Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I was thinking about modelling mathematically (or finding the mathematical model) of the following experiemnt. Think about students $S_i$ saying how fast or slow they feel the lecture has passed - and I'd like to predict that.

Let's also suppose that I measure

  • the data time $T_i$ the start time
  • $D_i$ the duration of the lecture
  • $O_i$ the temperature outside
  • $I_i$ the temperature inside the lecture room
  • $M$ the average passing rate for the course (i.e. how "difficult" it is)

My assumption is that

  • the greated $D_i$, the more students will report that the time passes harder
  • the higher the difference $|I_i - O_i|$, the more the effect of $D_i$ will be reduced
  • the higher $M$ is, the more students will say that time has passed harder

How could I find out how good this model is and perhaps find out a better model to predict how hard (in fuzzy logic) a given student $S_i$ will say the time has passed (given the above parameters), if I collected all this information mentioned about and also reports from the student $S_i$ on how slow the time has passed?

share|cite|improve this question
up vote 1 down vote accepted

You should make large scale experiments. Let $N$ be the number of random experiments that you do. Then the subjective assertions will approach to the objective ones when $N\rightarrow\infty$.

If some of the parameters that are introduced have no effects on the model, then your assumtions will fail; namely for example the greater the $D_i$ will have no effect on the feeling of the students that the time passed faster etc..

In such a case, those assertions should be removed from the model and the newer ones could be included. At any case, the results of such a model, after asssuming a good built of a model, will still be related to the common understanding of the humanbeings on time.

share|cite|improve this answer
Ok, and then? Let's assume I've established that my assumption was completely right (for the sake of simplicity), then how do I predict how a student would react to a given tuple $(T,D,O,I,M)$? I'm interesting in saying "Student X will say that this was [0,1] hard". – Flavius Jan 21 '13 at 15:33
It is related to the collection of statistics. There will be some possible events and the students will choose one among many. For example; giving a number between -100 and 100. This will help alot. Finally after enough number of experiments, if it has a role then the expected number which will come out will be off $0$, else nearby. – Seyhmus Güngören Jan 21 '13 at 15:41

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.