00:00
00:54
12:15
Crash Course: Statistics
Null Hypotheses Explained
00:54 - 02:20
Explains what null hypotheses are.
Sign up to access lesson features such as sample questions, standards alignment, and discussion tools to check for understanding.
Comments
Please sign in to write a comment.
Video Transcript
0:52
come from the null distribution.
0:54
Null means nothing so null hypotheses tend to say that there’s no effect, or nothing’s
0:58
going on.
0:59
For example, for whether babies who drink non-dairy milk are more likely to have allergies,
1:04
the null hypothesis (or H0) would be that there is no difference in proportion of babies
1:09
with allergies between babies who drink non-dairy milk, and those who do not.
1:14
In the case of home makeover shows, the null hypothesis might be that there’s no relationship.
1:19
So the regression slope--or coefficient--between number of home makeover shows watched and
1:24
age would be 0:
1:26
By looking at this slope, we can see it’s not exactly flat, but we don’t know whether
1:29
this slope is due to a real relationship, or just random variation.
1:33
When we get low p-values, we “reject” the null hypothesis because we’ve decided
1:38
that our data would be pretty rare if the null was true since the probability of getting
1:42
data as or more extreme than ours is below our alpha level.
1:47
That’s option 1.
1:48
Option 2 is that our p-value is not lower than our pre-selected cutoff which means that
1:54
we “fail to reject” the null hypothesis.
1:56
So, we’ve narrowed it down to two decisions: we can either reject, or fail to reject the null.
2:01
The null can either be true, or not true.
2:03
This means that there are four possible situations: either you correctly reject the null, mistakenly
2:10
reject the null, correctly fail to reject the null, or mistakenly fail to reject the null.
2:15
In two of these situations we make the correct decisions, and in the other two, we’d have
2:19
made an error.
