search for: tricub

Hi I am trying to get the tricube weights from the loess outputs as I need to calculate an error function which requires the weight. So I have used the following example from the R: cars.lo <- loess(dist ~ speed, cars, span=0.5, degree=1, family="symmetric") Then i try to get the weights: cars.lo$weights [1] 1 1...

...near polynomial fit is + \file{src/library/stats/src/lowess.doc}. Normally a local linear polynomial fit is used, but under some circumstances (see the file) a local constant fit can be used. \sQuote{Local} is defined by the distance to the \code{floor(f*n)}th nearest neighbour, and tricubic weighting is used

...he data set according to these deviations. This way the first row has the (x0, NA) value. 4. I drop the first row. 5. I divide all the deviations by the m-th one, where m is the number of points used in local fitting - m = floor(n*span) where n is the number of points. 6. I calculate the "tricube" weights and assign 0's to the negative ones. This eliminates all the points except the m points of interest. 7. I fit a linear weighted regression using lm. 8. I predict y(x0) from this linear model. This is basically the same procedure I use to predict at the x values from the data se...

...stance from x (with differences in `parametric' variables being ignored when computing the distance). The size of the neighbourhood is controlled by &alpha; (set by span or enp.target). For &alpha; < 1, the neighbourhood includes proportion &alpha; of the points, and these have tricubic weighting (proportional to (1 - (dist/maxdist)^3)^3. For &alpha; > 1, all points are used, with the `maximum distance' assumed to be &alpha; times the actual maximum distance. </SNIP> I understand the situation when alpha is less than one, presuming it uses the same conv...

...stance from x (with differences in `parametric' variables being ignored when computing the distance). The size of the neighbourhood is controlled by &alpha; (set by span or enp.target). For &alpha; < 1, the neighbourhood includes proportion &alpha; of the points, and these have tricubic weighting (proportional to (1 - (dist/maxdist)^3)^3. For &alpha; > 1, all points are used, with the `maximum distance' assumed to be &alpha; times the actual maximum distance. </SNIP> I understand the situation when alpha is less than one, presuming it uses the same conv...

...;m looking at is more complex so I need a small span value to allow for a close fit. I foresee that changing the "weigthing" is the way to go but I do not really understand how the "weight" option is used (I tried to change it and nothing happened), and also the embedded "tricubic weighting" does not seem changeable. So any idea would be very welcome. Emmanuel

...each element in w I want to find a good match (subscript number) of an element in x. x and w can be long. Instead of just finding the closest match I want to use weighted multinomial sampling (which I've already figured out once I have the probabilities) where the probabilities come from the tricube function of absolute differences between donor and target values, but normalized to sum to one, and using the maximum absolute difference as the scaling factor. This is similar to the loess weighting function with f=1. Here's code that works, to get the probability matrix to use for sampling...

SAS proc rank has ties options of high and low that would allow producing ranks of the type found in the sports pages, e.g., rank (c(1,1,2,2,2,2,3)) == 1 1 3 3 3 3 7 Could R support these ties.methods?

...nfidence intervals for a loess smoother (function: loess()), but have been thus far unsuccessful. The CI for the loess predicted values, yhat, are apparently yhat +- t*s * sqrt(w^2), where s is the residual sum of squares and w is the weight function Correct me of I'm wrong, but R uses the tricubic function (1-abs(z)^3)^3, where z = (x-xi)/h, where h is the the number of neighboring values within the bandwidth. Assuming that's correct, here is my code (for the first observation in x1: x1 <- 1:156 # x set.seed(123) y <- arima.sim(list(order=c(2,0,0), ar=c(1,-.1)),...

...each element in w I want to find a good match (subscript number) of an element in x. x and w can be long. Instead of just finding the closest match I want to use weighted multinomial sampling (which I've already figured out once I have the probabilities) where the probabilities come from the tricube function of absolute differences between donor and target values, but normalized to sum to one, and using the maximum absolute difference as the scaling factor. This is similar to the loess weighting function with f=1. Here's code that works, to get the probability matrix to use for sampling...