Estimate Bradley-Terry ability scores from paired comparison data using the I-LSR algorithm.
Avoids using stats::glm()
and seems to be faster, but only approximates maximum likelihood.
ILSR(C, sort = FALSE, maxits = 100, tolerance = 1e-06, verbose = FALSE)
C | a square matrix of paired comparisons |
---|---|
sort | logical. If |
maxits | The maximum number of iterations in the I-LSR algorithm |
tolerance | The criterion for convergence of the algorithm |
verbose | logical. If |
A vector of estimated ability scores
The function uses iterative Luce Spectral Ranking (I-LSR) to approximate the maximum likelihood ability weights of the Bradley-Terry model. To do: Add unit tests.
Maystre, Lucas and Grossglauser, Matthias (2015). Fast and accurate inference of Plackett--Luce models. In Advances in Neural Information Processing Systems, 172--180.
Other network centrality estimators: BTscores
,
BradleyTerry
, PageRank
,
Scroogefactor
ILSR(citations)#> AmS AISM AoS ANZS Bern BioJ #> 0.023845803 0.021878755 0.063145181 0.016872929 0.031871582 0.010675591 #> Bcs Bka Biost CJS CSSC CSTM #> 0.037234178 0.057807370 0.030739517 0.021617390 0.004520609 0.007571317 #> CmpSt CSDA EES Envr ISR JABES #> 0.008415962 0.009438678 0.009860333 0.014311652 0.022124895 0.013518074 #> JASA JAS JBS JCGS JMA JNS #> 0.056297501 0.003881006 0.006919858 0.030368921 0.010145372 0.009411896 #> JRSS-A JRSS-B JRSS-C JSCS JSPI JSS #> 0.031968723 0.129001550 0.017391450 0.006377069 0.011478352 0.007147140 #> JTSA LDA Mtka SJS StataJ StCmp #> 0.023094738 0.017604588 0.013265793 0.030851089 0.016326278 0.016523634 #> Stats StMed SMMR StMod StNee StPap #> 0.008292948 0.017007064 0.011229792 0.012792923 0.014350610 0.004146546 #> SPL StSci StSin Tech Test #> 0.014493825 0.017852214 0.021274276 0.027140416 0.007914610