- Created by: Alejandra García
- Created on: 24-05-11 10:51
Chi squared test
- Use when the measurements relate to sample size in different categories.
- Produce a null hypothesis: There's no difference between the expected and observed results."
- Calculate the value of chi and look at the tables.
- The degrees of freedom are one less than the number of categories.
- If the value of chi is greater than the critical value we reject the null hypothesis and say there IS a significant difference between the observed and expected.
1 of 4
Spearman's rank correlation
- Null hypothesis: there's no association between the two variables.
- Calculate the Rs.
- Look up on table the number of measurements and the critical values for each one
- If your Rs is greater than the critical value you reject the null hypothesis.
2 of 4
- To find if there's difference between two means.
- Null hypothesis: no difference between the no. of seeds in the dark than the ones at the sun.
- Calculate standard error.
- 95% confidence are 1.96+ mean and mean-1.96.
- If these values don't overlap, there's a significant difference between the 2 variables. (Plot a whisker!!)
- If they overlap we accept the null hypothesis.
3 of 4
- Significant difference between two means.
- Null hypothesis: There's no difference between the two variables.
- Calculate t.
- Degrees of freedom are both sample sizes -2.
- Look up the degrees and critical values.
- If t greater than critical, the null hypothesis is rejected.
4 of 4