I am trying to use the rdbwselect command and it has the the following syntax (from The Stata Journal (2017) 17, Number 2, pp. 372–404)

rdbwselect depvar runvar [if] [in] [, c(cutoff) p(pvalue) q(qvalue) deriv(dvalue) fuzzy(fuzzyvar [sharpbw] ) covs(covars) kernel(kernelfn) weights(weightsvar) bwselect(bwmethod) scaleregul(scaleregulvalue) vce(vcemethod) all ]

where they define : weights(weightsvar) : specifies the variable used for optional weighting of the estimation procedure. The unit-specific weights multiply the kernel function.

Can someone guide me towards what these weights are doing exactly? For instance, if I am using survey data that uses sampling weights, should I be using those weights in this syntax. My confusion stems from the fact that these weights could be representative of the fact that values of the running variable that are closer to the cutoff have a higher probability of receiving the treatment and it does not have to do something with sampling weights in particular. I highly appreciate your time and views!