Employee commute times

One row per employee of a fictional mid-sized company, Sandreed Services, describing a typical one-way commute: travel mode, shift, distance and the usual door-to-door time. Commute times are right-skewed with two extreme values, which makes the dataset ideal for comparing the mean and median and for discussing outliers.

Open in the lab Download CSV

Rows: 240
Columns: 5
One row is: one employee (their typical one-way commute)
Version: v1

Data dictionary

Column	Type	Unit	Summary	Description
`employee_id` Employee	id			Anonymous employee identifier (E001–E240).
`mode` Travel mode	category		5 levels: car, bus, metro, bike, walk	Main travel mode of the commute.
`shift` Shift	category		3 levels: morning, day, evening	Working shift (morning starts 07:00, day 09:00, evening 15:00).
`distance_km` Distance	number	km	mean 13, median 11.4, SD 9.346, range 0.3–61.4	One-way door-to-door distance.
`commute_min` Commute time	integer	minutes	mean 37.31, median 31.5, SD 23.81, range 4–148	Typical one-way door-to-door commute time.

What it is good for

Compare the mean and median of a right-skewed variable and explain why they differ.
Identify outliers with the 1.5 × IQR rule and judge whether to keep them.
Compare a numeric variable across groups (mode, shift) with box plots.
Describe the relationship between distance and time and how it varies by mode.

Methods: mean vs median, skewness, box plot, IQR outlier rule, histogram, scatter plot, correlation.

Data quality notes

commute_min is strongly right-skewed (skewness > 1).
Two deliberate extreme values: employee E038 (car, about 61 km, 148 minutes) and E152 (bus, 14.2 km, 126 minutes — a breakdown-affected commute far slower than its distance suggests).
Times are rounded to whole minutes and distances to 0.1 km.
No missing values.

Provenance and licence

Mode drawn with fixed shares (car 48%, metro 17%, bus 15%, walk 12%, bike 8%). Distance depends on mode (log-normal for car/bus/metro, gamma for bike/walk). Time = fixed access/waiting overhead per mode + distance ÷ mode speed (morning trips 25% slower by car and 15% slower by bus because of congestion), multiplied by log-normal day-to-day variation (sd 0.18 on the log scale), rounded to whole minutes. Two records were then made extreme on purpose (rows 38 and 152 in 1-based order).

Synthetic data · CC0-1.0 (synthetic data generated by Statistics Quest) · generated deterministically (seed 20241001). It does not describe real people or organisations; any resemblance is coincidental.

Preview

Dataset

Employee commute times

240 rows · one row = one employee (their typical one-way commute) · synthetic data

About this dataset Open in the lab

Employee	Travel mode	Shift	Distance (km)	Commute time (minutes)
E001	car	day	9.6	24
E002	car	day	13.2	38
E003	bus	day	17.4	71
E004	walk	morning	2.5	24
E005	walk	day	0.9	10
E006	car	day	7.6	22
E007	car	day	18.7	38
E008	metro	day	18.4	43
E009	metro	morning	4.6	29
E010	metro	day	10.7	39
E011	bus	day	19.9	73
E012	car	morning	8.4	19

Used in

What statistics is for · Statistical Thinking
Variables and observations · Statistical Thinking
Frequency and relative frequency · Describing Data
Mean, median and mode · Describing Data
Variance and standard deviation · Describing Data
Five-number summary and outliers · Describing Data
Grouped data · Describing Data
Histograms · Visualising and Exploring Data
ECDFs and Q-Q plots · Visualising and Exploring Data
Accessible charts and data stories · Visualising and Exploring Data
Sampling distributions · Sampling and the Central Limit Theorem
Standard error · Sampling and the Central Limit Theorem
The central limit theorem · Sampling and the Central Limit Theorem
Finite populations · Sampling and the Central Limit Theorem
Sample size, precision and cost · Sampling and the Central Limit Theorem
Point estimates and their properties · Estimation and Confidence Intervals
The idea of an interval estimate · Estimation and Confidence Intervals
Interval for a mean with known σ · Estimation and Confidence Intervals
Interval for a mean with unknown σ · Estimation and Confidence Intervals
Interpreting confidence correctly · Estimation and Confidence Intervals
Planning sample size · Estimation and Confidence Intervals