的显著水品大。这证明 I 行观测值是离群的。

 5. [B,BINT,R,RINT,STATS] = REGRESS(Y,X)

returns a vector STATS containing, in the following order, the R-square statistic, the F statistic and p value    for the full model, and an estimate of the error variance.     ​

返回一个矢量STATS依次包含：​

6. [...] = REGRESS(Y,X,ALPHA)

uses a 100*(1-ALPHA)% confidence level to    compute BINT, and a (100*ALPHA)% significance level to compute RINT.    

 使用100*（1-α）%的置信水平来计算BINT,使用100α%的

X should include a column of ones so that the model contains a constant    term.  The F statistic and p value are computed under the assumption    that the model contains a constant term, and they are not correct for    models without a constant.  The R-square value is one minus the ratio of    the error sum of squares to the total sum of squares.  This value can    be negative for models without a constant, which indicates that the    model is not appropriate for the data.    

If columns of X are linearly dependent, REGRESS sets the maximum    possible number of elements of B to zero to obtain a "basic solution",    and returns zeros in elements of BINT corresponding to the zero    elements of B.​​

如果X的列都线性相关，REGRESS 将

REGRESS treats NaNs(Not a Number) in X or Y as missing values, and removes them.​

拟合函数对于X或者Y里面的非数值的元素，认为他们是缺失的，并删除他们。