statistical testing

notes on spearmans rank, Mann Whitney U test and Chi squared test and their advantages and disadvantages

HideShow resource information
Preview of statistical testing

First 276 words of the document:

Geographical skills theory
Statistical testing
These tell you if there is a difference or correlation between 2 sets of data as
well as saying the degree of the difference or correlation.
Mann Whitney U test
Tests the difference between medians of 2 sets of data and can be used when the
data is in an awkward form such as with samples of very different sizes.
- Shows the median between 2 sets of data
- Good at dealing with skewed data
- You can decide the boundaries of 2 groups
- More appropriate when the data sets are independent from each
- More appropriate when both sets of data have the same shape
- Have to have equal sample sizes
Spearman's rank
Used when both sets of data can be easily ranked, when a quick and easy measure
of correlation is needed and where exact values may be uncertain. It indicates if
2 sets are related. To be significant the end value must be at or above 95%
significance level.
- Shows the significance of the data
- Proves/disproves correlations
- Allows for further analysis
- Can be difficult to work out
- Quite a complicated formula
- Can be misinterpreted
Chi squared test
Used when data is in categories or when it can be grouped into categories i.e. when
it is nominal. It tests the difference between the observed pattern and the
expected pattern from chance events.

Other pages in this set

Page 2

Preview of page 2

Here's a taster:

Geographical skills theory
- Can test associations between variables
- Identifies differences between observed and expected variables
- Can't use percentages
- Data must be numerical
- Categories of 2 are not good to compare
- The observations must be 20+
- Quite complicated to get right due to difficult formula…read more


No comments have yet been made

Similar Geography resources:

See all Geography resources »See all resources »