l1line computes the least absolute deviation line from scatterplot data. It gives the estimate b0 and b1 that minimizes sum_i=1,n |y_i - b0 - b1 x_i |.
Semiparametric test for I(0) of a time series against fractional alternatives, i.e., long-memory and antipersistence. The test is semiparametric in the sense that it does not depend on a specific parametric form of the spectrum in the neighborhood of the zero frequency. The first argument of the fu
locpoldis computes the local polynomial estimator without mixed terms but allows for including a linear part in the regression model. It is using the quartic kernel.
computes the Nadaraya-Watson leave-one-out estimator without binning using the quartic kernel. Prior to estimation, looreg sorts the data. The sorted data, along with the sorted leave-one-out regression estimates, are returned as an output.
computes the so-called Lp-distances between the rows of a data matrix. In the case p=1 (absolute metric) or p=2 (Euclidean metric) one should favour the function DISTANCE.
Estimates the derivative of a regression function (including the 0th derivative) by local polynomial fits on a grid. This quantlet can be used for univariate or multivariate regression estimation.
lprotint computes the integral of the (p+1)st derivative of a polynomial of order (p+3), this function is used to find rule-of-thumb bandwidth for local polynomial regression and derivative estimation