☕ Customer satisfaction survey (Likert scale)
Research question: Do the eight items form a reliable satisfaction scale, and how satisfied are customers overall? Answer: The 8-item satisfaction scale had excellent internal consistency, Cronbach's α = .91.
Open this example in StatLab Dataset and codebook (CSV, Excel, .sav)
What is the situation?
A fictional café chain with three outlets in the Klang Valley ran an 8-item satisfaction questionnaire (1 = strongly disagree … 5 = strongly agree). Item s4 (“I waited too long to be served”) is negatively worded. The data are synthetic — produced by a seeded random process for teaching; they describe no real people or organisations.
What is in the dataset?
220 cases.
| Variable | Label | Measure | Value labels |
|---|---|---|---|
id | Customer ID | scale | |
outlet | Outlet | nominal | 1 = Bangsar, 2 = Shah Alam, 3 = Cyberjaya |
s1 | Food quality was good | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s2 | Drinks were well made | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s3 | Staff were friendly | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s4 | I waited too long to be served | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s5 | The outlet was clean | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s6 | Prices were fair | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s7 | Wi-Fi was reliable | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
s8 | I would recommend this café | ordinal | 1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly agree |
How is it analysed, step by step?
- Frequencies — Look at the distribution of the key outcome item first. (guide)
I would recommend this café: Strongly disagree 13 (5.9%), Disagree 49 (22.3%), Neutral 64 (29.1%), Agree 69 (31.4%), Strongly agree 25 (11.4%) - Recode into different variables — Reverse-score the negatively worded item so that a high score always means more satisfied. (guide)
New variable s4r: 1↔5, 2↔4, 3 unchanged. - Reliability (Cronbach's alpha) — Check internal consistency with Cronbach's alpha and the item-total statistics. (guide)
Cronbach's α = .915 (8 items, n = 220); corrected item-total correlations .49–.78.
How would I write it up (APA style)?
The 8-item satisfaction scale had excellent internal consistency, Cronbach's α = .91.
Every number on this page was computed by StatLab's statistics engine from this dataset when the page was built, and the same analyses are part of the reference validation against scipy/statsmodels (433 reference test cases, 36,554 values checked against scipy/statsmodels/numpy, 0 failures). “Open this example” loads the data and runs these steps live in your browser.