Manuscript Psy03-D@1 · Psy03-D-v1.tex · section · 3e18951d

The original repetition statistic

Response metrics and old-function persistence › The original repetition statistic · lines 953–973

Psy03-D@1#eq:repeatmetric

Let

E_{t} = 1 {Y_{t} \neq = Y_{t}}, A_{t} = 1 {Y_{t} = Y_{t - 1}} .

A distinct statistic is

Π_{repeat ∣ error} = \frac{\sum _{t \in \cup_{j} W_{j}} E _{t} A _{t}}{\sum _{t \in \cup_{j} W_{j}} E _{t}},

when its denominator is positive.

We call this repeated-response fraction among post-switch errors. It is not renamed as old-rule persistence.

Displayed formulas in this passage

unlabeled · line 956
$E_{t} = 1 {Y_{t} \neq = Y_{t}}, A_{t} = 1 {Y_{t} = Y_{t - 1}} .$
Psy03-D@1#eq:repeatmetric · line 961
$Π_{repeat ∣ error} = \frac{\sum _{t \in \cup_{j} W_{j}} E _{t} A _{t}}{\sum _{t \in \cup_{j} W_{j}} E _{t}},$