Skip to contents

With R and L the summed percentages of the pos and neg categories (by default the right and left RILE categories of Laver and Budge 1992): rile = R - L; the Kim and Fording (1998) ratio scale \((R - L)/(R + L)\); the ratio \(R/L\); and, when the quasi-sentence count total is given, the logit scale of Lowe et al. (2011) \(\log((R\,total/100 + 0.5)/(L\,total/100 + 0.5))\). These are manifestoR::rile, scale_ratio_1, scale_ratio_2 and logit_rile.

Usage

ManifestoScales(
  per,
  total = NULL,
  pos = c(104, 201, 203, 305, 401, 402, 407, 414, 505, 601, 603, 605, 606),
  neg = c(103, 105, 106, 107, 202, 403, 404, 406, 412, 413, 504, 506, 701),
  zero_offset = 0.5
)

Arguments

per

A named list or vector (names like "per104" or "104") of category percentages, or a data frame with one document per row.

total

Quasi-sentence count(s) for the logit scale.

pos, neg

Categories scored positive and negative.

zero_offset

Added to each count in the logit scale.

Value

List with rile, ratio_1, ratio_2, logit.

References

Laver, M. and Budge, I. (1992). Party Policy and Government Coalitions. Macmillan.

Kim, H. and Fording, R. C. (1998). Voter ideology in Western democracies, 1946-1989. European Journal of Political Research 33, 73-97.

Lowe, W., Benoit, K., Mikhaylov, S. and Laver, M. (2011). Scaling policy preferences from coded political texts. Legislative Studies Quarterly 36, 123-155.

Examples

ManifestoScales(list(per104 = 5, per401 = 7.5, per403 = 2, per504 = 10), total = 200)
#> $rile
#> [1] 0.5
#> 
#> $ratio_1
#> [1] 0.02040816
#> 
#> $ratio_2
#> [1] 1.041667
#> 
#> $logit
#> [1] 0.04000533
#>