Descriptives

  • 5 number summary
  • Center of the data effects of extreme values
  • spread of the data
  • Shape of the data
  • Categorical variables
  • Visualizing categorical & continues data

Making sense of our data

  • Analyze → descriptives → options
  • click on mean, min, max

Looking beyond the Mean

  • Examine the Minimum & Maximum values
  • Let's recode the missing values

Another way to examine descriptive data

  • Let's ask for M, Med, Min, Max,

  • Don't forget to ask for quartiles too!

  • In this function we have more options to select from

5 number summary

  • Here we can extract a 5 number summary of our data
  • Min 1st Q. Mean 3rd Q Max
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   14.09   30.55   36.99   38.84   43.78  124.40    1292

Q = quartile in between 1st and 3rd contain 50% of the responses. This information helps us summarize our data in terms of the average.

Interpret each statistic:

Visualizing the 5 number summary

  • Scatterplot

  • Histogram

  • Barplot

Center of the data effects of extreme values

  • IQR =
  • lower innerfence =
  • Upper innerfence =

Center of the data effects of extreme values

  • IQR = 3rdQ – 1stQ = 13.23
  • lower innerfence = 1st Q - (1.5 * IQR) = 23.9
  • Upper innerfence = 3rd Q + (1.5 * IQR) = 63.6

Spread of the data

  • Range
  • Variance
  • SD

Spread of the data

  • Range = max - min
  • Variance \[ \begin{equation} s^2 = \frac{\sum\limits_{i=1}^{n}(y_i - \bar{y})^2} {n - 1} \end{equation} \]
  • SD \[ \begin{equation} s = \sqrt{\sum_{i=1}^n (y_i - \bar{y})^2} \end{equation} \]

Shape of the data

Shape of the data

Shape of the data

Shape of the data