Statistical Tests Flashcards
What is a null hypothesis?
A hypothesis that you try to disprove with a statistical test.
What is the observed value?
The value that is calculated from a statistical test.
It is compared with a table of critical values and used to accept or reject the null hypothesis.
How is the degree of freedom calculated?
Number of values minus 1
What is nominal data?
Data which can be categorised.
e.g. gender
What is ordinal data?
Categorised data that can be placed into a rank.
e.g. running times
What is interval data?
Data measured on scales with known intervals.
e.g. temperature
What are the tree statistical tests that can be used?
Spearman’s rank correlation coefficient, Chi-squared test, Student’s t-test
What is the purpose of Spearman’s rank correlation coefficient?
To test whether two ordinal variables display correlation
What is the purpose of Chi-squared test?
To test how likely it is that any differences between observed and expected results are due to chance.
What is the purpose of Student’s t-test?
To test whether the differences in the mean value of the interval variable for the two categories is significant.
There are two types
Unpaired- difference in the means between two independent groups.
Paired- Difference in the mean between the same group before and after a change.
What are the steps of calculating spearman’s rank correlation coefficient?
- State the null hypothesis.
- Make sure the two sets of data are ordinal (ranked).
- Calculate the observed value using the given formula.
- Compare the observed and critical value in the table.
If the observed number (ignoring whether it is positive or negative) is less than the critical value, accept the null hypothesis.
What are the steps of calculating the chi-squared test?
- State the null hypothesis
- Calculate the observed value using the given formula.
- Compare the observed and critical value in the table.
If the observed number is less than the critical number, accept the null hypothesis.
What are the steps of calculating the student’s t-test?
- State the null hypothesis
- Calculate the mean and variance for both of the categories, using the two given formulas.
- Use the given formula to calculate the student’s t-test.
- Compare the observed and critical value in the table.
If the observed number is less than the critical number, accept the null hypothesis.
How do you compare the observed number with the critical number in the table?
- Calculate the degree of freedom (no. of data values or pairs minus 1).
- Find the critical value corresponding the degree of freedom and 5% significance level on the table.
- Compare the observed and critical value.
