Applies scale scoring rules from the instrument to response data. Handles reverse coding, optional weighted composite score computation, and minimum valid item thresholds. Returns a data frame with one scored column per scale.
Sum scores with unanswered items
With method = "sum" and a min_valid below the number of items, a
respondent who answered at least min_valid items gets a prorated sum:
the mean of the answered items times the number of items (with weights,
the weighted mean times the sum of the weights). 5 and 5 on 2 of 4 items
on a 1 to 5 scale scores 20. Before 0.4.3 an unanswered item counted as 0,
so the same respondent scored 10.
Codes that are not scores
An item's scores are the longest run of its choice set's numeric codes at
1 even step: 1 to 5, or 0 to 100 in steps of 25. A code outside that run,
such as 99 for "do not know" after 1 to 5, is read as missing, with a
message naming it and how many answers held it, and a reversed item is
reversed on the run's ends (1 + 5 - x). A set with 2 equally long runs,
such as 1, 2, 4, 5, has no clear run, and its scale is refused with an
error. validate_sframe() notes such a choice set. Before 0.4.3 every numeric code was a score, so the reversal
point moved to 1 + 99 and a 99 entered the mean.
See also
sframe_scale(), sframe_reliability_results()
Other Analyse functions:
run_analysis_plan(),
sframe_assumption_results(),
sframe_descriptives_results(),
sframe_efa_readiness_results(),
sframe_efa_solution(),
sframe_item_results(),
sframe_posthoc_results(),
sframe_reliability_results(),
sframe_validity_results()
Examples
cs <- sframe_choice_set("ag5", 1:5,
c("Strongly disagree", "Disagree", "Neutral",
"Agree", "Strongly agree"))
i1 <- sframe_item("sat_1", "Item 1", type = "likert",
choice_set = "ag5", scale_id = "sat")
i2 <- sframe_item("sat_2", "Item 2", type = "likert",
choice_set = "ag5", scale_id = "sat")
i3 <- sframe_item("sat_3", "Item 3 (reverse)", type = "likert",
choice_set = "ag5", scale_id = "sat", reverse = TRUE)
scale <- sframe_scale("sat", "Satisfaction",
items = c("sat_1", "sat_2", "sat_3"), min_valid = 2L)
instr <- sframe_instrument("Demo", components = list(cs, i1, i2, i3, scale))
responses <- data.frame(
sat_1 = c(4, 5, 3),
sat_2 = c(4, 4, 3),
sat_3 = c(2, 1, 3),
stringsAsFactors = FALSE
)
scored <- score_scales(responses, instr)
scored$sat