The name is absent

Saved results

bspline saves in r():

Scalars

r(xvar)        Х-variable specified by xvar option

Matrices

r(knotv) row vector of knots

frencurv saves all of the above results in r(), and also the following:

Macros
r(refpts) final list of reference points

Matrices
r(refv) row vector of reference points

The result r(nincomp) is the number of values of xvar outside the completeness region of the space of splines defined by
the reference splines or В-splines. The number lists r(knots) and r (refpts) are the final lists after any left and right extensions
carried out by bspline or frencurv, and the vectors r(knotv) and r (ref v) contain the same values in double precision (mainly
for programmers). The scalars r(xinf) and r(xsup) are knots, such that the completeness region is r(xinf) ≤ x < r(xsup).

Acknowledgements

The idea for the name frencurv came from Nick Cox of Durham University, UK, who remarked that the method was like
an updated French curve when I described it on Statalist.

References

de Boor, C. 1978. A practical guide to splines. New York: Springer-Verlag.

Sasieni, P. 1994. snp7: Natural cubic splines. Stata Technical Bulletin 22: 19-22. Reprinted in Stata Technical Bulletin Reprints, vol. 4, pp. 171-174.

Unser M., A. Aldroubi, and M. Eden. 1992. On the asymptotic convergence of В-spline wavelets to Gabor functions. IEEE Transactions on Information
Theory 38: 864-872.

Wold, S. 1971. Analysis of kinetic data by means of spline functions. Chemica Scripta 1: 97-102.

——. 1974. Spline functions in data analysis. Technometrics 16: 1-11.

Ziegler, Z. 1969. One-sided Lι-approximation by splines of an arbitrary degree. In Approximations with Special Emphasis on Spline Functions, ed. I.
J. Schoenberg. New York: Academic Press.

sg152 Listing and interpreting transformed coefficients from certain regression models

J. Scott Long, Indiana University, [email protected]

Jeremy Freese, University of Wisconsin-Madison, [email protected]

Abstract: listcoef is a post-estimation command that facilitates the interpretation of estimated coefficients in regression models
for categorical, limited, and count dependent variables. The command provides options to list various transformations of
the estimated coefficients, such as percent change, factor change, and standardized coefficients. The user can restrict which
coefficients are listed by specifying a variable list or indicating a minimum significance level. The help option provides
details on the proper interpretation of coefficients.

Keywords: regression models, list coefficients, standardized coefficients, odds ratios, percent change coefficients, post-estimation.

Introduction

The most effective interpretation of regression models often requires the use of alternative transformations of the canonical
parameters that define a model. In Stata, each command for estimating a regression model lists estimates of these fundamental
parameters. In some cases, there are options to list transformations of the parameters, such as the or option to list odds
ratios in logit-type models or the beta option to list fully standardized coefficients for regress. Other programs, such as

<<   24   25   26   27   28   29   30   >>

More intriguing information