Skip to main content
Cross Validated

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

Required fields*

13
  • $\begingroup$ Bravo! I have not mentioned it but the deity told me that it uses median of Y in place of constant. So alternatively we might assume that we model is Y/(medianY) = Home * Sex * Rank (with out constant). What you have estimated looks promising. $\endgroup$ Commented Sep 19, 2019 at 11:02
  • 1
    $\begingroup$ The elders also forgot to mention something. It is not just about the constant coefficient, but also the parameter coefficients can be scaled relatively to each other. $$\text{Y/(medianY) = (Home/a/b) * (Sex*a) * (Rank*b)}$$ will hold for any values of $a$ and $b$. So the divine is not so easy to capture and we may never know what values the deity has been using. We will have to remain humble and just accept that ratio's are the only thing that we can capture and for the rest we need to trust whatever the deity tells us. $\endgroup$ Commented Sep 19, 2019 at 11:06
  • $\begingroup$ In addition to this problem with ratio's you have been expression your parameters without taking the exponent. When you perform a linear model with the logarithm $$\text{log(Y) = log(Home) + log(Sex) + log(Rank)}$$ then this means that you are computing the logarithm of the values $Home$, $Sex$ and $Rank$. And since you seem to be adding into it some minus sign (although I can't see exactly where that discrepancy arises) you end up with low values in your model when the divine values are high. $\endgroup$ Commented Sep 19, 2019 at 11:13
  • $\begingroup$ I got the lesson: "The only divine values that matter are the ratio's of coefficients". There is still shade of doubt. You have thrown out "one of a kind" of each variable. For example you have thrown out Atreides from Home variable. Does it mean the coefficient for Atreides is equal 1? $\endgroup$ Commented Sep 19, 2019 at 11:17
  • $\begingroup$ It is arbitrary and depends on the setup of the computation. It is actually amazing how you got to compute your values. I wonder how you did that. It must have been under influence of quite some spice, since only the deity might help you with a computation that results into output like that. $\endgroup$ Commented Sep 19, 2019 at 11:18