The numbers seemed so clean that I decided to spend some extra time running more tests. The average results are what I used to come up with this equation for determining how long it takes for the internal temperature of the MR-138 unit to reach another temperature approaching room temperature. So if you have the MR-138 set at 50°F and you turn the unit off, this equation allows you to determine how long it will take to reach room temperature, or any other temperature in-between. This is useful if you want to make use of the slow increase in temperature in the unit for bringing cold fermented doughs to room temperature before you bake, so you're not wasting energy and you know exactly when to open the door to pull the dough.
t = [delta]T2 * log [delta]T
where t is the time in minutes,
... [delta]T is the temperature difference in Fahrenheit.
Example (50°F -> 68°F):
t = 182 * log 18
t = 324 * 1.2552725051
t = 406.7082916535 or 6 h 46 m 42.5 s
All the tests were performed with 1.988 kg of mass (48.7% glass, 48.5% dough, 2.8% plastic) in the unit. I haven't tested it, but I'm pretty sure the equation will work in the other direction for warm fermentation decreasing to room temperature. The only thing I can think of that would prevent it from being accurate in the other direction is if the unit has seals that are either tighter or looser under warm temperatures.
EDIT: An astute observer may notice that the time it takes to increase 1°F is 0 minutes. That is due to one of the problems I had with testing really short times. The unit seems to work on fuzzy logic, so several times when I turned off the the unit the temperature would change by as much as 3°F instantly. Of course this isn't really possible, but I have no way of modeling what's going on in the first few seconds of being off. It could just be the difference between the fan being on or off.