Tip:
Highlight text to annotate it
X
Now, suppose we've collected like a lot of data, like 100 peoples 100 mens
weights, as part of a nutrition study and they range in value from 121 to, you
know, a high for 263 for a total span of 142 and these scores might be all over
the place. So we might have 100 different weights
and if we tried to create a frequency table for each, showing each individual
weight and the frequency, we'd probably get a lot of frequencies of 1.
In fact, almost all of your values would probably have a frequency of 1.
And so, what we're going to do is group the data into something called classes or
class intervals, and so this is going to be a range of values and then we can
create a frequency table based on the range of values.
and so, there's a, it, there's a lot sort of decisions we have to make here, one of
which is, is how many classes we want to have.
And usually, we want we want somewhere in the range of 5 to 20 classes or groupings
depending upon sort of how much data we have or how big the the data set is.
and so, so even often times, it's nice to have the value, the ranges were start in
nice values, so that's not necessary. and we, but it is important that each
interval be the same size. And so, we could say with our, with our a
hundred 142 values here you, we would have a lot of options let's consider a
couple. So for example, I could have let's see,
so I mean like one option would be if I used ten classes.
sorry, actually let's do 14 classes. then the width of each one would be
around 10. So I could create a class like 100 to 129
and 130 to 139 and I'd end up with 14 classes that way.
and so that'd be one option. I'm, I think I'm going to go for a
slightly different approach here and I'm going to make my classes a little wider.
I'm going to use a class width of 15. So I'm going to start at 120, even
though, my data starts at 121, just because it's a nice number.
and so my first class, my first class interval will be 120 to 134.
my next one will start at the next value up, so 135 up to 149 just as I, as a
point of clarification. If my data included decimals like you
know, if people reported their weights as 135 and a half, then this class would
need to go all the way up to like, you know, 140, 34.99 in order to cover those
decimals. but, we're going to assume for the
simplicity for now that, that that's not the case and so, my classes would
continue developing something something like this.
So, here is the rest of our, our, our class intervals and, and then I put in
some frequencies, of course, this would come from the actual data.
This would tell us that four students weights were in the range of 120 to 134
and 14 students weights were in this interval.
and now that we have this, we can create our histogram.
So our histogram here would start at, let's say 120 and then, maybe 135 and 150
and 165, and so on, and so forth. and, so, our first bar here would start,
would have a height of four and would start at 120 and go up to but not include
[UNKNOWN] not include. So it goes up to 135 because we're going
up to 135. My next category would have a height of
14, which I don't think I left enough room for.
So we'll just pretend, 14 and extend out to 150, right?
So it's including this entire range of values.
Let me show you what this is supposed to look like.
This is what that that histogram would end up looking like.
And this very nicely shows the distribution of, of weights.
Now, some, some software doesn't let you put the values along the axis like this.
And if that's the case, you can create a bar graph where the title of the bar is
the range of values. And that does a pretty good job at
capturing the same idea.