Versión de HTML Básico
TOURISM&CREATIVE INDUSTRY WORKSHOP
Sustainable tourism, cultural tourism, creative tourism, culinary tourism, heritage & tourism
193
1
Univerisity of Utah
David Eccles School of Business, Dept. of
Operations and IS
1655 E Campus Center Drive
Salt Lake City, UT 84112
EEUU
don.wardell@utah.edu
2
Bank of the West
San Francisco, CA
mailto:candiama@pon.net
Statistical Process Monitoring of Customer
Satisfaction Survey Data
4
Wardell
1
, D.G., Candia
2
, M.R.
Keywords:
categorical data, control charts, customer focus, goodness-of-fit,
multi-nomial distribution.
Understanding and monitoring customer needs and satisfaction are crucial
re-quirements of quality management and fundamental in the tourism industry.
Many organizations collect frequent customer satisfaction data over time
using customer surveys. The results of the survey help the organization to
know how customers feel about their products and services with the goal to
find ways to improve satisfaction and loyalty. A logical yet infrequently used
means of monitoring these data is with process control charts. Such charts
provide managers with a mechanism for scanning the external and internal
environments for changes in customer-satisfaction levels. The type of data
that are used in most customer surveys, however, does not fit the assump-
tions of traditional Shewhart control charts that use sample averages and
ranges. In particular, such charts typically assume that the data are normally
distributed, which is not the case for typical customer-satisfaction data. Hence
the charts need to be modi-fied to monitor categorical or ordinal customer
survey data. Using data from a major hospital, this article shows how blindly
applying traditional x-bar charts based on subgroup ranges to ordinal survey
data can lead managers to erroneous conclusions about the level of customer
4. This research was published in Quality Management Journal, Volume 3, Number 4, pages 36-
50. Reprinted with permission from Quality Management Journal ©1996 American Society for
Quality. No further distribution allowed without permission.