Data Analysis Flashcards
What is normal distribution ?
- where most scores cluster around the mean with an equal number of scores above and below the mean
- perfectly symmetrical
- central tendency are exactly at its peak
What is skewed distribution ?
- scores are not distributed equally = has long tail on one side than the other
Negative and positive skew
- negative skew= long tail on left side (- side of the peak )
- positive skew= long tail on right side ( + side of the peak )
What is central tendency ?
- is a measure of summary statistics, use to describe a set of data by identifying central value to represent the whole = mean mode median
Evaluation of mean
+ all values in data set are included = always 0 deviation
- can be affected by extreme scores = lead to misleading description with a heavily skewed distribution
Evaluation of mode
+ good at finding average of categorical data
- less good for continuous data since less likely to have another person has the exact same score
Evaluation of median
+ not affected by outliners = better indication of typical situation
- time consuming
What is dispersion ?
- how spread out data is around the measures of central tendency
- large dispersion = inconsistent = behave differently
- small dispersion = consistent = behave similarly
Ways of measuring dispersion
- range
- standard deviation
Evaluation of range
+ useful as a rough guide to the variability shown by the data = shows comparison
- only gives limited amount of info as data set are skewed