S 519 Evaluation of Information Systems Social Statistics
- Slides: 10
S 519: Evaluation of Information Systems Social Statistics Ch 4: Chart
Chart l Label everything One graph communicate one idea Keep things balanced Simple is best l A picture is worth a thousand words l l l
Frequency distribution l Frequency distribution is a method to represent the frequency of certain scores. l When you have a data set, such as a testing scores, l Class intervals l l Number of intervals: 5, 10, 20 Value of interval=range/number of intervals
Exercise Score l 50 scores l l l Set class intervals Create a histogram using your hand Using Excel to do that 47 2 44 41 7 6 35 38 35 36 10 11 14 14 30 30 32 33 34 32 31 31 15 16 17 16 15 19 18 16 25 25 26 26 27 29 29 28 29 27 20 21 21 21 24 24 23 20 21 20
A histogram
Excel for Histogram First, define your bins l l The starting point of a bin Data analysis Toolpak histogram 12 120. 00% Histogram 10 Frequency l 100. 00% 8 80. 00% 6 60. 00% Frequency 4 Cumulative % 40. 00% 2 20. 00% 0 0. 00% 24 29 19 34 14 39 Bin 9 44 4 49 More
Skewness l Skewness (S-p 98 -Fig 4. 15) l l l Measure of the lack of symmetry of a distribution mean>median>mode positively skewed mean<median<mode negatively skewed
Kurtosis l Kurtosis (S-p 99 -Fig 4. 16) l flat or peaked of a distribution
Variability l Variability (S-p 97 -Fig 4. 14)
Frequency distribution l Excel: SKEW() and KURT() l l l As a general rule, we will conclude that the distribution is significantly skewed or kurtotic if the statistic is greater than three times its standard error. For example, your rule to determine if the distribution is actually skewed (to confirm your visual impression) is: IF skew > ± 3 * SE_Skewness THEN it is skewed. SPSS can do this