Data Analysis
Data types
Qualitative data
= data expressed w/ words
Non-numerical
Quantitaive
= data that can be counted
Numerical
Primary data
= info that has been directly obtained first hand
Often gained directly from the ptps
As part of the experiment, self report or observation
Secondary data
Info that has been collected by s/one else
May include the work of other psychologists or government statistics
Descriptive statistics
Can be calculated from quantitative data
Describe and summarise a set of data
Two types
Central tendency
Essentially averages
Mode
Median
Mean
Measures of dispersion
Essentially the spread of data
Range
Standard deviation (s.d.)
Strengths
Likely to be most representative
Weaknesses
Harder to calculate than other measures
Cannot be used on nominal data
Can be affected by extreme scores
Strengths
V easy to calculate
Strengths
Unaffected by extremes
Easier to calculate than mean
Weaknesses
Less representative than mean
As it does not use all the scores
as all scores used
Unaffected by extreme values
Weaknesses
Data is often multi-modal
So meaningless
Does not use all scores
Tells you the spread of data around the mean
See the relationships between scores
Strengths
It shows the overall spread of the whole dataset
Easy to calculate
Weaknesses
May not be representative of the data
If there are extreme values at the top/bottom of the dataset
Strengths
Provides a representative measure of data spread
Takes all values into account
Provides useful info about how individual scores relate to each other and to the mean
It gives a measure of the reliability if data
As small standard deviations mean there was little variation in the scores
Weaknesses
Harder to calculate than the range
A distribution curve can show standard deviation
Normal distribution
Mean, median and mode will be at the same point
The data is symmetrical about the mean
The shape of the line on the graph is bell shaped
Bell-shaped curve
68% of the data will fall evenly one standard deviation above and below the mean
95% within 2 standard deviations
99.7% within 3 s.d
Skewed distributions
Non-symmetrical
Scores are not evenly distributed on either side of the mean
Common when only a few measures have been taken
Positive skew
Peaks to the left
Negative skew
Peaks to the right
Caused by a difficult task
But a handful do well
Mode is where the peak is
Most ppl perform badly
Mode<median<mean
Mode is where the peak is
Most ppl perform well
Caused by an easy task
But a handful do badly
Mode>median>mean