Statistical Tests, Probability, Significance Flashcards
Why do we use statistical testing?
To determine whether differences between variables are statistically significant or occurred by chance.
What is the difference between a one-tailed and two-tailed test?
One-tailed test = directional hypothesis
Two-tailed test = non-directional hypothesis.
What is the sign test?
A statistical test used to analyse the difference in scores between related items.
What are 3 conditions for using a sign test?
- Need to be looking for a difference. 2. Use a repeated measures design. 3. Nominal data.
What is probability?
The likelihood that the data obtained is due to chance rather that the manipulation of the IV
What is the accepted level of probability in Psychology?
0.05.
What does it mean if the researcher accepts alternative
the hypothesis?
There is less than 5% probability that the results occurred by chance.
Why might a researcher adopt a significance level of 0.01?
When researchers need to be more confident that results were not due to chance. For example, where there is a human cost (drug trials) or results are theoretically very important
Which 3 pieces of information do you need to locate the critical value?
- The significance level desired
- The number of participants
- Whether the hypothesis is directional or non-directional.
Why can psychologists never be 100% certain about their results?
They have not tested all members of the population under all possible arrangements.
What are the 3 levels of measurement?
- Nominal 2. Ordinal 3. Interval.
What is nominal data?
Named, distinct categories (sex, gender, eye colour)
What is ordinal data?
The order of the data matters, but the actual value isn’t measurable (aggression, test scores)
What is interval data?
Measured along a scale where the distance between one value and the next is equal. Standardised. (Temperature)
Which two experimental designs are known as related?
Repeated measures and matched pairs design.
Choosing a statistical test mnemonic
Chairs Save Children
Meanwhile Waiting Standing risks
Uncomfortability Right Peter
Choosing a statistical test
Chi squared, Sign Test, Chi squared
Mann-Whitney, Wilcoxon, Spearmans rho
Unrelated t test, Related t test, Pearsons r
What is a parametric test?
A group of inferential statistics that make certain assumptions about the parameters (characteristics) of the population from which the sample is drawn
Explain how the researcher would determine whether the results of the statistical test are significant.
- The researcher would compare the calculated value (test statistic) to the critical value in a statistical table
- The N value (sample size) and chosen significance level (typically p ≤ 0.05) would be used to find the critical value
- If the calculated value is equal to or greater than the critical value, the result is statistically significant, meaning the null hypothesis can be rejected (1 mark)
What is the difference between the null and alternative hypothesis?
The null hypothesis states there will be ‘no difference’ between the conditions, whereas the alternative hypothesis states there will be a difference (either directional or non-directional)
What is the purpose of a statistical test?
To determine which hypothesis is ‘true’ and thus whether we accept or reject the null hypothesis
What is a Type I error?
Too lenient. Wrongly rejecting the null hypothesis (also known as a ‘false positive’, finding it significant when it wasn’t).
What is a Type II error?
Too strict wrongly accepting the null hypothesis (known as ‘false negative’, finding it not significant when it was)
When are researchers most likely to make type 1/ type 2 errors
Type 1 - when the significance level is too lenient (0.1)
Type 2 - when the significance level is too strict
What is significance?
The researcher can state that the relationship between the variable is more than just chance.