I have been assigned the task of helping someone who has collected some survey associated data related to some kind of government facilities provided to people. The data corresponding to small scale entrepreneurs across 3 cities who are the providing the services to the customers looks like this (sample data):

Years of experience of the entrepreneurs in City 1:
0-5 yrs: 15
5-10 yrs: 25
10-20 yrs: 30
>20 yrs: 3

Years of experience of the entrepreneurs in City 2:
0-5 yrs: 10
5-10 yrs: 27
10-20 yrs: 35
>20 yrs: 0

Years of experience of the entrepreneurs in City 3:
0-5 yrs: 5
5-10 yrs: 15
10-20 yrs: 25
>20 yrs: 5

I have to suggest some kind of statistical analysis, like representing the data in box-plot, or somehow showing the avgs using graphical representations. Currently, he uses simple column graphs for each of the cities.

  • $\begingroup$ Some basic questions: Do you know how many people responded for each city? What is the data going to be used for? $\endgroup$
    – user31668
    Commented Aug 22, 2014 at 19:03
  • $\begingroup$ Yea ..I know the total number of people from each city who participated in the survey. The government basically wants to know the background of these small scale entrepreneurs, their age groups, income, years of exp and correlate it with the level of satisfaction they are having with their small scale business. The problem is that the data has intervals instead of absolute values for each of the categories I mentioned $\endgroup$
    – Bitsy
    Commented Aug 22, 2014 at 19:21
  • $\begingroup$ Thanks! Does the government care about location-specific effects, or just individual characteristics? $\endgroup$
    – user31668
    Commented Aug 22, 2014 at 19:30
  • $\begingroup$ Maybe not so much on the locations..as the cities were selected randomly. Any ideas coming to your mind ? $\endgroup$
    – Bitsy
    Commented Aug 22, 2014 at 19:49

1 Answer 1


Given your responses and the goal of correlating satisfaction with personal-level characteristics, I think the following may be helpful:

  1. Aggregate your data by age interval across cities, since you don't care about location.
  2. Prepare box-and-whisker plots of satisfaction for each age interval.
  3. Check the normality of your data for each age interval.
  4. If data are reasonably normal, perform an ANOVA to compare the levels of satisfaction between the age groups. If not, try Kruskal-Wallis (nonparametric version).
  5. If you find differences, then use a multiple-comparisons test to verify which ones are different (e.g. Tukey's procedure for normal data).

The above should give you some useful insights, if there are any. The tests are pretty basic and easy to interpret.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.