Skip to content
Open navigation
OpenOpen workspace

Worked exampleE-commerce and retail

Did returning visitors buy more often than new visitors?

Sessions with recorded revenue, by visitor type: Returning visitor: 1,470 of 10,551 (13.9%). New visitor: 422 of 1,694 (24.9%). The share was 11.0 percentage points lower for Returning visitor.

The table

Sessions with and without recorded revenue by visitor type. Percentages use each visitor-type column as the base.
Purchase in session \ Visitor typeReturning visitorNew visitorTotal
Revenue recorded1,47013.9%42224.9%1,892
No revenue recorded9,08186.1%1,27275.1%10,353
Total10,5511,69412,245

Count / Column %. Each column total is the base for that column’s percentages.

Shaded cells are the two shares the answer compares.

Check the reading before you quote it

Pick the statement this table supports, then open each option to see what the counts say. Every figure here is computed from the table above.

Returning visitors account for most sessions with revenue. Does that mean they bought more often?

  1. Yes, because they had more sessions with revenue.

    Not supported. 1,470 against 422 compares counts, and returning visitors simply had many more sessions: 10,551 against 1,694.

  2. Yes, because they made up most of the revenue sessions.

    Not supported. 77.7% of the 1,892 revenue sessions came from returning visitors. That base is revenue sessions, so it describes who the buyers were, not how often each group bought.

  3. No. A smaller share of their sessions had revenue.

    Supported. Using each group’s own sessions as the base, 13.9% of returning-visitor sessions had revenue against 24.9% of new-visitor sessions, 11.0 percentage points lower.

The figures behind the check

  • Base = each visitor type’s sessions: Returning visitor 13.9%, New visitor 24.9%.
  • Base = the 1,892 revenue sessions: Returning visitor 77.7%, New visitor 22.3%.
  • No base (raw counts): Returning visitor 1,470, New visitor 422. The source’s Other visitor class is excluded, leaving 12,245 sessions.

What to carry forward

Quote the share with its denominator: of returning-visitor sessions, of new-visitor sessions. The same counts look reversed when divided by revenue sessions.

Reproduce the exact tableOpens the calculator with this table’s counts, labels and category order, so each figure can be checked.

Use this result

  1. Reproduce it

    Open these exact counts in the chi-square calculator. It loads the same table, with the same category order, and computes the percentages, χ² and Cramér’s V in your browser. Change a cell to see how the result moves.

  2. Cite it

    Copy this reference. The data credit and licence below travel with it.

    Did returning visitors buy more often than new visitors? — Crosstabs. https://www.crosstabs.com/examples/rq25-purchasing-among-new-and-returning-visitors

    Source

    Scope
    E-commerce website; country unspecified
    Period
    One-year sampling period; dataset released 2018. Calendar dates unspecified.
    One record is
    one recorded website session

    Data: C. Sakar, Yomi Kastro. Online Shoppers Purchasing Intention Dataset. UCI Machine Learning Repository.. Licensed under CC BY 4.0. Crosstabs selected, recoded and aggregated the records into this table.

    Download these counts: CSVJSON

  3. Run it on your file

    Open a CSV, Excel or SPSS file to build the same kind of table. The file is read in this browser tab: nothing is uploaded and no account is needed.

    Run a crosstab on your own data

Why ask this

At this shop, returning visitors accounted for more sessions with recorded revenue. Which group had the higher share of sessions with revenue? Divide each group’s revenue-positive sessions by all of its sessions.

How to read it

Read down each column. Returning visitors supply most sessions (10,551) and most revenue sessions (1,470), yet their share is the lower one. The source’s third visitor class, Other, is left out of this table, so 12,245 sessions remain.

Column percentages answer “within each column, how often does each row occur?”. Switch to row percentages and the question turns around: “of the records in this row, how were they split across the columns?”. Both are correct; they answer different questions, so say which one you used.

What it means

New-visitor sessions ended in a purchase more often than returning-visitor sessions, a moderate gap. Each user contributes exactly one session in the sample year; “returning” means the site had seen the visitor before, not a before-and-after comparison of the same person. The table describes these sampled sessions, not why the two groups differ.

Cramér’s V = 0.105. It summarizes the whole table, all 2 × 2 categories, on a scale from 0 (no association) to 1. It does not say which cells differ, and it is not a measure of impact.

Comparing only Returning visitor and New visitor, and only Revenue recorded against every other row, Cramér’s V = 0.105. That number describes this one contrast, not the whole table.

Limits

These are selected sessions from one website over one year. A recorded purchase is only yes or no: the file gives no order amount and no experimental assignment, so nothing here says what a change to the site would do. Each user contributes exactly one session in the sample year, so a returning visitor’s earlier visits can lie outside the sample.

Keep exploring