[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
Richard Williams <[email protected]> |

To |
[email protected] |

Subject |
Re: st: time series modeling question |

Date |
Sun, 19 Oct 2003 17:22:35 -0500 |

I haven't done this sort of thing in a while, but back when I was doing it I used discrete time methods. See Paul Allison's chapter entitled "Discrete time methods for the analysis of event histories", pp. 61-89 in Sociological Methodology 1982. (Edited by Samuel Leinhardt). For an application, see "The stability of interracial friendships" by Maureen Hallinan and Richard Williams, American Sociological Review, V. 52 Issue 5, Oct. 1987, pp. 653-664. I believe the technique is also described in Paul Allison's 1984 Sage book on Event History Analysis.

Basically, what you do is create a record for each time period you have data for. Once the event occurs, you stop having data for that individual. The dependent variable is a dichotomy (off/on) and you use logistic regression analysis.

Like I say, I haven't done this for a while, so I don't know if this is still state of the art, but it sounds like it could apply to your problem.

At 02:12 PM 10/19/2003 -0400, you wrote:

I am having some difficulty determining the most appropriate way to model a process. I have time series (month by month) data on a set of subjects, most of whom (but not all) make a single transition from "off" to "on". My goal is to estimate the contributions of set of time-varying and time-invariant independent variables to the probability of this transition. My not-so-deep understanding of survival time and hazard models suggest that they are not what I'm looking for here. Can anybody point me in the right direction? (Please don't spend the time on a detailed explanation; although I'd appreciate it, I don't want to impose that much.) Thanks. -ml * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

------------------------------------------- Richard Williams, Associate Professor OFFICE: (574)631-6668, (574)631-6463 FAX: (574)288-4373 HOME: (574)289-5227 EMAIL: [email protected] WWW (personal): http://www.nd.edu/~rwilliam WWW (department): http://www.nd.edu/~soc * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: time series modeling question***From:*"Michael I. Lichter" <[email protected]>

- Prev by Date:
**st: time series modeling question** - Next by Date:
**st: Re: fixed effects models** - Previous by thread:
**st: time series modeling question** - Next by thread:
**st: Re: fixed effects models** - Index(es):

© Copyright 1996–2024 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |