persval (version 1.1.1)

pvq40: Compute personal values from PVQ-40 data

Description

This function computes personal values scores and different higher-order dimensions related to Schwartz's theoretical framework based on the 40 items of the PVQ-40 Value Scale (Schwartz, 2006; Schwartz et al., 2001). By default, the function applies the recommended statistical adjustment (MRAT centering) as suggested by the authors, to correct for individual differences in response styles thus enhancing the interpretative validity of the scores.

Usage

pvq40(
  df,
  items = NULL,
  compute = "all",
  correction = TRUE,
  na.rm = TRUE
)

Value

A data frame with computed values. If both "df" and "items" parameters are provided, the returned data frame includes the original data with the calculations appended as new columns.

Arguments

df

A Data frame containing the raw responses for the 40 PVQ items. If "items" is not provided, it must have exactly 40 columns, and their order must correspond to the PVQ-40 items.

items

An optional vector containing the names or indices of the columns that correspond to the PVQ-40 items. Must be exactly 40 items. If NULL, the function assumes the items are the only columns given in the "df" parameter.

compute

Character. Indicates which personal values scores to compute and return. Possible values are "all" (default; computes all first and second-order personal values scores), "ten.values" (computes the ten basic personal values scores), "four.higher" (computes the four main higher-order values scores), "two.foci" (computes two higher-order values scores: self-focused values that regulate personal interests and characteristics, and other-focused values that regulate social relationships), "two.anxiety" (computes two higher-order values based on their relation to anxiety: self-protective values aimed at coping with anxiety due to uncertainty in the social and physical world, and growth-oriented or self-expansive values that express anxiety-free motivations).

correction

Logical. When TRUE, the scores are corrected for individual differences in the use of the response scale. Default is TRUE.

na.rm

Logical. When TRUE, NAs are ignored in calculations; when FALSE, NAs are preserved and will affect calculations. Default is TRUE.

Examples

persval::pvq40(df = data.frame(
pvq1 = c(3, 1, 4), pvq2 = c(2, 5, 3), pvq3 = c(1, 5, 2), pvq4 = c(4, 3, 5),
pvq5 = c(5, 2, 1), pvq6 = c(3, 4, 2), pvq7 = c(1, 2, 4), pvq8 = c(3, 1, 5),
pvq9 = c(2, 4, 1), pvq10 = c(5, 3, 2), pvq11 = c(1, 4, 3), pvq12 = c(2, 1, 5),
pvq13 = c(3, 5, 4), pvq14 = c(1, 2, 3), pvq15 = c(4, 5, 1), pvq16 = c(2, 3, 4),
pvq17 = c(5, 1, 2), pvq18 = c(3, 4, 1), pvq19 = c(2, 3, NA), pvq20 = c(1, 3, 4),
pvq21 = c(2, 5, 1), pvq22 = c(4, 1, 5), pvq23 = c(3, 4, 2), pvq24 = c(5, 1, 3),
pvq25 = c(4, 2, 5), pvq26 = c(1, 3, 2), pvq27 = c(5, 4, 1), pvq28 = c(2, 1, 4),
pvq29 = c(3, 5, 2), pvq30 = c(1, 4, 3), pvq31 = c(2, 3, 5), pvq32 = c(4, 1, NA),
pvq33 = c(3, 5, 4), pvq34 = c(1, 2, 3), pvq35 = c(4, 1, 5), pvq36 = c(2, 3, 4),
pvq37 = c(5, 2, 1), pvq38 = c(4, 3, 2), pvq39 = c(1, 5, 3), pvq40 = c(2, 4, 1)),
correction = TRUE,
compute = "all",
na.rm = TRUE)