Pair t test: record temps at 1-hr intervals w/ model, thermo

[grain]

Hello,

What can use instead of the ‘pair t test’?

I have two variables both of which are recording temperature of the same house at 1 hr intervals over the same time period. One of the variables is the real-world measurements and the other is temperature modelled by myself in a program.

I need an indication of how separate two sets of measurements are. They are measured over 2 months so I have 1300 measurements i.e. n = 1300.

These temperatures oscillate over the day like a sine wave and so aren’t normally distributed.

Can anyone please help?

 

[tkhunny]

Re: Pair t test

Did you find the "Goodness of Fit" test? Try this one: http://en.wikipedia.org/wiki/Goodness_of_fit

Let's talk about the Paired t-Test - From the Handbook of Biological Statistics:

"When to use it
You use the paired t-test when there is one measurement variable and two nominal variables. One of the nominal variables has only two values. The most common design is that one nominal variable represents different individuals, while the other is "before" and "after" some treatment. Sometimes the pairs are spatial rather than temporal, such as left vs. right, injured limb vs. uninjured limb, above a dam vs. below a dam, etc. "

You just don't have this situation. The situation you have is emperical data vs. model data. It is a little odd to be trying to determine how these are related. Of course they are related. Isn't that the idea of a model? They had better be related, or you have a useless model.

Are you trying to determine how good the model is? Wheter it possesses predictive capabilities? Whether it is better than some other model?

In any case, you need to define what you mean by "how separate". There are various designs. Sum of Squares, Sum of Absolute Values, really, anything you can dream up that is useful to you.

Rather than dodge my questions and start a new thread, why not just answer the questions?

 

[grain]

Re: Pair t test

Hi tkhunny,

Thanks for your help so far, I didn't intentionally dodge you questions.

Are you trying to determine how good the model is? Wheter it possesses predictive capabilities?

Yes, that is exactly what I'm trying to do.

I'll have a look at the wikipedia page that you provided and also look up the other methods like Sum of Squares, Sum of Absolute Values etc over the next couple of days and get back with what I find.

Thanks again.

 

[tkhunny]

Re: Pair t test

No worries. Let's see what you get.