7. RESEARCH METHODS (Statistical testing) Flashcards
What is the purpose of a statistical test in research?
A statistical test is used to calculate a value (called the calculated or observed value) to determine which hypothesis to accept, by comparing it to the critical value.
What happens if the results of a statistical test are significant?
If the results are significant, the null hypothesis is rejected and the alternative hypothesis is accepted.
What happens if the results of a statistical test are not significant?
If the results are not significant, the null hypothesis is accepted, and the alternative hypothesis is rejected.
How do you decide which statistical test to use?
You need to consider:
1. Whether the study is investigating a difference or an association.
2. The type of experimental design used.
3. The type of data generated (nominal, ordinal, interval).
4. If the data is interval, whether it meets the criteria for a parametric test.
What are the two types of statistical tests based on research design?
- Tests of Difference (used for experiments): e.g., Wilcoxon, Mann-Whitney, Related t-test, Unrelated t-test, Sign test.
- Tests of Association (used for correlations): e.g., Spearman’s Rho, Chi², Pearson’s r.
What is nominal data?
Nominal data is categorical, where participants are counted in distinct categories. For example, classifying participants based on whether they improved, showed no change, or got worse.
What is ordinal data?
Ordinal data is ranked data where the order matters, but the distances between ranks are not equal. Example: rating how attractive a face is on a scale from 1 to 10.
What is interval data?
Interval data is numerical data with equal and measurable intervals, where the distance between values is consistent, such as temperature or IQ scores
What are the criteria for using a parametric test?
Parametric tests are used when:
* Data is interval.
* The data is drawn from a normally distributed population.
* The variances of the two samples being compared are equal.
Why is the 5% level of significance commonly used in psychology research?
The 5% level strikes a balance between the risk of making Type I and Type II errors, giving researchers a 95% confidence level that the results are not due to chance.
What is the definition of probability in statistical testing?
Probability is the likelihood that an event will occur, ranging from 0 (impossible) to 1 (certain).
What is significance in statistical testing?
Significance refers to how confident the researcher can be that the observed effect is not due to chance. A significant result allows the rejection of the null hypothesis.
What are Type I and Type II errors?
- Type I Error: Rejecting the null hypothesis when it is true (false positive).
- Type II Error: Failing to reject the null hypothesis when it is false (false negative).
What is the usual significance level used in psychological research?
The standard significance level is p < 0.05, meaning there is less than a 5% probability that the results occurred by chance.
Why might a researcher choose a more stringent significance level of 0.01?
A researcher might use p < 0.01 when more accuracy is needed, such as in highly controversial or important research where errors could have serious consequences (e.g., drug safety).