Unit Cost Equation

[Scott Hebert]

sushiboat said:
I look forward to adding magic paths. However, it would not surprise me if they turn out to be correlated with the stats already in -- especially precision, magic resistance, and magic leadership. The number of total path levels should be highly correlated with magic leadership. Levels in death and blood paths will be highly correlated with undead leadership. Fire magic adds to attack skill, and so on. What may happen is that the path levels stay in the final equation, other stats come out, and overall variance explained is bumped up only a little. Chipping away at the last 20% of the variance will be tough, I bet.

Hmm. Well, here's the thing. If you look at total Magic leadership (including magic path additions), wouldn't that tend to overvalue Astral magic? Similar with Undead Leadership, etc.

I would think that, since we ostensibly have what the path costs should be for a given configuration (I've worked these all out, including full randoms, if you'd like it), shouldn't you remove that from consideration before running your analysis?

That done, wouldn't you gain a clearer picture of how to value the stats?

What I'm getting at is perhaps by working together (using my guesses and your regression analysis), we might be able to come up with a value for any given stat configuration, and then just 'plug in' the rest of the information.

Unfortunately, I don't very much at all about regression testing, so it's hard for me to grasp much of the jargon.

[Evil Dave]

Scott Hebert said:

Unfortunately, I don't very much at all about regression testing, so it's hard for me to grasp much of the jargon.

No problem. Say you wanted to model the damage the units do in Dom2. You'd probably guess it was some function of strength and weapon damage.

So, you'd make a model like:

damage = A * strength + B * weapon damage

"strength" and "weapon damage" are the regressors (or contributors). A and B are their coefficients. The regressors also each have p-values, which is the likelihood they're due to chance -- 1%, 5%, and 10% are typical cut-offs for scientific work. The whole model has an R-squared, which is the fraction of the variation of the data it explains. R-squareds range from 0 to 1.

So, in this toy example, strength and weapon damage would probably have very small p-values (probably less than 0.01), but the R-squared would probably be pretty low, because the 2d6oe tends to swamp out the effects of the regressors.

Hope that helps.