Box Plots, IQR, and Standard Deviation — Quick Reference

Box plots and distribution comparisons

• Box plots visualize distributions and enable quick comparisons across groups (e.g., calories for hot dogs; poultry generally lower than beef and meat; some poultry brands higher than beef/meat).

• Including the minimum and maximum on box plots highlights the full range and potential outliers.

Skewness and the five-number summary

• For skewed distributions, the two halves differ; summarize spread with the five-number summary: min, Q1, median, Q3, max.

• For symmetric distributions, a single spread measure can be informative.

Interquartile range (IQR)

• For approximately symmetric distributions, the spread can be described by $\text{IQR} = Q<em>3 - Q</em>1$.

• On a box plot, the IQR is the length of the box (visual cue for spread).

Standard deviation and computation

• Steps to compute the standard deviation:

  • Mean: $\mu = \frac{1}{n} \sum<em>{i=1}^n x</em>i$

  • Deviation of each value: $x_i - \mu$

  • Variance: $\sigma^2 = \frac{1}{n} \sum<em>{i=1}^n (x</em>i - \mu)^2$

  • Standard deviation: $\sigma = \sqrt{\sigma^2} = \sqrt{ \frac{1}{n} \sum<em>{i=1}^n (x</em>i - \mu)^2 }$

• A smaller $\sigma$ indicates tighter clustering around the mean.

• Use the standard deviation to compare the spread of different distributions.

Music-based metabolic profiling analogy

• Biochemistry researchers convert metabolic values into musical notes to supplement visual data; some notes are very similar across individuals, others vary widely.

• The normal range can be inferred using the standard deviation.

From pictures to numbers

• This program shows the progression from distribution visuals to numeric descriptions: mean, median, quartiles, and standard deviation.

• Calculators/computers ease computation; focus on pictures first to identify which numbers matter.