Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

I have a response variable in a model that is calculated from binary values of an 8x8 grid of pixels, giving a proportion. Technically, there are only 64 possible values the result can take, so would this count as discrete data? There are many values, and there are not integers. Would it be fair to describe the variable as pseudo-continuous?

The values, I suppose, are 1/64, 2/64. 3/64, 4/64 etc.

share|improve this question
add comment

1 Answer

up vote 5 down vote accepted

There is no right answer to this question. Almost all real-world data is "really" discrete, but it is often more convenient to model it as continuous. You should follow whichever option gives you the easiest model. For example, if the distribution of values appears to be a smooth curve, use a continuous distribution. If you have a huge amount of data and can can simply count how often each possibility appears, use the discrete distribution.

share|improve this answer
    
Is there a technical way to describe this (e.g. pseudo-continuous) or should I just call it continuous and be prepared to defend it if necessary? –  gisol Aug 20 '12 at 16:15
add comment

Your Answer

 
discard

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.