Wedneday A handful of links today, but with content.

Dan Drezner discusses China, Thucydides, and the limit of metaphor. It strikes me that Dan’s buried the lede here. The question isn’t whether Thucydides is applicable to the Sino-American relationship, or whether Tuchman is better, but rather why even Chinese IR professors have adopted the tropes of the Western professoriate. After all, China has its very own history from which to draw analogies, as smart scholars like Victoria Tin-bor Hui and David Kang have reminded Western audiences. The history of the Warring States period seems at least as likely to offer more appropriate analogies for struggles between rising and falling powers as the Hellenistic period. Then again, perhaps nineteenth-century Prussia is an even better example.

Jonathan Zasloff brings news of a new mayor of El Pueblo de Nuestra Señora la Reina de los Ángeles and his somewhat quirkly, somewhat endearing choice of second-person pronoun.

And one final link, for quanty-duckies, below the fold:

stgenreg: A Stata Package for General Parametric Survival Analysis, in the Journal of Statistical Software.

The most popular tool for analysing survival data remains the Cox proportional hazards model (Cox 1972), which avoids making any assumptions for the shape of the baseline hazard function. One of the reasons the Cox model remains the prefered choice over parametric models is that standard parametric models available in standard software are often not flexible enough to capture the underlying shape of the hazard function seen in real data. … In this paper we present the Stata command stgenreg which enables the user to fit general parametric models through specifying any baseline hazard function which can be written in a standard analytical form. This is implemented through numerical integration of the user- defined hazard function. This allows complex extensions to standard parametric models, for example, modelling the log baseline hazard function using splines or fractional polynomials, as well as complex time-dependent effects; methods that are unavailable in standard software. Time-varying covariates can also be incorporated through using multiple records per subject. We do not consider frailty (unobserved heterogeneity) in this article.

I haven’t read this (but I did skim it!), but given the increasing popularity of Cox PH models in the literature (especially the IR literature), I wanted to flag this for potentially interested Duckies.

.

Share