The Student Room Group

Grouped data

How would you form a grouped frequency table using 6 equal classes given 30 values of data? Is there a method of doing this?
Original post by Peanut247
How would you form a grouped frequency table using 6 equal classes given 30 values of data? Is there a method of doing this?


Round lowest value down for your lower bound, higher value up for your upper bound and then divide the new range by how many classes you want for your interval length (assuming you want the classes to be 'neat').

Posted from TSR Mobile
(edited 9 years ago)
Original post by Peanut247
How would you form a grouped frequency table using 6 equal classes given 30 values of data? Is there a method of doing this?

I'm not familiar with this as part of the syllabus, but I imagine you'd need to order the data and then come up with six intervals (preferably as close to equally-sized as possible, for neatness) such that a sixth of the data lies in each interval.
Reply 3
Original post by Arithmeticae
Round lowest value down for your lower bound, higher value up for your upper bound and then divide the new range by how many classes you want for your interval length (assuming you want the classes to be 'neat').

Posted from TSR Mobile


Round it by how much?

the back of the book sys 3.95, 5.95, 7.95, 9.95, q11.95, 13.95 , 15.95

but I have no idea how to get there!!
Reply 4
Original post by Smaug123
I'm not familiar with this as part of the syllabus, but I imagine you'd need to order the data and then come up with six intervals (preferably as close to equally-sized as possible, for neatness) such that a sixth of the data lies in each interval.


But is there a way of figuring how the intervals? Because I'd be there for hours. I've posted the answers above.
Original post by Peanut247
But is there a way of figuring how the intervals? Because I'd be there for hours. I've posted the answers above.

Oh, I see what they mean - I interpreted their request as "group the data into six buckets such that the number in each bucket is equal", whereas they wanted "group the data into six equally-sized buckets". I still don't see why they'd use the numbers 4,6,8,10,12,14,16 rather than the interval 4.2 to 14.3 split into six, though.
Original post by Peanut247
X


First off, they've just rounded to 4 and 16 (rounding lowest value down to integer and highest value up to integer). The gap is 12, so dividing this by 6 gives an interval size of 2. Then simply take the lower bound of each of the new intervals, and you're pretty much done.

Seems like a strange way of going about things though.

Posted from TSR Mobile
Original post by Arithmeticae
First off, they've just rounded to 4 and 16. The gap is 12, so dividing this by 6 gives an interval size of 2. Then simply take the lower bound of each of the new intervals, and you're pretty much done.

It seems to me that their rounding is a bit arbitrary - why not round to the nearest .5, for instance, or even to the nearest 1?
Original post by Smaug123
It seems to me that their rounding is a bit arbitrary - why not round to the nearest .5, for instance, or even to the nearest 1?
That's exactly what I though, no idea why they've chosen to do it like this instead of just taking the range straight from the lowest to highest value.

Maybe it's explained in more detail in another chapter of the book (I can't say I'm too familiar with this method though :s-smilie:). My guess is that it's something to do with the degree of accuracy of the original data, but that's just my thoughts.

Quick Reply