Multiple Linear Regression using fitlm function

Question

ANURAG DEEPAK 2020-1-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/500877-multiple-linear-regression-using-fitlm-function

回答： Image Analyst 2020-1-18

采纳的回答： Star Strider

Hello Sir, why i am not getting the intercept for the other variables?

>> lm=fitlm(X,TAG)

Warning: Regression design matrix is rank deficient to within machine precision.

> In classreg.regr.CompactTermsRegression/checkDesignRank (line 35)

In LinearModel.fit (line 1237)

In fitlm (line 121)

lm =

Linear regression model:

y ~ 1 + x1 + x2 + x3 + x4 + x5 + x6 + x7

Estimated Coefficients:

Estimate SE tStat pValue

__________ __ _____ ______

(Intercept) 0 0 NaN NaN

x1 0 0 NaN NaN

x2 0.00037516 0 Inf NaN

x3 0.00021467 0 Inf NaN

x4 -0.16078 0 -Inf NaN

x5 0.68268 0 Inf NaN

x6 -0.0013354 0 -Inf NaN

x7 0 0 NaN NaN

Number of observations: 5, Error degrees of freedom: 0

R-squared: 1, Adjusted R-Squared: NaN

F-statistic vs. constant model: NaN, p-value = NaN

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Star Strider 2020-1-18

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/500877-multiple-linear-regression-using-fitlm-function#answer_410763

In a linear regression of any sort, there is only one intercept.

2 个评论
显示无隐藏无

ANURAG DEEPAK 2020-1-18

Then sir how to deal with such situation, 7 independent variable and 1 dependent variable?

Star Strider 2020-1-18

If you want to ssee what the intercepts of the individual variables are, you need to regress them individually. However, the entire idea of a multiple linear regression is to regress the various predictor variables together, to get a unified idea of how they all interact. Note that they do not have to be individual predictors, and can be interaction terms (predictors multiplised together) that distorts the idea of an intercept.

If you want to see what variables best predict the dependent variable, use the stepwiselm function.

请先登录，再进行评论。