Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

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

From |
Nick Cox <njcoxstata@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Subtract Closest Cell Which has A Value |

Date |
Fri, 26 Oct 2012 20:06:33 +0100 |

All that said, the first step here is an interpolation that treats each series as a step function. Have you considered other interpolation methods, including linear (official -ipolate-) cubic (SSC -cipolate) cubic spline (SSC -csipolate-) ? Nick On Fri, Oct 26, 2012 at 9:49 AM, Nick Cox <njcoxstata@gmail.com> wrote: > This can be solved using the same techniques as for your previous problem. > > See my previous posting. > > You need a variable that is the previously observed value and one that > is the next observed value. You get those variables by copying down in > a cascade in the usual (panel id, time) order and then again after > reversing time. > > Then you use the previous value if the timeline date is positive and > the next value if it is negative. > > See also > > FAQ . . . . . . . . . . . . . . . . . . . . . . . Replacing missing values > . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . N. J. Cox > 2/03 How can I replace missing values with previous or > following nonmissing values? > http://www.stata.com/support/faqs/data/missing.html > > (Reversing time is one of the top tricks many people need occasionally > in Stata but often don't seem to know about.) > > NIck > > On Fri, Oct 26, 2012 at 3:41 AM, Lisa Wang <lhwang0925@gmail.com> wrote: >> Dear all, >> >> I have another question. I have two columns of values - variables A >> and B to make it simple. I would like to A-B in a new column C; >> however, column B has a lot of missing values (.), so it doesn't seem >> that simple. Variable A is complete, so no missing data. I would like >> Stata to find the nearest cell (data is already sorted by column D) >> with a value in column B to subtract off for each panel that I have. >> >> For instance, >> >> 51 . 31 >> 50 . 30 >> 47 20 27 >> 51 . 31 >> 25 . 5 >> 49 . 29 >> 45 . 25 >> 24 . 4 >> 51 . 1 >> 22 . -28 >> 27 . -23 >> 57 . 7 >> 20 . -30 >> 57 50 7 >> 59 . 9 >> 33 . -17 * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/

**References**:**st: Subtract Closest Cell Which has A Value***From:*Lisa Wang <lhwang0925@gmail.com>

**Re: st: Subtract Closest Cell Which has A Value***From:*Nick Cox <njcoxstata@gmail.com>

- Prev by Date:
**Re: st: Default Seed of Stata 12** - Next by Date:
**RE: st: Thread-Index: Ac2zpwBrnny9GG5FQQ6Vz7stZfQOCw==** - Previous by thread:
**Re: st: Subtract Closest Cell Which has A Value** - Next by thread:
**st: convergence problems in mi impute chained** - Index(es):