Experiments and Statistics Flashcards
What are the 4 stages of experiments?
- Formulate some research hypotheses
- Translate hypotheses into treatment conditions
- Administer treatments to participants
- Measure performance on a response measure
What are the 3 types of IV?
- Quantitative variables
- Qualitative variables
- Classification variable
What is a nuisance variable?
Potential IVs which, if left uncontrolled, could have a systematic influence on the different treatment conditions.
What is a nuisance variable?
Potential IVs which, if left uncontrolled, could have a systematic influence on the different treatment conditions.
What is a completely randomised design? What is this also known as?
Each subject is randomly allocated to one of the treatment conditions. This is also known as a between-subjects design.
What is a randomised block design?
Randomised block designs use blocks of subjects who are matched closely on some relevant characteristics.
What is a repeated measures/within-subjects design?
When participants experience all the treatment conditions.
What is a research hypothesis?
A fairly general statement about the presumed nature of the world that inspires a specific experiment.
What is a statistical hypothesis?
A precise statement about the parameters of distributions for different treatment populations.
What are treatment parameters?
The parameters of the distribution for each treatment population (the mean µ and standard deviation σ), assuming a normal distribution.
What are treatment parameters?
The parameters of the distribution for each treatment population (the mean µ and standard deviation σ), assuming a normal distribution.
What is the null hypothesis?
A classic statistical test seeks to test (accept or reject) the null hypothesis.
It can be expressed as an equation expressing equality between the different treatment populations.
This is the same as saying that no treatment effects are present in the population.
What is the alternative hypothesis?
If the treatment parameters do not satisfy the null hypothesis, we reject the null hypothesis in favour of its inverse, the alternative hypothesis (𝐻1 or 𝐻𝐴).
Usually 𝐻1 simply states that the parameters are not all equal between treatment populations.
What is the F-distribution?
The F-value is the test statistic.
Suppose we drew a large number of samples at random from a population, and assigned people randomly to groups.
In such a situation, we know 𝐻0 is true, because there is no treatment difference between groups.
The random variation between these groups, across all these samples, can be modelled as an F-distribution
What is the p-value?
The probability of finding this F-value, given that the null hypothesis is true, by comparing it to the F-distribution.
