TEST 45:

From documentation on loess (local polynomial regression fitting)

> cars.lo <- loess(dist ~ speed, cars)

> predict(cars.lo, data.frame(speed = seq(5,30,1)), se=TRUE)

$fit

[1] 7.810489 10.041808 12.567960 15.369183 18.425712 21.828039 25.539675

[8] 29.350386 33.230660 37.167935 41.205226 45.055736 48.355889 49.824812

[15] 51.986702 56.445263 62.008703 68.529340 76.193111 85.142467 95.323096

[22] NA NA NA NA NA

$se.fit

[1] 7.568539 5.943649 4.976453 4.515801 4.316362 4.030120 3.750561 3.715593

[9] 3.776298 4.091044 4.708759 4.244697 4.035236 3.752765 4.004017 4.056945

[17] 4.005540 4.065234 4.579053 5.948757 8.300416 NA NA NA

[25] NA NA

$residual.scale

[1] 15.29233

$df

[1] 44.62733

TEST 46:

cars.lo2 <- loess(dist ~ speed, cars, control = loess.control(surface="direct"))

> predict(cars.lo2, data.frame(speed=seq(5,30,1)), se=TRUE)

$fit

[1] 7.741006 9.926596 12.442424 15.281082 18.425712 21.865315

[7] 25.713413 29.350386 33.230660 37.167935 41.205226 45.781544

[13] 48.355889 50.067148 51.986702 56.445263 62.025404 68.569313

[19] 76.193111 85.053364 95.300523 106.974661 120.092581 134.665851

[25] 150.698545 168.190283

$se.fit

[1] 7.565991 5.959097 5.012013 4.550013 4.321596 4.119331 3.939804

[8] 3.720098 3.780877 4.096004 4.714469 4.398936 4.040129 4.184257

[15] 4.008873 4.061865 4.033998 4.078904 4.584606 5.952480 8.306901

[22] 11.601911 15.792480 20.864660 26.823827 33.683999

$residual.scale

[1] 15.31087

$df

[1] 44.55085

TEST 47:

> cars.spl <- smooth.spline(speed, dist, df=6.4)

> plot(cars.spl)

>

TEST 48:

scatter.smooth(speed, dist)