Computes, for each group (typically a country), mean achievement and the socio-economic gradient, and draws the OECD-style "quality vs equity" scatter: mean performance on one axis against the strength of the socio-economic gradient (the percentage of variance ESCS explains) on the other. Reference lines at the across-group averages split the plot into the familiar quadrants (high quality / high equity, and so on).
Usage
equity_scatter(
data,
by,
achievement,
escs = "ESCS",
weight = NULL,
repweights = NULL,
rep_method = c("BRR", "JK2", "JK1"),
fay = 0.5,
design = NULL
)Arguments
- data
A data frame of student-level records.
- by
Name of the grouping column (e.g. country).
- achievement
Character vector of achievement plausible-value columns.
- escs
Name of the socio-economic index column (default
"ESCS").- weight
Name of the final student weight column.
- repweights, rep_method, fay
Replicate-weight specification passed to
social_gradient().- design
Optional
lsa_design()bundlingweight,repweights,rep_methodandfay; when supplied it overrides those arguments.
Value
An object of class "equity_scatter": a list with data (a data
frame of group, mean, slope, strength) plus metadata. Plot it with
plot.equity_scatter().
Examples
data(pisa_mini)
es <- equity_scatter(pisa_mini, by = "IMMIG",
achievement = paste0("PV", 1:10, "MATH"),
escs = "ESCS", weight = "W_FSTUWT")
es
#> Quality-equity summary by IMMIG
#>
#> group mean slope strength
#> native 501.13 41.87 20.19
#> second_gen 480.25 39.23 17.93
#> first_gen 469.13 32.70 13.13