Engagement survey population and response rates

Companion table to engagement_survey: for each department of the fictional Palmstone Group, the number of employees invited to the survey (headcount), the number who responded and the response rate. Use it to see that the respondents over-represent some departments and to build post-stratification weights that correct the overall engagement estimate.

Open in the lab Download CSV

Rows: 6
Columns: 4
One row is: one department
Version: v1

Data dictionary

Column	Type	Unit	Summary	Description
`department` Department	category		6 levels: Operations, Customer Service, Sales, Technology, Finance, Human Resources	Department.
`headcount` Headcount	integer	employees	mean 233.3, median 235, SD 132.9, range 60–420	Employees invited to the survey.
`responses` Responses	integer	responses	mean 129.7, median 147, SD 53.56, range 48–189	Completed responses received (rows in engagement_survey).
`response_rate_pct` Response rate	number	%	mean 61.7, median 61.65, SD 13.73, range 45–80	responses ÷ headcount × 100.

What it is good for

Compute response rates and compare the respondent mix with the population mix.
Build post-stratification weights (population share ÷ sample share) and apply them to survey means.
Explain nonresponse bias with a concrete example.

Methods: proportions, chi-square goodness of fit, post-stratification weighting, weighted mean.

Data quality notes

Aggregated table (6 rows); the respondent-level data are in engagement_survey.
No missing values.

Provenance and licence

Fixed headcounts and response rates chosen for teaching (less engaged departments respond less). responses = round(headcount × response rate) and equals the number of rows per department in engagement_survey exactly.

Synthetic data · CC0-1.0 (synthetic data generated by Statistics Quest) · generated deterministically (seed 20241011). It does not describe real people or organisations; any resemblance is coincidental.

Preview

Dataset

Engagement survey population and response rates

6 rows · one row = one department · synthetic data

About this dataset Open in the lab

Department	Headcount (employees)	Responses (responses)	Response rate (%)
Operations	420	189	45
Customer Service	330	165	50
Sales	260	143	55
Technology	210	151	71.9
Finance	120	82	68.3
Human Resources	60	48	80

Used in

Populations, samples, parameters and statistics · Statistical Thinking
Bias and representative samples · Statistical Thinking
Sampling methods · Sampling and the Central Limit Theorem
Sampling bias and nonresponse · 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
Sensitivity analysis · Resampling and Statistical Reasoning
Survey research · Applied Statistics for Professionals