Is it the venue or the time of year?
Six months by three venues, one attendance figure per cell, the way event data actually arrives. Both factors are real, and the month explains more of the swing than the venue does.
Words on this sheet
- Venue: The place an event is held. A venue line is what hiring it costs, usually a fixed amount whatever the turnout.
Operations Intermediate Statistics free
After you install, this is the model to open.
Venue and Month: What Drives Attendance?
- In your spreadsheet, click the Sortia icon in the strip of icons down the right-hand edge. No strip? Click the arrow at the bottom-right to open it. You can also use Extensions, then Sortia, then Open Sortia.
- Click Start from a template and put that name in the search box.
- Pick the card with that name and click Load this template. It arrives on a new tab with real numbers already in it.
The answer
- The month
- 55.8% of the sum of squares; F 52.8, p 0.0000007
- The venue
- 42.1% F 99.8, p 0.00000025
- Unexplained
- 2.1% both factors are real
- November
- 343 average heads; February manages 238
Eighteen events from a monthly business-networking series: six months down the side, three venues across the top, one paying-attendance figure in each cell, because you only get one November. Click Run. The month effect comes back F 52.85 with a p-value of 0.00000072 and the venue effect comes back F 99.78 with a p-value of 0.00000025, so both are real and neither is noise.
Now read the sums of squares rather than the F values, because that is where the size of each effect lives. The month accounts for 21,859 of the 39,194 total, which is 55.8%. The venue accounts for 16,508, which is 42.1%. Only 2.1% is left unexplained, which is unusually tidy and is what you get when both factors are strong. The month is the bigger lever, and the practical reading is that holding your November event in your worst venue would still beat holding your February event in your best one, which is exactly the trade a venue negotiation usually asks you to make.
The venue means are 326.7, 279.5 and 253.5 against room capacities of 420, 340 and 320, so in an average month all three rooms are running around four fifths full and none of them is the constraint. The month means run from 343.3 in November to 238.0 in February. Because there is one number per cell, this design cannot detect an interaction: if you suspect one venue is only bad in winter, this test averages that away and tells you nothing about it.
To look for it you would need the same venue and month combination measured more than once, and then the with-replication version of the test. Now rerun on September to December only, by trimming the input range to the first four months. The venue effect stays strong at F 169.80 and its sum of squares barely moves, from 16,508 to 13,990, while the month effect falls from 21,859 to 7,392 and drops below the venue effect.
So the New Year collapse was doing most of the seasonal work, and inside the autumn season the venue is the bigger lever after all. What the test cannot tell you is why: an attendance number has no opinion about the speaker. To use your own series, put one venue per column and one month per row and keep the grid complete.
The model
It arrives on a tab called Template: Venue by Month, carrying these columns:
- Attendance
- Rivergate (attendance)
- The Old Exchange (attendance)
- Barrow Court (attendance)
- Venue
- Room capacity
Once it is in your sheet
- The model arrives with real numbers in it and runs as it stands, so you can press the button first and understand it second.
- Change the numbers to yours. The sheet marks which cells are inputs and which hold formulas, and most labels carry a note explaining the row.
- Press the run button at the bottom of the panel. It is labeled for the tool you are in, and the result lands on its own tab, with a written reading of it beside the figures.
Never used Google Sheets? Start here goes the whole way, in seven steps, and assumes nothing.
Next question
- What does outsourcing cost once you price the risks?Outsource or Keep It In House?
- Are three of your regions really scoring the same?Do the Regions Rate Us Differently?
- The season looks fine on pace. Is it really?Will the Season Fill?
- Should weekends be staffed like any other day?Weekday and Weekend Are Not the Same Business
- What is the standing recipe costing you a tonne?The Cheapest Blend That Meets the Spec
- Will the changeover fit inside the weekend?How Much Buffer Does the Changeover Need?
Every model like this one, and the method behind them: Statistics in Google Sheets.
The method behind this one, worked end to end: ANOVA in Google Sheets.