1. ## Sturges' Formula

How can I prove Sturges' formula for determining number of classes in frequency distribution? k=Log2n+1 (n=number of data, k=number of classes)

2. ## Re: Sturges' Formula

What do you want to prove?

3. ## Re: Sturges' Formula

I wrote, k=log n+1 (log base is 2)

4. ## Re: Sturges' Formula

You'll need to be more specific. Sturges' Formula isn't a theorem - it's a rule for how many bins to use. It may or may not give the "optimal" number of bins (for some measure of optimal) depending on the actual underlying data. But we aren't mind readers so you'll have to be more specific.

5. ## Re: Sturges' Formula

Not sure why OP suddenly interested in this topic, but as always you may first try to find out the original paper first:

The Choice of a Class Interval

http://www.jstor.org/discover/10.230...21102671800931

Sorry I am not a student now and do not have access to E-Journals.

6. ## Re: Sturges' Formula

Oooo, that is an old paper. Those are fun sometimes since they seem to be straight to the point. Yes, BGM has a good point on finding the source document. I am sure there are also numerous comparison papers between methods that illustrate the pros and cons.

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts