Tip:
Highlight text to annotate it
X
Hello my name is Beth Dixon and this is part six of a video series on frequency distribution
and histograms and I would like to apologize for having it to be so long but then I got to looking
and Mrs. Borlaug made a
PowerPoint of over 80 slides and it just takes this long to get that information across because the information is so deep and so detailed
and speaking of Mrs. Borlaug again I'd like to thank Mrs. Borlaug for the use of her
power points
to help us with this video
histograms can help us visualize characteristics of the data set
we have some histograms here histograms A
B, C, D and E
and we're going to look more at these histograms
histograms can tell us about the shape of data
what can that shape tell us
with these five examples of histograms shown we can describe some different shapes of the data
which histogram looks like it came from a uniformly distributed data
data is spread evenly over all the possible values
that would be histogram D
notice how all the heights
are very uniform in frequency not exactly but close and the data remains the same
as we look at it from left to right
again looking at the shapes
which data looks like it came from a data set that is skewed to the right
when data is skewed to the right it has a longer right tail
more data to the right than we would expect
in other words
the data trails off with values to the right that go on and on like the energizer bunny
it just doesn't seem to want to quit
look at the shape
look at each shape we can eliminate histogram D we said it was
uniform it doesn't seem to fit
that would be histogram C
histogram C has that tail of data to the right where the right hand data just seems to have more data on the right hand side
than we would expect no the frequencies are not high on the right hand side but there seems to be more of it toward
that right hand side so it's skewed to the right
notice that here
clearing that question out which histogram looks like it came from a data set that is skewed to the left
well
histogram D is fairly evenly
distributed or uniformly distributed
histogram C we said had a tail to the right
we're looking for one with a tail to the left
with more of its data
on the left hand side
that would be
here
histogram E
Skewness is one of the things hard for me to explain just remember that the direction of the tail is the direction of the skewness
that takes care of the two types of skewness now what other shapes can we describe
which histogram looks like it came from a normally distributed data
this data will be shaped like a bell
this data will be mostly symmetrical
it will have this same shape from a middle point looking at histograms although histogram D is symmetrical it's not shaped
like a bell
histogram E we said was skewed it's not shaped like a bell
histograms C is not shaped like a bell and my bells are awful on this computer (LOL) but you can see
hopefully
that histogram B
is a very much shaped like a bell
one last shape then to describe
which looks like it came from a data set that is bimodal
data that has two values that occur most often
and that of course leaves histogram A it has a peak
and then a second peak
and therefore
most often once
most often twice and two areas
that
have two peaks or occur most often
now for that word of caution that I've been promising since the first video
always critically analyze your data that is presented to you
histograms can be tricky
and the people presenting them too can try to trick you and never turn your brain off when looking at the data or pictures of the data
you and your thinking skills
are always the best tools for that job
no computer can replace those critical thinking skills
and histogram A number one in histogram number two
some quick judgments about the data that represents
what's the difference between the two data sets
both histograms represent the same data did you catch that? the difference between the 2 graphs
is what?
the difference it is the value of the tick marks on the vertical axis
0 to 7, 8 to 15,16 to 23, 24 to 31, 32 to 39, and 40 to 48 is the same for both
histograms
the height of the first one looks to be 39
the height of the second one looks to be about 37
then 45
the next one 42
maybe 41
then back to 39
and then lastly 41
and that does look to be 42 if that's 41 so the heights are the same and yet the differences between the
groups are exaggerated
in histogram two
to avoid this misrepresentation the vertical axis
for the histograms should always start
with what value
if histogram two exaggerates that misrepresentation or the differences between the groups you should always then start with zero
that concludes this presentation and this series on histograms
thank you for watching
and we're signing off
All spelling errors are mine-- no comments or laughter please. Beth Dixon