Statistical testing

Question 1

What is statistical testing and and why do researchers use it?

Answer 1

Researchers use statistical tests to determine the likelihood that the difference/relationship found has occurred due to chance. If they are not due to chance the results are significant

Question 2

What are the two types of hypothesis for every study? and what are they?

Answer 2

Alternative and null
Researchers always start with the null hypothesis - which states there will be NO difference/association .
The alternative hypothesis (can be directional/non directional) states there will be a difference/association

Question 3

How do you decide if the hypothesis will be directional or not?

Answer 3

Directional is used when there is a previous researcher
Non - directional is used when there is no previous research

Question 4

What is the sign test?

Answer 4

The sign tests determines whether the difference we have found is significant, we can use a simple statistical calculation called the sign test

Question 5

What are the 3 reasons we select the sign test?

Answer 5

1. The type of data
   Nominal data which is the named categories of data and the number of participants falling into categories
2. The research method
   We are looking for a difference (experiment) rather than an association (correlation)
3. Experimental design
   Repeated measures or matched pairs

Question 6

The concept of probability

Answer 6

All studies employ a significance level on order to check for significance. The accepted level of probability/significance is 0.05 (5%)
This is the level at which a researcher decides that the findings are significant (meaningful)

Question 7

Where do the findings we obtain come from?

Answer 7

A sample of participants

Question 8

When do we accept the alternative hypothesis?

Answer 8

If we find a difference/relationship

Question 9

What does P ≤ 0.05 (less than or equal to) mean?

Answer 9

If the hypothesis is accepted, we are saying that there is a 5% probability that the results are due to chance. This means that there is a 95% probability that the results are significant (they are due to the manipulation of the IV)
Therefore, we can be 95% certain that the data from our investigation is significant and we can infer to the rest of the target population.

Question 9

When do we accept a null hypothesis?

Answer 9

If we don’t find a difference

Question 10

How do we establish significance

Answer 10

1. You will need the N values (this is the number of participants)
2. You will need the significance level (always 0.05 unless you are told otherwise)
3. Whether the test is one tailed or two tailed
4. The critical value ( the value you take from the table)
5. The calculated value

Question 11

What are the steps?

Answer 11

First step: record the data and work out the sign (+ or -)

Second step: Work out the calculated value of S (add up the + and - select the smaller value. This is the calculated value

Third step: Find the N value minus any 0 scores if there are any

Fourth step: Think about whether you used a one-tailed test or a two tailed test (which hypothesis was accepted)

Fifth step: You then identify the probability level (0.05)

Sixth step: Using this you’ll find out the critical value by finding it from the table

Seventh step: Compare the calculated value of S with the critical value of S. The calculated value of S must be equal to or less than the critical value in this table for significance to be shown