Module R’Stat1 : La régression linéaire polynomiale

Novembre 2019 ; IRD-Montpellier-France

CC BY-NC-ND 3.0

Reg. lin. poly. : exemple

Relation entre pression atmosphérique et température

## 'data.frame':    1000 obs. of  3 variables:
##  $ temperature: num  26.78 9.79 3.85 6.91 26.58 ...
##  $ pressure   : num  995 1039 1066 1032 997 ...
##  $ date       : num  1.57e+09 1.55e+09 1.55e+09 1.55e+09 1.56e+09 ...

## 
## Call:
## lm(formula = myY ~ poly(myX, polyN))
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -13.0500  -2.1855   0.2745   2.4241  10.2494 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         10.7864     0.1162   92.87   <2e-16 ***
## poly(myX, polyN)1 -231.5078     3.6730  -63.03   <2e-16 ***
## poly(myX, polyN)2   65.3138     3.6730   17.78   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.673 on 997 degrees of freedom
## Multiple R-squared:  0.8114, Adjusted R-squared:  0.811 
## F-statistic:  2144 on 2 and 997 DF,  p-value: < 2.2e-16