Interesting. However, A BIG assumption in your inference is that “good conference” is related to “impact factor”. There are lots of reasons to doubt whether “impact factor” of a journal has any relationship at all with “quality of publication”.
Is there a bias here? I assume there are many more low-acceptance rate conferences than high-acceptance. Therefore, it makes sense that there are more papers which were accepted to low-acceptance conferences, and then gained high impact.
The question should be different, I think. If you have a paper that was accepted to a high-acceptance conference, what are the chances it will gain high impact factor over time?
It’s clear that having low acceptance rates for the sake (or prestige) of having low acceptance rates is not a useful signal detection (detection of quality work) strategy. But what is a good signal detection strategy? And what contributes to a low acceptance rate, is it a high rejection bias or a low submission threshold? Teasing these apart might yield related matrics that are more meaningful.
Interesting. However, A BIG assumption in your inference is that “good conference” is related to “impact factor”. There are lots of reasons to doubt whether “impact factor” of a journal has any relationship at all with “quality of publication”.
That’s likely because the earning power (or impact) isn’t in the school (conference).
On the other hand, I imagine there might be some interesting observations to make regarding the whole distributions, rather than just the means.
@Vellino I’m not making this assumption. I have stopped tracking the Impact Factor entirely after giving it a bit of thought.
But here, it suits my purpose which is to question this concept that “low acceptance rates” are a good thing.
Is there a bias here? I assume there are many more low-acceptance rate conferences than high-acceptance. Therefore, it makes sense that there are more papers which were accepted to low-acceptance conferences, and then gained high impact.
The question should be different, I think. If you have a paper that was accepted to a high-acceptance conference, what are the chances it will gain high impact factor over time?
I’ve often felt this is true, but I wonder how things stack up within specific areas (eg., theory versus theory or AI versus AI)…
It’s clear that having low acceptance rates for the sake (or prestige) of having low acceptance rates is not a useful signal detection (detection of quality work) strategy. But what is a good signal detection strategy? And what contributes to a low acceptance rate, is it a high rejection bias or a low submission threshold? Teasing these apart might yield related matrics that are more meaningful.