WEBVTT

00:00:00.660 --> 00:00:06.650
We will now begin our journey
into the world of statistics,

00:00:06.650 --> 00:00:09.750
which is really a way
to understand or get

00:00:09.750 --> 00:00:11.520
our head around data.

00:00:11.520 --> 00:00:14.670
So statistics is all about data.

00:00:14.670 --> 00:00:19.000
And as we begin our journey
into the world of statistics,

00:00:19.000 --> 00:00:20.610
we will be doing
a lot of what we

00:00:20.610 --> 00:00:23.210
can call descriptive statistics.

00:00:23.210 --> 00:00:25.470
So if we have a bunch
of data, and if we

00:00:25.470 --> 00:00:27.990
want to tell something
about all of that data

00:00:27.990 --> 00:00:29.890
without giving them
all of the data,

00:00:29.890 --> 00:00:33.870
can we somehow describe it
with a smaller set of numbers?

00:00:33.870 --> 00:00:35.720
So that's what we're
going to focus on.

00:00:35.720 --> 00:00:37.360
And then once we
build our toolkit

00:00:37.360 --> 00:00:39.260
on the descriptive
statistics, then we

00:00:39.260 --> 00:00:41.710
can start to make
inferences about that data,

00:00:41.710 --> 00:00:44.200
start to make conclusions,
start to make judgments.

00:00:44.200 --> 00:00:49.430
And we'll start to do a lot
of inferential statistics,

00:00:49.430 --> 00:00:51.160
make inferences.

00:00:51.160 --> 00:00:53.110
So with that out of
the way, let's think

00:00:53.110 --> 00:00:56.390
about how we can describe data.

00:00:56.390 --> 00:01:00.710
So let's say we have
a set of numbers.

00:01:00.710 --> 00:01:02.360
We can consider this to be data.

00:01:02.360 --> 00:01:04.580
Maybe we're measuring
the heights of our plants

00:01:04.580 --> 00:01:05.740
in our garden.

00:01:05.740 --> 00:01:07.400
And let's say we
have six plants.

00:01:07.400 --> 00:01:13.870
And the heights are 4 inches,
3 inches, 1 inch, 6 inches,

00:01:13.870 --> 00:01:17.990
and another one's 1 inch,
and another one is 7 inches.

00:01:17.990 --> 00:01:20.934
And let's say someone just
said-- in another room, not

00:01:20.934 --> 00:01:22.350
looking at your
plants, just said,

00:01:22.350 --> 00:01:24.657
well, you know, how
tall are your plants?

00:01:24.657 --> 00:01:26.240
And they only want
to hear one number.

00:01:26.240 --> 00:01:30.560
They want to somehow
have one number that

00:01:30.560 --> 00:01:33.410
represents all of these
different heights of plants.

00:01:33.410 --> 00:01:36.580
How would you do that?

00:01:36.580 --> 00:01:38.810
Well, you'd say, well,
how can I find something

00:01:38.810 --> 00:01:40.990
that-- maybe I want
a typical number.

00:01:40.990 --> 00:01:44.060
Maybe I want some number that
somehow represents the middle.

00:01:44.060 --> 00:01:46.250
Maybe I want the
most frequent number.

00:01:46.250 --> 00:01:48.830
Maybe I want the number
that somehow represents

00:01:48.830 --> 00:01:51.270
the center of all
of these numbers.

00:01:51.270 --> 00:01:53.220
And if you said any
of those things,

00:01:53.220 --> 00:01:55.189
you would actually have
done the same things

00:01:55.189 --> 00:01:57.730
that the people who first came
up with descriptive statistics

00:01:57.730 --> 00:01:58.230
said.

00:01:58.230 --> 00:02:00.150
They said, well,
how can we do it?

00:02:00.150 --> 00:02:04.960
And we'll start by thinking
of the idea of average.

00:02:04.960 --> 00:02:07.610
And in every day
terminology, average

00:02:07.610 --> 00:02:09.720
has a very particular
meaning, as we'll see.

00:02:09.720 --> 00:02:11.570
When many people
talk about average,

00:02:11.570 --> 00:02:13.070
they're talking
about the arithmetic

00:02:13.070 --> 00:02:14.960
mean, which we'll see shortly.

00:02:14.960 --> 00:02:18.100
But in statistics, average
means something more general.

00:02:18.100 --> 00:02:22.980
It really means
give me a typical,

00:02:22.980 --> 00:02:29.810
or give me a middle number,
or-- and these are or's.

00:02:29.810 --> 00:02:31.930
And really it's
an attempt to find

00:02:31.930 --> 00:02:33.490
a measure of central tendency.

00:02:38.550 --> 00:02:40.560
So once again, you have
a bunch of numbers.

00:02:40.560 --> 00:02:42.970
You're somehow trying
to represent these

00:02:42.970 --> 00:02:45.840
with one number we'll call
the average, that's somehow

00:02:45.840 --> 00:02:49.130
typical, or middle,
or the center somehow

00:02:49.130 --> 00:02:50.450
of these numbers.

00:02:50.450 --> 00:02:54.110
And as we'll see, there's
many types of averages.

00:02:54.110 --> 00:02:56.690
The first is the one that you're
probably most familiar with.

00:02:56.690 --> 00:02:58.398
It's the one-- and
people talk about hey,

00:02:58.398 --> 00:03:00.840
the average on this exam
or the average height.

00:03:00.840 --> 00:03:02.970
And that's the arithmetic mean.

00:03:02.970 --> 00:03:05.470
Just let me write it in.

00:03:05.470 --> 00:03:13.100
I'll write in yellow,
arithmetic mean.

00:03:13.100 --> 00:03:16.010
When arithmetic is a noun,
we call it arithmetic.

00:03:16.010 --> 00:03:19.960
When it's an adjective like
this, we call it arithmetic,

00:03:19.960 --> 00:03:21.620
arithmetic mean.

00:03:21.620 --> 00:03:25.300
And this is really just the
sum of all the numbers divided

00:03:25.300 --> 00:03:28.180
by-- this is a human-constructed
definition that we've

00:03:28.180 --> 00:03:31.630
found useful-- the sum of
all these numbers divided

00:03:31.630 --> 00:03:34.460
by the number of
numbers we have.

00:03:34.460 --> 00:03:36.830
So given that, what
is the arithmetic mean

00:03:36.830 --> 00:03:39.114
of this data set?

00:03:39.114 --> 00:03:40.280
Well, let's just compute it.

00:03:40.280 --> 00:03:46.160
It's going to be 4 plus
3 plus 1 plus 6 plus 1

00:03:46.160 --> 00:03:51.210
plus 7 over the number
of data points we have.

00:03:51.210 --> 00:03:53.210
So we have six data points.

00:03:53.210 --> 00:03:54.860
So we're going to divide by 6.

00:03:54.860 --> 00:04:01.840
And we get 4 plus 3 is 7,
plus 1 is 8, plus 6 is 14,

00:04:01.840 --> 00:04:04.934
plus 1 is 15, plus 7.

00:04:04.934 --> 00:04:07.927
15 plus 7 is 22.

00:04:07.927 --> 00:04:09.135
Let me do that one more time.

00:04:09.135 --> 00:04:15.180
You have 7, 8, 14, 15,
22, all of that over 6.

00:04:15.180 --> 00:04:17.070
And we could write
this as a mixed number.

00:04:17.070 --> 00:04:21.120
6 goes into 22 three times
with a remainder of 4.

00:04:21.120 --> 00:04:25.200
So it's 3 and 4/6, which is
the same thing as 3 and 2/3.

00:04:25.200 --> 00:04:28.670
We could write this as a
decimal with 3.6 repeating.

00:04:28.670 --> 00:04:32.360
So this is also 3.6 repeating.

00:04:32.360 --> 00:04:34.380
We could write it any
one of those ways.

00:04:34.380 --> 00:04:36.700
But this is kind of a
representative number.

00:04:36.700 --> 00:04:39.820
This is trying to get
at a central tendency.

00:04:39.820 --> 00:04:41.620
Once again, these are
human-constructed.

00:04:41.620 --> 00:04:43.590
No one ever-- it's
not like someone just

00:04:43.590 --> 00:04:46.140
found some religious
document that said,

00:04:46.140 --> 00:04:47.990
this is the way that
the arithmetic mean

00:04:47.990 --> 00:04:49.180
must be defined.

00:04:49.180 --> 00:04:52.700
It's not as pure
of a computation

00:04:52.700 --> 00:04:55.005
as, say, finding the
circumference of the circle,

00:04:55.005 --> 00:04:56.880
which there really is--
that was kind of-- we

00:04:56.880 --> 00:04:57.840
studied the universe.

00:04:57.840 --> 00:05:00.600
And that just fell out of
our study of the universe.

00:05:00.600 --> 00:05:02.250
It's a human-constructed
definition

00:05:02.250 --> 00:05:04.110
that we found useful.

00:05:04.110 --> 00:05:07.260
Now there are other ways
to measure the average

00:05:07.260 --> 00:05:10.130
or find a typical
or middle value.

00:05:10.130 --> 00:05:14.470
The other very typical
way is the median.

00:05:14.470 --> 00:05:15.667
And I will write median.

00:05:15.667 --> 00:05:16.750
I'm running out of colors.

00:05:16.750 --> 00:05:18.660
I will write median in pink.

00:05:18.660 --> 00:05:21.280
So there is the median.

00:05:21.280 --> 00:05:25.160
And the median is literally
looking for the middle number.

00:05:25.160 --> 00:05:27.350
So if you were to order
all the numbers in your set

00:05:27.350 --> 00:05:31.460
and find the middle one,
then that is your median.

00:05:31.460 --> 00:05:34.050
So given that, what's the
median of this set of numbers

00:05:34.050 --> 00:05:35.806
going to be?

00:05:35.806 --> 00:05:36.930
Let's try to figure it out.

00:05:36.930 --> 00:05:38.170
Let's try to order it.

00:05:38.170 --> 00:05:39.810
So we have 1.

00:05:39.810 --> 00:05:41.010
Then we have another 1.

00:05:41.010 --> 00:05:42.860
Then we have a 3.

00:05:42.860 --> 00:05:46.630
Then we have a 4, a 6, and a 7.

00:05:46.630 --> 00:05:48.700
So all I did is
I reordered this.

00:05:48.700 --> 00:05:50.890
And so what's the middle number?

00:05:50.890 --> 00:05:52.320
Well, you look here.

00:05:52.320 --> 00:05:54.960
Since we have an even number of
numbers, we have six numbers,

00:05:54.960 --> 00:05:57.260
there's not one middle number.

00:05:57.260 --> 00:05:59.650
You actually have two
middle numbers here.

00:05:59.650 --> 00:06:02.050
You have two middle
numbers right over here.

00:06:02.050 --> 00:06:03.160
You have the 3 and the 4.

00:06:03.160 --> 00:06:05.940
And in this case, when you
have two middle numbers,

00:06:05.940 --> 00:06:09.640
you actually go halfway
between these two numbers.

00:06:09.640 --> 00:06:12.080
You're essentially taking the
arithmetic mean of these two

00:06:12.080 --> 00:06:14.272
numbers to find the median.

00:06:14.272 --> 00:06:16.230
So the median is going
to be halfway in-between

00:06:16.230 --> 00:06:19.190
3 and 4, which is
going to be 3.5.

00:06:19.190 --> 00:06:24.424
So the median in
this case is 3.5.

00:06:24.424 --> 00:06:26.590
So if you have an even
number of numbers, the median

00:06:26.590 --> 00:06:28.714
or the middle two, the--
essentially the arithmetic

00:06:28.714 --> 00:06:31.329
mean of the middle two, or
halfway between the middle two.

00:06:31.329 --> 00:06:32.870
If you have an odd
number of numbers,

00:06:32.870 --> 00:06:34.270
it's a little bit
easier to compute.

00:06:34.270 --> 00:06:35.644
And just so that
we see that, let

00:06:35.644 --> 00:06:36.920
me give you another data set.

00:06:36.920 --> 00:06:39.030
Let's say our data
set-- and I'll

00:06:39.030 --> 00:06:41.740
order it for us--
let's say our data set

00:06:41.740 --> 00:06:55.689
was 0, 7, 50, I don't know,
10,000, and 1 million.

00:06:55.689 --> 00:06:56.980
Let's say that is our data set.

00:06:56.980 --> 00:06:58.450
Kind of a crazy data set.

00:06:58.450 --> 00:07:02.400
But in this situation,
what is our median?

00:07:02.400 --> 00:07:04.045
Well, here we have five numbers.

00:07:04.045 --> 00:07:05.420
We have an odd
number of numbers.

00:07:05.420 --> 00:07:07.200
So it's easier to
pick out a middle.

00:07:07.200 --> 00:07:12.040
The middle is the number that is
greater than two of the numbers

00:07:12.040 --> 00:07:13.540
and is less than
two of the numbers.

00:07:13.540 --> 00:07:14.760
It's exactly in the middle.

00:07:14.760 --> 00:07:18.840
So in this case,
our median is 50.

00:07:18.840 --> 00:07:20.742
Now, the third measure
of central tendency,

00:07:20.742 --> 00:07:22.200
and this is the
one that's probably

00:07:22.200 --> 00:07:26.426
used least often in
life, is the mode.

00:07:26.426 --> 00:07:27.800
And people often
forget about it.

00:07:27.800 --> 00:07:29.852
It sounds like
something very complex.

00:07:29.852 --> 00:07:31.310
But what we'll see
is it's actually

00:07:31.310 --> 00:07:33.080
a very straightforward idea.

00:07:33.080 --> 00:07:36.180
And in some ways, it
is the most basic idea.

00:07:36.180 --> 00:07:40.510
So the mode is actually the most
common number in a data set,

00:07:40.510 --> 00:07:41.885
if there is a most
common number.

00:07:41.885 --> 00:07:43.801
If all of the numbers
are represented equally,

00:07:43.801 --> 00:07:45.760
if there's no one single
most common number,

00:07:45.760 --> 00:07:47.320
then you have no mode.

00:07:47.320 --> 00:07:50.240
But given that
definition of the mode,

00:07:50.240 --> 00:07:54.190
what is the single most common
number in our original data

00:07:54.190 --> 00:07:58.300
set, in this data
set right over here?

00:07:58.300 --> 00:08:00.100
Well, we only have one 4.

00:08:00.100 --> 00:08:01.490
We only have one 3.

00:08:01.490 --> 00:08:03.370
But we have two 1's.

00:08:03.370 --> 00:08:04.880
We have one 6 and one 7.

00:08:04.880 --> 00:08:08.730
So the number that shows up
the most number of times here

00:08:08.730 --> 00:08:11.060
is our 1.

00:08:11.060 --> 00:08:14.070
So the mode, the most typical
number, the most common number

00:08:14.070 --> 00:08:17.610
here is a 1.

00:08:17.610 --> 00:08:19.590
So, you see, these
are all different ways

00:08:19.590 --> 00:08:23.320
of trying to get at a typical,
or middle, or central tendency.

00:08:23.320 --> 00:08:25.600
But they do it in very,
very different ways.

00:08:25.600 --> 00:08:27.350
And as we study more
and more statistics,

00:08:27.350 --> 00:08:29.760
we'll see that they're
good for different things.

00:08:29.760 --> 00:08:31.730
This is used very frequently.

00:08:31.730 --> 00:08:34.574
The median is really good if you
have some kind of crazy number

00:08:34.574 --> 00:08:35.990
out here that could
have otherwise

00:08:35.990 --> 00:08:38.100
skewed the arithmetic mean.

00:08:38.100 --> 00:08:41.449
The mode could also be useful
in situations like that,

00:08:41.449 --> 00:08:43.240
especially if you do
have one number that's

00:08:43.240 --> 00:08:45.960
showing up a lot
more frequently.

00:08:45.960 --> 00:08:47.570
Anyway, I'll leave you there.

00:08:47.570 --> 00:08:51.710
And we'll-- the next few videos,
we will explore statistics even

00:08:51.710 --> 00:08:53.260
deeper.