Section 5: ANALYSING DATA Flashcards
Measure of central tendency
A single summary score that represents a whole set of scores.
- How descriptive stats are summarized
Mode
Most occurring score in a distribution - add up all the scores and tally scores
Bimodal distribution
When there are two frequency occurring scores
Mean
The average within the distribution - all scores added together and then divided by number of.
Median
The middle score in the distribution - write down all the scores starting from the lowest, and find the middle number. If there is an even number of scores the median is the average of the middle two scores.
Regression towards the mean
When variables that are extremely high or low, tend to move closer to the average upon retesting.
- Ex: You achieve a lower than normal test score. You would be tempted to try to establish explanations as to why, and possibly change strategies, however it is important to consider that the same combination that resulted in that low grade won’t happen again, and the next set of results will regress back to your normal grade mean.
Percentile rank
The percentage of scores that are less than a given score. So if for example, you are in the ‘79th percentile’ in a Maths competition, your score is higher than 79 %of your peers.
Range
The gap between the lowest and highest scores, calculated by the largest score minus the
smallest score.
A simplified measure of variation.
Standard deviation
A computed measure of how much scores vary around the mean score. The standard deviation is better because it more accurately gauges whether scores are close together or dispersed as it uses information from each score. The higher the standard deviation, the more spread out the distribution.
Normal Distribution (aka Bell Curve)
0= Middle
+-1 SD= 34.13%
+-2 SD= 13.59%
+-3 SD= 2.14%
Total = 99.72%
Positively Skewed Distribution
Skewed to the left
- The mean is always the highest score
Negatively Skewed Distribution
Skewed to the right
- The mean is always the lowest score
Positive correlation
The presence of one thing predicts the presence of the other i.e. as chocolate consumption increases, happiness levels increase.
Negative correlations
The presence of one thing predicts the absence of the other i.e. as levels of homework increase, levels of happiness decrease.
Scatterplot
The line of best fit (also known as the regression line), is the line drawn on a scatter plot to show the relationship.
- Correlations are represented on a scatterplot
- Visual representation of the relationships or associations between two numerical variables