Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Maarten Buis <maartenlbuis@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: new version hangroot available from SSC |

Date |
Fri, 18 Nov 2011 16:46:05 +0100 |

Thanks to Kit Baum a new version of the -hangroot- package is now available from SSC. A hanging rootogram is graph for comparing the distribution of a variable with a theoretical distribution. It is a variation on a histogram with the density function of a normal distribution plotted on top of it, in that the bars are "hanging" from the normal distribution rather than "standing" on the x-axis. This way the deviations from the theoretical distribution are visible as deviations from the horizontal line y=0, making it much easier to spot patterns in these deviations. Moreover, the y-axis is changed to represent the square root of the frequencies rather than frequencies. The logic behind that is that the frequencies can be thought of as counts and large counts tend to be more variable than small counts. This way it becomes hard to compare the residuals from large bars with small bars. The square root transformation tends to make the variance more equal, and thus making it easier to compare across bins. Examples of these graphs can be found here: <http://www.maartenbuis.nl/software/hangroot.html> This update contains a large number of changes: 1) It can now be used after parametric regression models with covariates to compare the marginal distribution implied by that regression model with the distribution of the dependent variable. The logic is the same as that of -margdistfit-, which I announced earlier today <http://www.stata.com/statalist/archive/2011-11/msg00926.html>. 2) It can now represent new distributions: zero inflated Poisson, negative binomial (I and II) and the zero inflated negative binomial. 3) It can plot simulations from the theoretical distribution on top of the graph, so that one can see what kind of variability one could reasonably expect. 4) It has been thoroughly rewritten. Over time the -hangroot- has grown considerably, and after such a period of "organic growth" it is often useful to rewrite the program such that it better fits the new tasks. To install this package type in Stata -ssc install hangroot-, to update it type in Stata -ssc install hangroot, replace- or -adoupdate, update-. I hope some of you will find it useful, Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl -------------------------- * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**RE: st: Confidence intervals: saving -proportion- estimates to a .dta or .csv file last estimates not found** - Next by Date:
**Re: st: RE: new package margdistfit available on SSC** - Previous by thread:
**st: bootstrap p-value and predictions** - Next by thread:
**st: Intermittent crash: opening Data Editor, using SSH X-forwarding** - Index(es):