Research Methods - Parametric Diffrence Tests Flashcards
Compared to other tests parametric tests are ——
More powerful and robust than other tests
Are parametric tests able to detect significance within some data sets that non parametric tests cannot
Yes
What three specific criteria must be met for a parametric test to be used
Data must be interval level
Parametric tests use actual scores than ranked data
Population must show normal distribution for the variable being measured - large sample is needed
There must be homogeneity of variance
Set of scores in each condition in each condition must have a similar dispersion - standard deviation to check this (standard deviations should be similar)
When do we select unrelated t-test
Looking at the difference between two different groups
Unrelated design
Level of measure required is interval data
What two things do you need to interpret unrelated t test
Value of t used from the statistical test
Critical value of t from the table
How do we find the critical value of t in an unrelated t test
DF = NA + NB- 2
Number of participants in group A + number of participants in group B - 2
The significance value is needed
Identify if it is a one tailed or two tailed test
When are the results significant in an unrelated t test
If calculated value of t is more than Or equal to critical value of t
How do we write out the results from unrelated t test
‘As the calculated value of t (____) is more than or equal to critical value of t (____) (df= ____ p ≤ 0.05) the result is significant and we must reject the null hypothesis. There is a difference between ______ and ________.’
• ‘As the calculated value of t (____) is less than the critical value of t (____) (df= ____ p ≤ 0.05) the result is not significant and we must accept the null hypothesis. There is no difference between ______ and ________.’
When do we select a related t test
When Looking at the difference between two different groups
Repeated measures or matched pairs ( related )
Level of measurement is interval data
Data should be normally distributed - means large sample used
Should be homogeneity variance
How do you find the critical value of for a related t test
Identify significance level you are testing
Knowledge of whether it is one or two tailed test
DF= N-1 ( Number of data sets minus 1)
When do the results of a related t test show that results a re significant
When the calculated value of t is more than or equal to the critical value of t we reject the null hypothesis and conclude there is a difference.
How do write out the results for a related t test
As the calculated value of t (____) is more than or equal to critical value of t (____) (df= ____ p ≤ 0.05) the result is significant and we must reject the null hypothesis. There is a difference between ______ and ________.’
• ‘As the calculated value of t (____) is less than the critical value of t (____) (df= ____ p ≤ 0.05) the result is not significant and we must accept the null hypothesis. There is no difference between ______ and ________.’
