Descriptive Stats - summarize/describe numerical data
Measures all the subjects and summary data is certain
Inferential Stats - numerical data that allows one to generalize; estimates based on sample data
Low variable observations are more reliable than those that are more variable
Correlation Data
The pattern of dots on a scatterplot allows one to determine if a relationship exists between two variables
Correlation coefficient - a numerical measure of the strength of two variables; falls somewhere between -1 and 1, with 0 being No Correlation
A larger sample size helps to ensure that the observed effect did not occur simply due to a sampling a error
Replicated data also ensures results are accurate (not a fluke)
Measures of Central Tendency
Mean - the arithmetic average (sum total of all scores divided by the number of scores)
Median - the midpoint/halfway point in a date set (50th percentile)
Note: Remember that on a highway, the median is the middle… half way below it
Mode - the most frequently occurring score or scores in a data set
Skewed - a representation of scores that is lopsided due to a few way-out scores
Regression toward the mean - As more data is collected, the chance that random factors could influence the data is reduced
Measures of Variation
Range - the difference between the lowest and highest scores in a distribution
Standard deviation - the amount of variation in relation to the mean score
Normal Curve - bell-shaped curve that represents a normal distribution of scores