Belgium phone calls data

The file contains the annual numbers of telephone calls, in Belgium for 1950-1973.

year – last two digits of the year.

calls – number of telephone calls made (in millions of calls)

Least squares

## 
## Call:
## lm(formula = calls ~ year)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -78.97 -33.52 -12.04  23.38 124.20 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)   
## (Intercept) -260.059    102.607  -2.535   0.0189 * 
## year           5.041      1.658   3.041   0.0060 **
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 56.22 on 22 degrees of freedom
## Multiple R-squared:  0.2959, Adjusted R-squared:  0.2639 
## F-statistic: 9.247 on 1 and 22 DF,  p-value: 0.005998

Robust regression

Huber

rrhub.lm <- rlm(calls~year, psi = psi.huber,maxit=50)
    print(rrhub.lm$coef)

## (Intercept)        year 
##  -102.62220     2.04135

Hampel

  rrham.lm <- rlm(calls~year, psi=psi.hampel)
    print(rrham.lm$coef)

## (Intercept)        year 
## -248.099666    4.824029

Tukey’s bi-square

   rrtuk.lm <- rlm(calls~year, psi=psi.bisquare)
     print(rrtuk.lm$coef)

## (Intercept)        year 
##  -52.302456    1.098041

least trimmed squares

   lts.lm <- lqs(calls~year,method="lts")
     print(lts.lm$coef)

## (Intercept)        year 
##  -56.162443    1.158824

least median of squares

      lms.lm <- lqs(calls~year,method="lms")
      print(lms.lm$coef)

## (Intercept)        year 
##    -55.9475      1.1550