statistical testing: the sign test Flashcards
1
Q
what is the purpose of statistical testing?
A
- to determine whether the null / alternate hypothesis should be accepted or rejected
- we can find out whether differences or relationships between variables are significant (meaningful) or are likely to have occurred by chance
2
Q
what is the sign test used for?
A
to analyse the difference in scores between related items
3
Q
what conditions are needed to determine if you need to use a sign test?
A
- looking for difference rather than association
- use a repeated measures design
- need nominal data ie. data that is organised into categories
4
Q
what is probability (p)?
A
- the likelihood that certain events will occur
- the accepted level of probability in psychology is 0.05 (5%)
> this is the level at which a researcher decided that the findings are significant and will reject the null hypothesis
5
Q
when would you use more stringent significance levels?
A
- 0.01 (1%) may be used
- this is the case when research may involve a human cost, such as when new drugs are being trialled
- or when a particular investigation is a one-off and there is no possibility it can be repeated in the future
- in the absence of proof or certainty, psychologists have decided that 5% will generally be sufficient
6
Q
why do psychologists use phrases such as ‘this suggests’ rather than ‘this proves’?
A
- even though researchers may find statistically significant differences / association within data, they can never find statistical certainties
- therefore, ——–
7
Q
what is the critical value?
A
- the calculated value from the sign test needs to be compared with a critical value to decide whether a result is significant or not
- the critical values for a sign test are given in a table of critical values
8
Q
what do you need to look for in a critical value table?
A
- level of significance (generally 0.05)
- number of participants in the investigation (N value or sometimes degrees of freedom, df)
- whether the hypothesis is directional (one-tailed) or non-directional (two-tailed)
9
Q
how to do a sign test
A
- convert data into nominal data by subtracting control value from experimental value and recording the sign of difference
- from the table, add up the pluses and the minuses
- take the less frequent sign and call this S
- compare the calculated value with the critical value
- the calculated value of S must be equal to or less than the critical value at the 0.05 level of significance
10
Q
scaffold conclusion for the sign test
A
- for our investigation, the calculated value of S, x, is more than the critical value of S, x
- therefore, the difference is not statistically significant at the 0.05 level
- we accept the null hypothesis