Descriptive statistics
Variable types, frequencies, location, variability and the shape of a distribution. The foundation without which no table can be read.
Descriptive statistics squeezes data into a few numbers. The art is knowing which number lies and which one tells the truth.
The tasks follow the order in which the material is usually taught: first variable types and measurement scales, then frequencies and tables, measures of location and finally variability and the shape of a distribution. They include calculator exercises, multiple choice questions, short tasks in Python (pandas) and open questions on interpretation.
Lessons
Read first, then practise on the tasks.
Lesson 1
Measurement scales: what you may do with a variable
Four scales, three questions and one trap in pandas. Before your first calculation, you know which numbers make sense.
~10 minup to 50 ptsLesson 2
Median vs mean: when a single number lies
The mean sees everything, even the extremes. The median shows the typical case. Learn when to use which.
~10 minup to 60 ptsLesson 3
Variability and the box plot: how much the data differ
Range, IQR, standard deviation and the box plot. When to use which measure and what the shape reveals.
~12 minup to 50 pts
Projects
One real dataset, analysed step by step.
Project
Coffee ratings: variability, outliers and shape
How much do the ratings of 1,339 coffee samples differ? Range, IQR, standard deviation, fences, skewness and cleaning faulty values.
10 steps~50 minup to 200 ptsProject
Titanic passengers: mean, median and quartiles
Who travelled on the Titanic and how much did they pay? Measures of location by class, port and sex for 891 real passengers.
10 steps~45 minup to 180 ptsProject
Penguins from Antarctica: types of variables and frequencies
From a first look at the table through frequencies and intervals to a contingency table. On real measurements of 344 penguins.
9 steps~45 minup to 165 pts
Tasks
Variable types and measurement scales
Video with Sensei
Measurement scales
1:13 · narrated in Slovak
Frequencies and tables
Video with Sensei
A share of the right base
1:05 · narrated in Slovak
Proportion of the answers given
number10 ptsfrequenciesrelative frequencymissing valuesCumulative frequency
number10 ptsfrequenciescumulative frequencyordinal variableClass width by Sturges' rule
number15 ptsgrouping into classesSturges' rulehistogramBy rows or by columns?
choice15 ptscontingency tableconditional frequencyExpected frequency
number15 ptscontingency tableexpected frequencyresidualFrequencies and a contingency table in pandas
code25 ptspythonpandasfrequenciescontingency table
Measures of location
Video with Sensei
Median vs. mean
1:08 · narrated in Slovak
Median or mean?
choice10 ptsmedianmeanoutliersCalculate the median
number10 ptsmedianThe median from a frequency table
number15 ptsmedianfrequency tableThe mean of two groups combined
number15 ptsmeanweighted meanMean and median in Python
code20 ptspythonmedianmeanSalaries by department in pandas
code25 ptspythonpandasmedianmeanchartThe upper quartile
number10 ptsquartilespercentiles
Variability and shape
Video with Sensei
The box plot
1:12 · narrated in Slovak
What the standard deviation tells us
choice15 ptsstandard deviationvariabilitySample standard deviation by hand
number15 ptsstandard deviationvariancecalculationThe upper fence from describe() output
number15 ptsquartilesIQRoutlierspandasCoefficient of variation
number10 ptscoefficient of variationstandard deviationWhat a box plot shows
choice15 ptsbox plotquartilesmedianWhen the 68, 95 and 99.7 % rule holds
choice15 ptsstandard deviationshape of distributionskewnessWhat skewness reveals
choice10 ptsskewnessshape of distributionpandasOutliers and shape in pandas
code30 ptspythonpandasIQRoutliersskewnessbox plotShape of the distribution and the typical order
text25 ptsshape of distributionmedianIQRinterpretationWhich line meets the requirement
text25 ptsstandard deviation95 % ruledecision makingOutlier, error or exception?
text20 ptsoutliersdata cleaningIQR