Stats tests Flashcards
What are the uses for a Spearman’s rank coefficient test
To determine if there is a significant correlation between 2 continuous variables.
What is the null hypothesis of a spearman’s rank coefficient test
There is no significant correlation between x and y.
What are the degrees of freedom in a spearman’s rank coefficient test
The number of pairs of data
How do you interpret the calculated value against the critical value in a spearman’s rank coefficient test
- If the calculated value < critical value at p=0.05 (5%) then there is NO significant correlation between x and y, so ACCEPT null hypothesis
- If the calculated value is > or equal to the critical value at p=0.05 (5%) then there IS a significant correlation between x and y, so REJECT null hypothesis
What are the reasons for using a Chi squared test
To determine if there is a significant difference between the observed and expected numbers in categories x and y.
What is the null hypothesis for a Chi squared test
There is no significant difference between the observed and expected numbers for x and y.
How do you find the degrees of freedom for a Chi squared test
Number of categories -1 (e.g. if there were 7 categories, the degrees of freedom would be 6).
How do you interpret the calculated value against the critical value in a Chi squared test
- If the calculated value is < critical value at p=0.05 (5%), there is NO significant difference so ACCEPT null hypothesis
- If calculated value is > critical value at p=0.05 (5%), there IS a significant difference so REJECT null hypothesis
What are the reasons for using a student t test
To determine of there is a significant difference between the means of two or more datasets.
What is the null hypothesis of a student t test
There is no significant difference between the mean (number of)… and …
How do you find the degrees of freedom for a student t test
number of values in dataset one + number of values in dataset two - number of means
How do you interpret the calculated value against the critical value in a student t test
- If calculated value is < critical value at p=0.05 (5%), there is NO significant difference between means so ACCEPT null hypothesis
- If calculated value is > critical value at p=0.05 (5%), there IS a significant difference between the means so REJECT the null hypothesis
Why do you reject the null hypothesis if the calculated value is less than the critical value
- if the calculated value is less than the critical value, it shows that there is a greater than 5% probability that the differences/correlation in data is due to random chance
- This implies that there is some correlation/difference
- This means you can reject the null hypothesis as the null hypothesis states there is no relationship/difference
Why do you reject the null hypothesis if the calculated value is greater than the critical value
- If the calculated value is greater than the critical value, it shows that there is a less than 5% probability that the differences/correlation is due to random chance
- This implies that the difference/correlation in the dataset is most likely completely random
- This means you can accept the null hypothesis as the null hypothesis states that there is no relationship/difference