Hypotheses

Lesson 16/26 | Study Time: 0 Min

  Hypotheses

A hypothesis is “an idea that can be tested”

It is a supposition or proposed
explanation made on the basis of
limited evidence as a starting point
for further investigation


                                                                Null hypothesis (H0)

The null hypothesis is the hypothesis to be tested.

 

It is the status-quo. Everything which was believed until now that we are contesting with our
test.

   The concept of the null is similar to: innocent
until proven guilty.
We assume innocence until we have
enough evidence to prove that         a  suspect is guilty

                                                               Alternative hypothesis (H1 or HA)

The alternative hypothesis is the change or innovation that is contesting the
status-quo.

 

Usually the alternative is our own opinion. The idea is the following:

 

If the null is the status-quo (i.e., what is generally believed), then the act of
performing
a test, shows we have
doubts about the truthfulness of
 
the null. More often than not the researcher’s opinion is contained in the alternative hypothesis



 Null hypothesis 


After a discussion in
the Q&A, we have
decided to
include further clarifications regarding the null and alternative hypotheses 
Now note that the statement in the
question is NOT true.



    Instructor’s answer (with some adjustments)



 



‘I see why you would ask this question, as I asked the same one right
after 
I was introduced to hypothesis
testing.
In statistics, the null hypothesis is the statement we
are trying to reject.
Think of it as
the
‘status-quo’. The alternative, therefore,
is the change or innovation.



 

Example 1: So, for the data scientist
salary example, the null would be: the mean data scientist salary is
$113,000. Then we will
try to reject the
null with a statistical test. So, usually, your personal opinion
(e.g. data scientists don’t earn exactly
that much) is the alternative hypothesis.

 Example 2: Our friend
Paul told us that the mean salary is >=$125,000 (status-
quo, null). Our opinion is that
he may be wrong, so we are testing
that. Therefore, the alternative is: the mean
data scientist salary is lower than $125,000.
It is truly
counter-intuitive in the beginning, but later on, when start doing the
exercises,
you will understand the
mechanics.’