WEBVTT

00:00:00.000 --> 00:00:02.193
(female narrator)
This is just a couple of tips

00:00:02.193 --> 00:00:04.894
on how to use the 
significance test flow chart.

00:00:04.894 --> 00:00:11.738
As you go through each problem, this
flow chart can help you to determine

00:00:12.298 --> 00:00:15.908
what type of significance test you 
should perform on that problem.

00:00:15.908 --> 00:00:18.858
The first thing you want to do is you
want to read the problem.

00:00:18.858 --> 00:00:21.871
When you're done reading the 
problem, you need to ask yourself,

00:00:21.871 --> 00:00:24.778
"What was the data collected from 
each member of the sample?"

00:00:24.778 --> 00:00:27.605
For instance, did you collect 
a weight, or a height,

00:00:27.605 --> 00:00:29.606
or did you take their temperature,

00:00:29.606 --> 00:00:32.100
or did you count the number 
of dogs that they had?

00:00:32.100 --> 00:00:35.355
That would be numerical data. 
When you read the problem,

00:00:35.355 --> 00:00:40.223
did you see some key words like mean,
or average, or standard deviation.

00:00:40.223 --> 00:00:44.920
All of those things indicate that you
have a quantitative data problem.

00:00:45.510 --> 00:00:52.023
On the flip side of that, were there some
keywords like proportion, percent, rates,

00:00:52.023 --> 00:00:55.752
or was each member of the 
sample asked a yes or no question,

00:00:55.752 --> 00:00:59.108
such as, "Have you had 
a heart attack? Yes or no?"

00:01:00.118 --> 00:01:02.769
Maybe they were asked, "Are you 
overweight? Yes or no?"

00:01:02.769 --> 00:01:04.968
"Do you support the 
president? Yes or no?"

00:01:04.968 --> 00:01:07.967
So that type of a thing. That 
would be qualitative data.

00:01:07.967 --> 00:01:10.364
Once you determine the type of data,

00:01:10.364 --> 00:01:13.056
then you follow the decision 
tree down that side.

00:01:13.056 --> 00:01:17.867
For instance, if you have quantitative
data, then you would ask yourself,

00:01:17.867 --> 00:01:24.415
"Do I have two populations or 
do I have one population?"

00:01:24.415 --> 00:01:28.632
Now remember, an easy way to tell
whether you have one or two populations

00:01:28.632 --> 00:01:31.464
is to look for the samples 
that are given in the problem.

00:01:31.464 --> 00:01:34.854
If you're only given one sample,
then you only have one population.

00:01:34.854 --> 00:01:37.880
If you're given two samples, 
then you have two populations.

00:01:37.880 --> 00:01:41.996
You have to be given the complete
information about both of those samples,

00:01:41.996 --> 00:01:47.296
like the sample mean and sample standard
deviation, for two separate samples

00:01:47.296 --> 00:01:49.695
in order to determine 
you have two populations.

00:01:51.945 --> 00:01:55.412
Once you determine how 
many populations that you have,

00:01:55.412 --> 00:01:59.969
if you have one population, you're going
to do the t-stat one sample.

00:01:59.969 --> 00:02:02.278
If you have two independent populations,

00:02:02.278 --> 00:02:05.627
then you're going to do the 
t-stat two samples.

00:02:05.627 --> 00:02:11.293
Keep in mind that you need to determine
whether you're going to pull the variances

00:02:11.293 --> 00:02:13.177
or not pull the variances.

00:02:13.177 --> 00:02:16.242
Down here, we have the little 
tip on how to decide that.

00:02:16.242 --> 00:02:19.509
It's just the ratio of the larger 
sample standard deviation

00:02:19.509 --> 00:02:22.129
divided by the smaller sample
standard deviation,

00:02:22.129 --> 00:02:25.417
and looking to see if it's greater
than two, then you remove

00:02:25.417 --> 00:02:28.247
the pulled variances check mark, 
and if it's less than two,

00:02:28.247 --> 00:02:31.567
then you keep the pulled 
variances check mark.

00:02:31.567 --> 00:02:33.917
Now remember if you have 
two dependent samples,

00:02:33.917 --> 00:02:39.780
the two samples are related to each other,
such as a before and an after,

00:02:39.780 --> 00:02:45.058
a pre and a post test. The two samples are
related because it's the same person

00:02:45.058 --> 00:02:47.972
taking the pre-test and the 
same person taking the post-test,

00:02:47.972 --> 00:02:50.965
or maybe you're testing 
two different kinds of tires,

00:02:50.965 --> 00:02:53.848
so you take a car and you 
drive it with the first tire,

00:02:53.848 --> 00:02:57.101
and then you take the same car and you
drive it with the second tire.

00:02:57.101 --> 00:03:00.671
Those two samples are related because
it's the same car driving both times.

00:03:00.671 --> 00:03:03.497
If they're dependent samples, 
then you have a choice

00:03:03.497 --> 00:03:06.629
of either finding the differences 
between the two samples

00:03:06.629 --> 00:03:13.678
and doing a one sample t-test, or under
t-stats you can do the paired t-test.

00:03:15.098 --> 00:03:19.676
If you have more than two 
populations, we only have one test

00:03:19.676 --> 00:03:24.242
where we had more than two populations
and that was from chapter 14,

00:03:24.242 --> 00:03:28.966
and that was where we had three, four,
five, six, as many populations

00:03:28.966 --> 00:03:34.192
as were needed, and that was to perform
the one-way ANOVA test.

00:03:34.922 --> 00:03:39.975
Now, if you have two quantitative
variables, like you were collecting

00:03:39.975 --> 00:03:49.089
the height of a person and 
the weight of a person,

00:03:49.089 --> 00:03:56.511
and you were asked to decide if the 
variables were dependent,

00:03:56.511 --> 00:03:59.548
or associated, or independent, if 
you saw those words in there,

00:03:59.548 --> 00:04:03.531
but you have two quantitative 
variables, a height and the weight,

00:04:03.531 --> 00:04:06.914
then that would be a 
regression type problem,

00:04:06.914 --> 00:04:13.099
and you would perform that significance 
test using the test on beta, the slope,

00:04:13.099 --> 00:04:17.847
using the regression simple linear
command in StatCrunch,

00:04:17.847 --> 00:04:20.276
so again that's for two 
quantitative variables,

00:04:20.276 --> 00:04:23.514
and you're going to look for phrases
like "Determine if the variables

00:04:23.514 --> 00:04:25.879
are dependent, or 
associated, or independent"

00:04:26.919 --> 00:04:30.745
Back over here on the qualitative 
side, it's a little bit shorter

00:04:30.745 --> 00:04:36.205
on the qualitative side, but starting out
the same way we did on the quantitative

00:04:36.205 --> 00:04:39.775
side, we need to determine if we 
have one or two populations.

00:04:39.775 --> 00:04:43.957
Again, if you have two populations then
you're going to have information

00:04:43.957 --> 00:04:47.757
for two samples. You're going to be 
given the number of successes

00:04:47.757 --> 00:04:51.224
and the total sample size 
for two different samples.

00:04:51.874 --> 00:04:55.654
If you do determine that 
you have one population,

00:04:55.654 --> 00:04:58.955
then you would do a 
proportion stat one sample.

00:04:59.185 --> 00:05:02.315
If you do determine that you 
have two populations,

00:05:02.315 --> 00:05:04.606
then again you're going 
to do a proportion stat,

00:05:04.606 --> 00:05:06.389
but you're going to do two samples.

00:05:06.389 --> 00:05:11.654
Our last test for qualitative data,
is if we have two variables.

00:05:11.654 --> 00:05:19.487
For examples, we might be looking at
gender and happiness.

00:05:19.487 --> 00:05:25.020
That would be two qualitative variables.
For gender, you would be male or female.

00:05:25.020 --> 00:05:30.936
For happiness, they might indicate very
happy, or happy, and not happy,

00:05:30.936 --> 00:05:34.168
so those are word answers to those.
"How happy are you?"

00:05:34.168 --> 00:05:37.834
Very happy, happy, not happy.

00:05:37.834 --> 00:05:42.153
Those are word answers so those are
definitely qualitative variables,

00:05:42.153 --> 00:05:44.577
and it was two variables. 
We were collecting gender

00:05:44.577 --> 00:05:48.466
and we were collecting level of happiness
so we have two qualitative variables.

00:05:48.466 --> 00:05:52.688
In the problem you can also look to see
if it says the variables are dependent,

00:05:52.688 --> 00:05:54.648
associated, or independent.

00:05:54.648 --> 00:05:58.957
Also note, a little hint here, that when
you do have two qualitative variables,

00:05:58.957 --> 00:06:02.863
it's typically the data will be 
shown in a contingency table,

00:06:02.863 --> 00:06:05.681
so all of these clues here 
help you determine

00:06:05.681 --> 00:06:08.915
that you're going to perform a 
chi-square independence test.

00:06:10.325 --> 00:06:13.763
So this is a little bit about how 
to use this decision tree,

00:06:15.663 --> 00:06:19.547
or significance test flow chart. 
Sometimes I call it a decision tree

00:06:19.547 --> 00:06:21.412
because it branches off,

00:06:21.412 --> 00:06:24.594
or sometimes I just call it a 
significance test flow chart.

00:06:24.594 --> 00:06:28.861
But anyway, this is a little bit about
how to use this document.