[R] Regression fitting

Source: Internet
Author: User

The following example

> Fit <-LM (y~x, data =data01)>Summary (FIT) CALL:LM (Formula= data01$p ~ data01$m, data =data01) Residuals:min 1Q Median 3Q Max-4.2070-2.9109-0.9089  2.9160  8.8993coefficients:estimate Std. Error t value Pr (>|t|) (Intercept)6.340e+00  7.472e-01   8.485 4.26e-09***x1.305e-04  2.657e-05   4.911 3.87e-05***---signif. Codes:0‘***’0.001‘**’0.01‘*’0.05‘.’0.1‘ ’1residual standard error:3.575On -degrees of Freedommultiple R-squared:0.4718, Adjusted r-squared:0.4522F-statistic:24.11On1and -DF, P-value:3.872e-05

Coefficients:

Four values in turn are:

Estimate Std. Error t value Pr (>|t|)
Valuation, standard error, T-value, p-value

We can determine the significance of the corresponding explanatory variable directly by comparing the P value with our pre-set 0.05 (the original hypothesis is that if the coefficient is significantly 0,p<0.05, the original hypothesis is rejected, that is, the corresponding variable is significantly not 0). We can see that the intercept term intercept and X are considered to be significantly less than 0 at p 0.05, passing the significance test

Goodness of Fit r^2

We see multiple r-squared and adjusted r-squared these two values, in fact we often call "goodness of Fit" and "modified goodness of fit", refers to the regression equation to the sample fitting degree geometry, here we can see that the modified goodness of fit = 0.4522, that is, the approximate fitting degree of less than 50%, indicating that the degree of fitting is very general. This value is of course the higher the better, of course, there are many ways to improve the goodness of fit, and when it reaches a certain level, we think it is almost. In particular, there is a very complex decision content, interested can see: http://baike.baidu.com/view/657906.htm

F-statistic

We often say that f-statistic (f-test), often used to determine the overall significance of the equation test, its p-value of 3.872e-05, is obviously <0.05, we can think of the equation at p=0.05 level or through the significance of the test.

Summarize:
T test is to test the significance of explanatory variables;
R-squared is to see how the equation fits;
The F-Test is to test the overall significance of the equation;

[R] Regression fitting

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.