WEBVTT

00:00:00.500 --> 00:00:02.620
It never hurts to get
a bit more practice.

00:00:02.620 --> 00:00:05.600
So this is problem number five
from the normal distribution

00:00:05.600 --> 00:00:11.560
chapter from ck12.org's
AP statistics FlexBook.

00:00:11.560 --> 00:00:16.030
So they're saying, the 2007 AP
statistics examination scores

00:00:16.030 --> 00:00:20.750
were not normally distributed
with a mean of 2.8

00:00:20.750 --> 00:00:23.964
and a standard
deviation of 1.34.

00:00:23.964 --> 00:00:25.630
They cite some College
Board stuff here.

00:00:25.630 --> 00:00:27.170
I didn't copy and paste that.

00:00:27.170 --> 00:00:29.170
What is the approximate z-score?

00:00:29.170 --> 00:00:31.530
Remember, z-score
is just how many

00:00:31.530 --> 00:00:33.980
standard deviations you
are away from the mean.

00:00:33.980 --> 00:00:35.950
What is the approximate
z-score that

00:00:35.950 --> 00:00:39.337
corresponds to an
exam score of 5?

00:00:39.337 --> 00:00:40.920
So we really just
have to figure out--

00:00:40.920 --> 00:00:42.628
this is a pretty
straightforward problem.

00:00:42.628 --> 00:00:45.720
We just need to figure out how
many standard deviations is

00:00:45.720 --> 00:00:48.340
5 from the mean?

00:00:48.340 --> 00:00:53.370
Well, you just take
5 minus 2.8, right?

00:00:53.370 --> 00:00:54.400
The mean is 2.8.

00:00:54.400 --> 00:00:56.121
Let me be very
clear, mean is 2.8.

00:00:56.121 --> 00:00:56.870
They give us that.

00:00:56.870 --> 00:00:58.800
Didn't even have
to calculate it.

00:00:58.800 --> 00:01:00.230
So the mean is 2.8.

00:01:00.230 --> 00:01:03.760
So 5 minus 2.8 is equal to 2.2.

00:01:03.760 --> 00:01:06.374
So we're 2.2 above the mean.

00:01:06.374 --> 00:01:08.540
And if we want that in terms
of standard deviations,

00:01:08.540 --> 00:01:10.770
we just divide by our
standard deviation.

00:01:10.770 --> 00:01:14.860
You divide by 1.34.

00:01:14.860 --> 00:01:17.290
Divide by 1.34.

00:01:17.290 --> 00:01:20.710
I'll take out the
calculator for this.

00:01:20.710 --> 00:01:31.280
So we have 2.2 divided
by 1.34 is equal to 1.64.

00:01:31.280 --> 00:01:34.966
So this is equal to 1.64.

00:01:34.966 --> 00:01:37.590
And that's choice C. So this was
actually very straightforward.

00:01:37.590 --> 00:01:40.620
We just have to see how far
away we are from the mean

00:01:40.620 --> 00:01:42.929
if we get a score of
5-- which hopefully you

00:01:42.929 --> 00:01:44.720
will get if you're
taking the AP statistics

00:01:44.720 --> 00:01:46.242
exam after watching
these videos.

00:01:46.242 --> 00:01:48.450
And then you divide by the
standard deviation to say,

00:01:48.450 --> 00:01:50.850
how many standard deviations
away from the mean

00:01:50.850 --> 00:01:52.230
is the score of 5?

00:01:52.230 --> 00:01:53.545
It's 1.64.

00:01:53.545 --> 00:01:55.670
I think the only tricky
thing here might have been,

00:01:55.670 --> 00:01:58.400
you might have been tempted
to pick choice E, which says,

00:01:58.400 --> 00:02:01.300
the z-score cannot be calculated
because the distribution is not

00:02:01.300 --> 00:02:01.800
normal.

00:02:01.800 --> 00:02:04.700
And I think the reason why you
might have had that temptation

00:02:04.700 --> 00:02:07.430
is because we've
been using z-scores

00:02:07.430 --> 00:02:10.300
within the context of
a normal distribution.

00:02:10.300 --> 00:02:12.860
But a z-score literally
just means how many

00:02:12.860 --> 00:02:15.950
standard deviations you
are away from the mean.

00:02:15.950 --> 00:02:18.290
It could apply to
any distribution

00:02:18.290 --> 00:02:21.820
that you could calculate a mean
and a standard deviation for.

00:02:21.820 --> 00:02:23.910
So E is not the correct answer.

00:02:23.910 --> 00:02:27.045
A z-score can apply to a
non-normal distribution.

00:02:27.045 --> 00:02:29.170
So the answer is C. And I
guess that's a good point

00:02:29.170 --> 00:02:31.094
of clarification to
get out of the way.

00:02:31.094 --> 00:02:33.260
And I thought I would do
two problems in this video,

00:02:33.260 --> 00:02:35.460
just because that
one was pretty short.

00:02:35.460 --> 00:02:36.900
So problem number six.

00:02:36.900 --> 00:02:39.350
The height of fifth grade
boys in the United States

00:02:39.350 --> 00:02:41.480
is approximately
normally distributed--

00:02:41.480 --> 00:02:45.690
that's good to know-- with
a mean height of 143.5

00:02:45.690 --> 00:02:46.410
centimeters.

00:02:46.410 --> 00:02:50.960
So it's a mean of
143.5 centimeters

00:02:50.960 --> 00:02:56.635
and a standard deviation
of about 7.1 centimeters.

00:03:01.700 --> 00:03:04.620
What is the probability that
a randomly chosen fifth grade

00:03:04.620 --> 00:03:09.134
boy would be taller
than 157.7 centimeters?

00:03:09.134 --> 00:03:10.800
So let's just draw
out this distribution

00:03:10.800 --> 00:03:13.755
like we've done in a
bunch of problems so far.

00:03:13.755 --> 00:03:15.600
They're just asking
us one question,

00:03:15.600 --> 00:03:19.320
so we can mark this
distribution up a good bit.

00:03:19.320 --> 00:03:21.410
Let's say that's
our distribution.

00:03:21.410 --> 00:03:28.270
And the mean here, the
mean they told us is 143.5.

00:03:28.270 --> 00:03:30.414
They're asking us
taller than 157.7.

00:03:30.414 --> 00:03:32.080
So we're going in the
upwards direction.

00:03:32.080 --> 00:03:35.360
So one standard
deviation above the mean

00:03:35.360 --> 00:03:37.740
will take us right there.

00:03:37.740 --> 00:03:40.510
And we just have to add 7.1
to this number right here.

00:03:40.510 --> 00:03:42.700
We're going up by 7.1.

00:03:42.700 --> 00:03:45.980
So 143.5 plus 7.1 is what?

00:03:45.980 --> 00:03:49.440
150.6.

00:03:49.440 --> 00:03:51.047
That's one standard deviation.

00:03:51.047 --> 00:03:52.880
If we were to go another
standard deviation,

00:03:52.880 --> 00:03:54.950
we'd go 7.1 more.

00:03:54.950 --> 00:03:57.500
What's 7.1 plus 150.6?

00:03:57.500 --> 00:04:02.950
It's 157.7, which
just happens to be

00:04:02.950 --> 00:04:04.220
the exact number they ask for.

00:04:04.220 --> 00:04:06.240
They're asking for
the probability

00:04:06.240 --> 00:04:08.304
of getting a height
higher than that.

00:04:08.304 --> 00:04:10.470
So they want to know, what's
the probability that we

00:04:10.470 --> 00:04:12.830
fall under this area right here?

00:04:12.830 --> 00:04:15.980
Or essentially more than
two standard deviations

00:04:15.980 --> 00:04:16.630
from the mean.

00:04:16.630 --> 00:04:18.670
Or above two
standard deviations.

00:04:18.670 --> 00:04:21.420
We can't count this
left tail right there.

00:04:21.420 --> 00:04:24.480
So we can use the
empirical rule.

00:04:24.480 --> 00:04:26.630
If we do our standard
deviations to the left,

00:04:26.630 --> 00:04:29.830
that's one standard deviation,
two standard deviations.

00:04:29.830 --> 00:04:32.010
We know what this whole area is.

00:04:32.010 --> 00:04:35.660
Let me pick a different
color so that I don't.

00:04:35.660 --> 00:04:39.170
So we know what this
area is, the area

00:04:39.170 --> 00:04:40.780
within two standard deviations.

00:04:40.780 --> 00:04:42.020
The empirical rule tells us.

00:04:42.020 --> 00:04:46.820
Or even better, the
68, 95, 99.7 rule

00:04:46.820 --> 00:04:48.830
tells us that this
area-- because it's

00:04:48.830 --> 00:04:55.300
within two standard
deviations-- is 95%, or 0.95.

00:04:55.300 --> 00:04:59.740
Or it's 95% of the area under
the normal distribution.

00:04:59.740 --> 00:05:02.400
Which tells us that what's
left over-- this tail

00:05:02.400 --> 00:05:04.880
that we care about and
this left tail right here--

00:05:04.880 --> 00:05:08.340
has to make up the
rest of it, or 5%.

00:05:08.340 --> 00:05:12.216
So those two combined
have to be 5%.

00:05:12.216 --> 00:05:13.570
And these are symmetrical.

00:05:13.570 --> 00:05:14.590
We've done this before.

00:05:14.590 --> 00:05:16.330
This is actually a little
redundant from other problems

00:05:16.330 --> 00:05:17.250
we've done.

00:05:17.250 --> 00:05:20.010
But if these are added, combined
5%, and they're the same,

00:05:20.010 --> 00:05:22.580
then each of these are 2.5%.

00:05:22.580 --> 00:05:24.792
Each of these are 2.5%.

00:05:24.792 --> 00:05:26.250
So the answer to
the question, what

00:05:26.250 --> 00:05:29.160
is the probability that a
randomly chosen fifth grade boy

00:05:29.160 --> 00:05:32.820
would be taller then
157.7 centimeters.

00:05:32.820 --> 00:05:34.320
Well, that's literally
just the area

00:05:34.320 --> 00:05:35.927
under this right green part.

00:05:35.927 --> 00:05:37.510
Maybe I'll do it in
a different color.

00:05:37.510 --> 00:05:39.660
This magenta part that
I'm coloring right now.

00:05:39.660 --> 00:05:40.920
That's just that area.

00:05:40.920 --> 00:05:43.600
We just figured out it's 2.5%.

00:05:43.600 --> 00:05:47.780
So there's a 2.5% chance we'd
randomly find a fifth grade

00:05:47.780 --> 00:05:51.260
boy who's taller than
157.7 centimeters,

00:05:51.260 --> 00:05:53.650
assuming this is the mean,
the standard deviation,

00:05:53.650 --> 00:05:56.680
and we are dealing with
a normal distribution.