Inferential Statistic - Methods

notes on inferential statistics with methods

a2 psychology with aqa

HideShow resource information
  • Created by: Cara
  • Created on: 29-06-12 13:42
Preview of Inferential Statistic - Methods

First 256 words of the document:

Inferential Statistic
Inferential statistics describe a range of statistical tests designed to analyse sets of data to measure
if there actually is a significant difference (or correlation) between them
This is where the use of the terms `significant' and `chance factors' comes into the wording of
We can use inferential statistics on experimental, non-experimental and correlational research
In science, probability in linked to hypothesis testing
It is the chance (or likelihood) of an observed effect (difference or correlation) being due to
chance factors
This can be expressed on a scale of 0 to 1 or as a percentage
100% or p = 1 ­ always happens
0% or p = 0 ­ never happens
The mean, median, mode, range and standard deviation are all descriptive statistics
Small relationships are detectable between any data sets, however:
They may be caused by chance
They may be caused by something else
Statistical tests help psychologists decide for any given sets of data which of these possibilities is
more likely
Statistical analysis
If we find that it is highly probable that the relationship was caused by chance, then we
assume it was caused by chance ­ i.e. we accept the null hypothesis
If we find that it is highly improbable that the relationship was caused by chance, then we
assume it was caused by something else ­ i.e. we reject the null hypothesis
This is where probability and significance levels come in.

Other pages in this set

Page 2

Preview of page 2

Here's a taster:

Once the raw data of an experiment is obtained:
1. Depending on the design of the research and level of data, the psychologist will select a
suitable statistical test
2. This will provide an observed value
3. The psychologist then compares this value with something called a critical value from a
statistical table
4. It is also necessary for the psychologist to know the size of their sample and the minimum
acceptable probability level
5.…read more

Page 3

Preview of page 3

Here's a taster:

Situations where we reject the null hypothesis when results did occur by chance, e.g. the
`error of optimists'
Often occurs when the research has a poor design, small sample or poor control of
confounding variables
Type 2 error:
Situations where we reject the alternative hypothesis when there was a significant effect,
e.g. the `error of pessimists'
Often occurs when a more stringent significance level is chosen e.g. 0.01 rather than 0.…read more


No comments have yet been made

Similar Psychology resources:

See all Psychology resources »See all resources »