Likelihood-ratio chi-square: what it means and how to read it

In the report: Chi-square — How much −2 Log Likelihood dropped compared with the model with the intercept only.

How to read it

The larger, the more the predictors together improve the prediction. Read its Sig.; in a report: χ²(2) = 4.08, p = .130.

In plain words

A clinic scored how far its guesses about who would recover were from what really happened. With no information about the patients the score was 120, and with age and weight it was 104. The chi-square is simply the drop: 16. The bigger the drop, the more age and weight together brought the guesses closer to reality. A drop of 16 looks like a lot, but the clinic does not stop there. It looks at the chance column next to it, which says whether such a drop could easily be luck, and only then writes it in the report.

How it is computed

χ² = −2LL₀ − (−2LL), compared with the chi-square distribution with df = k − 1

Example

The cell with Chi-square is selected in each report; point at a label to see its note.

  • — the sample data (50 rows) the examples use
  • — two steps; pass is coded 0 and 1 =STATS_LOGISTIC(Data!A1:T51, "pass", "x1,x2|x", 0, 50, 1e-8)

Where you see it

Get it in your sheet

One formula in a cell gives the whole report, Likelihood-ratio chi-square included. ALS Stats is a free add-on for Google Sheets™.

Install ALS Stats from Google Workspace Marketplace (opens in a new tab)