Essentially, I want to do a dynamic pricing model. Create a formula where i take the correlation coefficients of various variables related to pricing, and then when calculating a certain price, increment the price using a combination of the other variable value and its correlation coefficient to price.

Essentially creating some sort of weight value from the correlation coefficient that affects the calculations(the weights would get updated as the correlation coefficients get updated, as new datasets come in)

So if you have the variables : price, distance, timerange1(binary),timerange2(binary)

price = initial price + distance*correlation + timerange(0 or 1)*corr +timerange2(0 or 1)*corr

The operators in there are placeholders just to get the idea across, I was wondering if there is an established way of doing something like this, or the closest thing I could base this off of?

Thank you. ]]>

Independent variable: Student engagement in simulation (likert scale 1-5)

St.engagement in traditional learning (likert 1-5)

Dependent variables: #1. Knowledge application (likert scale 1-5)

#2. Investment Literacy (true false)

Here are hypothesis I have developed :

#1. Students' high engagement in simulation is related to higher investment literacy.

#2. Students' high engagement in simulation is related to higher knowledge application.

How can I analyze the data with different scales?

thanks ]]>

Is there any analogous measure of sensitivity and specificity for non-binary variables?

For example, if I want to study the sensitivity of a test that analyzes blood types (i.e. A, B, AB or 0) in comparison with a gold standard tet. What's the best way to do it?

I have thought about doing 4 contingency tables, and in each one of them I can get a value of the test for that blood type. However, how can I translate the findings of each category to the test as a whole? I guess I can simply calculate the average sensitivity value, but is there any other possibility?

Thanks in advance. ]]>