Inferential Statistical Tests
- Created by: Iggle Piggle
- Created on: 14-03-17 09:58
View mindmap
- Inferential Statistical Tests
- Sign Test
- Nominal Data
- Not Frequency Data
- Methods
- 1. State the alternative and null hypothesis.
- This is a non-directional hypothesis therefore requires a two tailed test.
- 2. Record data and work out the "sign".
- The "sign" is wether it is a + or - depending on wether the results are the same or diffrent
- 3. Find the observed value of "S"
- S= the number of times the less frequent value occurs
- 5. State the conclusion.
- If the observed value is smaller than the critical value we must accept the alternative hypothesis, and reject the null hypothesis.
- 1. State the alternative and null hypothesis.
- Chi Square Test
- Nominal Data (The level of data when they are in separate categories. Can includes numbers)
- Frequency Data (occurrences in each category)
- Example study:
- Method:
- 2. Draw up a contingency table. Include totals around it.
- Example of a contingency table
- 1. State the null and alternative non-directional hypothesis.
- The alternative hypothesis is non directional, requiring a two tailed test.
- 3. Compare the observed and expected frequencies (calculated by multiplying two totals, and diving that by the overall total)
- 4.Find the observed value
- 5. Add the critical value
- 6. State the conclusion
- If the observed value is more than the critical value, we accept the alternative hypothesis
- 2. Draw up a contingency table. Include totals around it.
- Spearman's Rho Test
- Correlation
- Used to determine the correlation between two co-variables is significant or not.
- Not nominal data
- Method:
- 2. Record and Rank the data.
- 1. State the alternative and null hypothesis.
- Null hypothesis (There will be no correlation) VS Alternative directional hypothesis. This makes Spearman's Rho a one tailed test.
- 3. Calculate the rank difference.
- 4.Find the observed value: rho=1-(6?d²/ N(N² -1) )
- 5. State the conclusion
- If the observed value is greater than the critical value. It appears that you reject the null hypothesis.
- However, if the sign is in the wrong direction (e.g. negative), and does not support the alternative hypothesis, the null hypothesis is accepted.
- If the observed value is greater than the critical value. It appears that you reject the null hypothesis.
- Pairs of scores: Repeated Measures
- Correlation
- Mann Whitney U Test
- Not Nominal Data
- Not correlational
- Independent Groups
- Method
- 3. Find the observed value of U.
- U=(n_1×n_2 )+((n_1×(n_1+1))/2- T-1
- 2. Record the data in a table and find the mean of each condition.
- 4.Find the critical value of U.
- 1. State the alternative hypothesis and null hypothesis.
- The alternative hypothesis is a directional hypothesis therefore requires a one tailed test.
- 5. State the conclusion.
- When
p?0.05 for a one tailed test the critical value is (U) and the observed value is (_) therefore the data is significant. This means that we must (reject/accept) the null hypothesis and (accept/reject) the alternate hypothesis.
- If the observed value is smaller than the critical value we must accept the alternate hypothesis.
- When
p?0.05 for a one tailed test the critical value is (U) and the observed value is (_) therefore the data is significant. This means that we must (reject/accept) the null hypothesis and (accept/reject) the alternate hypothesis.
- 3.Then rank both conditions (all together) from lowest to highest
- 4. Add up all the ranks. (n1= the number of numbers)
- 3. Find the observed value of U.
- Ordinal Data
- Directional Hypothesis
- Wilcoxon T Test
- Not Nominal Data
- Not correlation
- Not Independent group
- Method
- 3. Rank
- 2. Record, and calculate diffrence
- 4. Find the observed valye of T
- T = the sum of the ranks of the less frequent sign.
- 1. State the alternative and null hypotheses
- Directional. Requires one tailed test.
- 5. Find the critical value of T
- N=sum of participants - omit results. Look up the critical value in the table
- 6. State the conclusion
- If the observed value is smaller than the critical value, we must accept the alternate hypothesis
- Directional Hypothesis
- At least Ordinal Data
- Sign Test
Comments
No comments have yet been made