Chapter 7: Analyzing Data from Independent Groups: Categorical Measures

Categorical or Nominal data

- can only take on one of a limited number of values, often simply yes or no

Mode

- very rarely used as an appropriate measure of central tendency.
- it does not tell much

Summary Statistics

- we usually describe the % of people in each group and the differences between them
- we also get on to the 95% CIs.

Absolute and Relative Change

- three main ways of showing the difference between two proportions. (fourth one as well)

Absolute and Relative Change

- all look very similar to each other and it is often not clear which one people are talking about.

Odds Ratio

- third way of showing the difference two proportions

Odds Ratio

- trickier than percentages and proportions but most common way

Number Needed to treat (NNT)

- one more method of presenting the effect of an intervention which is commonly used in medicine, though less commonly used in psychology.

NNH or number needed to harm.

Number Needed to treat (NNT) is also known as ____

NNT

asks, "How many people do I have to treat with X, rather than Y, in order that I can expect that one person does Z?"

NNH

asks: "How many people have do to something, before we would expect that one of them would come to harm as a result?"

Chi-Square Test

- there is only one way to calculate the probability value given the plethora of ways of displaying the difference between two proportions. (Sort of only one way)

Chi-Square Test

- developed by Pearson and sometimes known as the Pearson χ² test.

E (expected) value

are the values that we would expect if the null hypothesis were true, the null hypothesis in this case being that the task type had no effect.

Fisher's Exact Test

- If the sample size is small, there is a better test we can use ___

Fisher's Exact Test

its idea is that for some events we can work out the exact probability of them occurring without needing to use test statistics and tables

correlation

Pearson is also known for ___

"something to one"

Odds are always presented as _____

liberal test

is slightly more prone to say that a result is statistically significant than it should be, so the Type I Error rate is not 0.05, but a little bit higher than that.

problem with Yates' correction

is that it makes the test a little conservative so the Type I Error rate is now smaller than 0.05.

Fisher's Exact Test

gives the probability of getting the exact result that was found in the study

Fisher's exact test

with this, there is no test statistic, and no need to look anything up in a table