statistical testing Flashcards
define statistical testing
- provides a way of determining whether hypotheses should be accepted or rejected
- they tell us whether differences or relationships between variables are statically significant OR have occurred by chance
why do we need to complete a statistical test ?
to see whether the difference found within studies haven’t occurred by chance/coincidence
define sign test
a statistical test used to analyse the difference in scores between related items
what is an example of ‘related items’ ?
the same participant tested twice
what are the 2 types of hypotheses ?
- the original/alternate hypothesis
- the null hypothesis
what is the difference between original and null hypothesis ?
O - states there will be an effect
N - states there will not be an effect
give an example of original hypothesis
there will be a difference in participants depression score on the BDI before and after a 6-week course of CBT
give an example of null hypothesis
there will be no difference in participants depression score on the BDI before and after a 6-week course of CBT
what are the abbreviated form of original and null hypothesis ?
H1 - O
H0 - N
what does the statistical test allow to decide between original and null hypothesis ?
to determine whether to accept or reject the null hypothesis
what is the sign test used for ?
used to find out whether the difference established is significant
what conditions need to be met in order to carry out the sign test ?
- looking for a difference rather than an association
- have used a repeated measures design
- nominal data.
what are significance levels used for ?
to check for significance differences or relationships
what is the accepted level of probability in psychology ?
0.05 / 5%
define significance levels
represents the threshold at which researchers decide whether to reject the null hypothesis
what does it mean if the experimental hypothesis is accepted ?
this means there is less than 5%
probability that the results occurred by chance
what do some researchers do to the significance level and why ?
-make a stringent (small) signifance level (0.01/1%)
- means that researchers can be more confident in their results
- to make sure that results weren’t due to a chance
give examples of why one may want to employ 1% level of significance
- may involve a human cost (new drugs are being on trial )
- when a particular investigation is a one-off , and there is no possibility that it can be repeated in the future
what can choosing the wrong significance levels result in ?
type 1 error + type 2 error
define type 1 error
if too lenient significance level is used
(e.g. 10% )
–> results rejecting the null hypothesis that is fact true
null hyp = true
alt hyp = wrong
define type 2 error
if a too stringent significance level is used
(e.g. 1%)
–> results in accepting a false null hypothesis
null hyp = wrong
alt hyp = true
what does one -tailed and two-tailed mean ?
one-tailed means directional hypothesis
two-tailed means non-directional hypothesis
what are 5 pieces of information one needs in order to reading a table of critical values
- the significance level desired (always 0.05 or 5% except in the cases described
above). - the number of participants in the investigation (the N value),
- whether the hypothesis is directional (one-tailed) or non-directional (two-tailed)
- the calculated value
- the critical value
what does test of difference/correlation mean ?
association or relationship = correlation
what are the test designs ?
unrelated - independent groups
related - matched pairs or repeated measures
define matched pairs
pairing up participants who are similar in important ways
define repeated measures
all participants take part in all
conditions of the experiment
define independent groups
- participants allocated to different groups where each group represents one experimental condition
what does levels of measurements mean ?
quantitative data that can be classified into different levels of measurement
what are the types of levels of measurement ?
- nominal
- ordinal
- interval
define what nominal data means ?
- categorical data
e.g - favourite dessert , smoker/non-smoker and sex - discrete data –> only appears in 1 category
define what ordinal data means ?
- data that can be ordered in some way
e.g. rating scales - subjective + no equal intervals between values
define what interval data means ?
- data based on numerical scales
e.g. weight, size , scores , speed - objective
-equal intervals between values - most sophisticated form
draw out the choosing test table
find in notes :)
what is the way of remembering the 8 tests we need to use ?
Carrots - Chi 2
Should - Sign test
Come - Chi 2
Mashed - Mann-Whitney
With - Wilcoxon
Swede - Spearman’s rho
Under - Unrelated t-test
Roast - Related t-test
Potatoes - Pearson’s r