3
$\begingroup$

In Data Mining course, we are taking 3-4-5 Rule to segments the data uniformly.

I'm trying to understand these lines below, and how they are linked to the graph below too.

If an interval covers 3, 6, 7 or 9 distinct values at the most significant digit, partition the range into 3 equi-width intervals

If it covers 2, 4, or 8 distinct values at the most significant digit, partition the range into 4 intervals

If it covers 1, 5, or 10 distinct values at the most significant digit, partition the range into 5 intervals

Why did we partitioned step 3 into 3 intervals and step 4 to 4 intervals?

The graph: 3-4-5 Rule Example

Would really appreciate it if someone could help explaining my question above. Thanks!

$\endgroup$
-1
$\begingroup$

It is a refinement step for the original partitioning. You can refine the leftmost interval using the msd of 0 and the lowest value -351. Thus we get msd = 100 and get the new interval (-400,0). We do not have all values covered on the right side, so we add another interval starting at 2000 where the highest value of our data is 4700. Thus the msd = 1000 giving us the interval (2000,5000).

Now our first partitioning covers all values occurring in our data.

I hope, i could help you with your problem.

$\endgroup$
  • 16
    $\begingroup$ It would be helpful to explain the statistical principles on which this method is based, if there are any. $\endgroup$ – Frank Harrell Apr 6 '14 at 12:51

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