Data Analysis: Descriptive statistics Flashcards
explain the ‘mean’ as a measure of central tendency?
-add up all the values and divide by the total amount of numbers of values in set
evaluate the ‘mean’ as a measure of central tendency?
+most sensitive, as it takes into account every value
+most precise
-most likely to be distorted by anomalous scores because it uses all values in data set so may not give representation of the most typical score
explain the ‘medium’ as a measure of central tendency?
- rank all the values in order from smallest to largest
- then count middle value
- if there are two, then find the middle value of the two
evaluate the ‘medium’ as a measure of central tendency?
+not affected by anomalous results, as it looks at middle, unlike mean
-less precise than mean, doesn’t examine all values in data set, only focuses on one
explain the ‘mode’ as a measure of central tendency?
-calculated by identifying most frequently occurring value in data set
evaluate the ‘mode’ as a measure of central tendency?
+most appropriate method to use if we have categorical data
- may have multiple modal values in data set
- may not represent most typical score
rank the best measures of central tendency to use, and how to remember?
mean (me first)
median
mode (mo last)
explain ‘range’ as a measure of dispersion?
-subtracts the lowest data score from the highest
evaluate the ‘range’ as a measure of dispersion?
+less sensitive measure compared to standard deviation as it considers all values
+easy to calculate
-range only takes into account the most extreme values
explain ‘standard deviation’ as a measure of dispersion?
- single value that says how far scores have deviated from the mean
- the larger the deviation the greater the dispersion, further from mean =bad
- closer deviation= better (closer to the mean and less range)
name the measures of dispersion
- range
- standard deviation
name the descriptive statistics?
- mean
- median
- mode
evaluate ‘standard deviation’ as a measure of dispersion?
+very precise
+includes all values within final conclusion unlike the range
-but can distorted by an anomalous value like the mean