Analyses

Cochran–Armitage trend test

Test a linear trend in proportions across ordered groups.

Edit on GitHub

When to use it

Use Cochran–Armitage when the outcome is binary and the groups have an order. It is the z-test cousin of the Mantel–Haenszel trend test.

Assumptions

The group column must sort into the intended order. The outcome has two levels.

Running it in Tensr

Analyze → Correlate → Cochran-Armitage Trend. In chat: “Cochran–Armitage trend of dose by illness.”
Group column is ordered. Outcome column is binary.

Options

Prop

Type

Reading the output

The same dose groups against a response that rises from low to high.

Cochran–Armitage trend test: response by dose (decreasing trend). The primary result is significant (p = < .001). This is large enough, in this sample, to treat the comparison this page is about as a real association rather than noise. Metrics: Z = -29.811; p (two-tailed) = < .001; p (one-tailed) = > .999; Trend = decreasing.

Reporting (APA 7)

Cochran–Armitage trend test: response by dose (decreasing trend). This result is significant (p = < .001). The effect is moderate, so report its size with the p-value.

Coming from SPSS

Analyze → Correlate → Cochran-Armitage Trend.