Re: [Gretl-devel] duration models and Liu-Hong test

On Sun, 18 Dec 2016, Allin Cottrell wrote: > On Sun, 18 Dec 2016, Sven Schreiber wrote: > >> Am 17.12.2016 um 20:19 schrieb Allin Cottrell: >>> Any duration model experts out there? >> >> No (well, not me at least... ;-) >> >>> The relevant pages of the article are 6-10. Here's my problem: their >>> empirical survivor function (p. 10) involves counting cases where >>> V_i(\theta) and C_i(\theta), for observations i, are greater than >>> duration value t. But V_i and C_i are (if I'm reading the paper right) >>> CDF values and therefore limited to [0,1], while the duration t is said >>> on page 6 to be distributed on [0, \infty). So I don't see how these two >>> terms can be meaningfully compared. >>> >>> I guess I'm missing some implicit mapping/transformation (maybe of t >>> onto [0,1]?). Can anyone help? >> >> I see what you mean and just have a wild guess to offer: Maybe on p.10 in >> the equations with the summations it should be V_i and C_i with tildes >> instead. (So $\tilde{V}_i(\theta) > t$ etc.) This obviously is a >> typo-based explanation, and I'm not at all sure. > > Thanks, Sven. That would make sense of the inequalities, but I think it > would make nonsense of the broader argument on page 10. 8-/ I guess that Sven's typo argument should read like: we count the number of times $V_i(\theta) > F_0(t)$, which is by definition the same as $\tilde{V}(\theta) > t$. But more in general: I'd try to contact the authors. The fact that a PhD thesis defended in 2007 hasn't seen the light as a journal article is definitely not a good sign. (But of course that means nothing certain: each of us has some horror story from the publish-or-perish trenches.)