Impact of numerical relativity information on effective-one-body waveform models

We present a comprehensive comparison of the spin-aligned effective-one-body (EOB) waveform model of Nagar et al. [Phys. Rev. D 93, 044046 (2016)], informed using 39 numerical-relativity (NR) data sets, against a set of 149 l = m = 2 NR waveforms freely available through the Simulating Extreme Spacetimes (SXS) catalog. We find that, without further calibration, these EOBNR waveforms have unfaithfulness-at design Advanced-LIGO sensitivity and evaluated with total mass M varying as 10M(circle dot) <= M <= 200M(circle dot) - always below 1% against all NR wa\veforms except for three outliers, that still never exceed the 3% level; with a minimal retuning of the (effective) next-to-next-to-next-to-leading-order spin-orbit coupling parameter for the non-equal-mass and non-equal-spin sector, that only needs three more NR waveforms, one is left with another two (though different) outliers, with maximal unfaithfulness of up to only 2% for a total mass of 200M(circle dot). We show this is the effect of slight inaccuracies in the phenomenological description of the postmerger waveform of Del Pozzo and Nagar [Phys. Rev. D 95, 124034 (2017)] that was constructed by interpolating over only 40 NR simulations. We argue that this can be easily fixed by using either an alternative ringdown description (e.g., the superposition of quasi-normal-modes) or an improved version of the phenomenological representation. By analyzing a NR waveform with a mass ratio 8 and dimensionless spins +0.85 obtained with the BAM code, we conclude that the model would benefit from NR simulations specifically targeted at improving the postmerger-ringdown phenomenological fits for mass ratios greater than or similar to 8 and spins greater than or similar to 0.8. We finally show that some of the longest SXS q = 7 waveforms suffer from systematic uncertainties in the postmerger-ringdown part that are interpreted as due to unphysical drifts of the center of mass: thus some care should be applied when these waveforms are used for informing analytical models.