IQ130: derham development

The notebook

In order: what the lab saw, what it asked, what it proposed and why, what the tests said, and what an investigator concluded. Numbers are aggregates on the discovery data unless a step says otherwise.

1. Hypothesised15 Oct, 23:10

   IQ130: derham development KILLED amber

   because A: Harry Derham, hurdle start 2-4, technique below the median last time, predicted uplift above the median.

   dv_now IS NOT NULL AND dv_hyp_a = 1

   made by import

2. Tested15 Oct, 23:10

   broad: A/E 1.28 on 26 bets. info

   Zone: all. On IQ130: derham development

   By period

   betsA/E0.71.01.3

   Earlier half23–

   Later half3–

3. Tested15 Oct, 23:10

   HOLDOUT 2023-25, all: A/E 0.49 on 36 bets. info

   Zone: all. On IQ130: derham development

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago36–

   Last year0–

4. Tested15 Oct, 23:10

   Britain: A/E 0.49 on 36 bets. info

   Zone: all. On IQ130: derham development

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago36–

   Last year0–

5. Tested15 Oct, 23:10

   Ireland on 0 bets. info

   Zone: all. On IQ130: derham development

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago0–

   Last year0–

6. Tested15 Oct, 23:10

   discovery year (reference): A/E 1.45 on 30 bets. info

   Betfair SP return +14.7%. Zone: all. On IQ130: derham development

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago0–

   Last year30–

7. Promoted15 Oct, 23:10

   IQ130: derham development Falsification → FROZENimport: frozen

8. Killed15 Oct, 23:10

   IQ130: derham development Vault → KILLEDfailed the vaultimport: holdout CONTRADICTED: A/E 0.488 on 36 (GB 0.488, IRE None), p 0.9443 against BH 0.003448 over 29 tests