check_items: Screen items for problems before factor analysis

In ackwards: Bass-Ackwards Hierarchical Structural Analysis

Screen items for problems before factor analysis

Description

Real-world item sets often contain columns that break or silently degrade a factor analysis: an item everyone answered the same way (no variance), an item dominated by one response with a couple of stray answers, or an item with heavy missingness. On the polychoric basis these are especially costly – a near-empty response category can make psych::polychoric() fail outright (see the correct argument of ackwards()), and a near-constant item can produce a plausible-looking but meaningless factor with no warning.

check_items() reports these problems before you fit, one row per item, so you can collapse rare categories, drop degenerate items, or set cor/correct deliberately rather than debugging a cryptic error. It only reports; it never changes your data. ackwards() runs the same screen internally: it errors on a constant item and warns on a near-degenerate one, naming the offenders.

Usage

check_items(data, cor = c("polychoric", "pearson", "spearman"))

Arguments

data	A data frame or numeric matrix (items in columns).
cor	The correlation basis you plan to use: "polychoric" (default), "pearson", or "spearman". Only affects which problems are flagged – sparse response categories destabilise the polychoric basis but not the others.

Value

A data frame (class check_items) with one row per item and columns item, n_valid, pct_missing, n_distinct, min_count (smallest observed category count), top_prop (proportion of valid responses in the most common value), and flag – one of "ok", "constant", "near-constant", "sparse category", or "high missing". Print it for a grouped summary with guidance; treat it as a plain data frame for the full per-item table.

See Also

ackwards() and its correct argument (the polychoric failure this screens for); factorability(), suggest_k(), and comparability(), the other pre-analysis diagnostics.

Examples

# sim16 is clean continuous data -> nothing flagged
check_items(sim16, cor = "pearson")

# An item dominated by one response with a couple of stray answers is flagged
d <- sim16
d$bad <- c(rep(1L, nrow(d) - 2L), 2L, 3L)
check_items(d)

ackwards documentation built on July 25, 2026, 1:08 a.m.