matchesLink function

matchesLink

matchesLink produces two dataframes that store all the pairs that share a pattern that conforms to the an interval of the Fellegi-Sunter weights

matchesLink(gammalist, nobs.a, nobs.b, em, thresh, n.cores = NULL)

Arguments

• gammalist: A list of objects produced by either gammaKpar or gammaCKpar.
• nobs.a: number of observations in dataset 1
• nobs.b: number of observations in dataset 2
• em: parameters obtained from the Expectation-Maximization algorithm under the MAR assumption. These estimates are produced by emlinkMARmov
• thresh: is the interval of posterior zeta values for the agreements that we want to examine closer. Ranges between 0 and 1. Can be a vector of length 1 (from specified value to 1) or 2 (from first specified value to second specified value).
• n.cores: Number of cores to parallelize over. Default is NULL.

Returns

matchesLink returns an nmatches X 2 matrix with the indices of the matches rows in dataset A and dataset B.

Examples

## Not run:

## Calculate gammas
g1 <- gammaCKpar(dfA$firstname, dfB$firstname)
g2 <- gammaCKpar(dfA$middlename, dfB$middlename)
g3 <- gammaCKpar(dfA$lastname, dfB$lastname)
g4 <- gammaKpar(dfA$birthyear, dfB$birthyear)

## Run tableCounts
tc <- tableCounts(list(g1, g2, g3, g4), nobs.a = nrow(dfA), nobs.b = nrow(dfB))

## Run EM
em <- emlinkMAR(tc)

## Get matches
ml <- matchesLink(list(g1, g2, g3, g4), nobs.a = nrow(dfA), nobs.b = nrow(dfB),
em = em, thresh = .95)
## End(Not run)

Author(s)

Ted Enamorado ted.enamorado@gmail.com, Ben Fifield benfifield@gmail.com, and Kosuke Imai