# Statistical Learning/Classification problem (True or false)

I think the answer is false, but I'm not entirely sure how to put it into words. The problem is as follows:

An electronic store wants to build a model to predict the number of televisions that it will sell in a year. Since the variable being predicted is discrete (i.e. integer valued), this is best viewed as a classification problem and logistic regression would be an appropriate tool.

Anyone able to shred some insight into the problem?
Thanks!

• The outcome is not discrete. This is a regression problem, where you predict a numeric value (number of items sold). – lnathan Mar 8 at 14:53
• Please do not vandalize your question. Once you post it & it has an upvoted answer, it is not to be deleted. SE sites (such as Cross Validated) have 2 goals: to help the OP (short term), & to provide a permanent repository of high quality information in the form of questions & answers (long term). In using the site you have agreed to that (even if most people skim over it). – gung Mar 8 at 20:01

## 1 Answer

The variable being predicted is discrete in that presumably only whole/integer numbers of TVs can be sold (but if the numbers being sold are large enough then it may be possible to approximate it to a continuous distribution, e.g. to a Normal distribution, with a continuity correction).

I wouldn't call this a classification problem, because the outcome variable is not categorical. So I agree with lnathan that it is a regression problem, not a classification problem.

As a starting point for this type of data, if there were lots of low counts (0's and 1's etc.), I would use a general linear model with a Poisson distribution, or with a negative binomial distribution if needed. Or if the counts were large (generally, lambda>10) then I would approximate to a Normal distribution.

I would tend to use logistic regression for cases where the outcomes are categorical rather than numeric. In its simplest form this is where the outcome is binary (e.g. 'Yes'/'No').