Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 1 down vote favorite

I have a questionnaire with a five point scale. Differences in means is obtained. As my data is not normal I am using NON-PARAMETRIC tests for my comparisons.

Population: 1 group (Pharmacists only)

Question example: 

Statement                                                Min   Max  Mean Std.D 
Are important reference tool while  dispensing medication  1    5   3.4  .829
Are important reference tool while responding to symptoms  1    5   3.7  .876

How do you test if a significance exists between these two statements?

share|improve this question
1  
Statement or question? – Stat-R Aug 22 '12 at 23:13
Although the data may be non-normal, if you have a moderate to large sample it's likely the sampling statistics are close to normal. In that case, resorting to non-parametric methods may decrease your ability to discriminate important differences (loss of power). If that's the case, you ought to reconsider your approach. – whuber♦ Aug 23 '12 at 14:05

1 Answer

up vote 1 down vote

If you are trying to determine if there is a significant difference in the average (or more generally center ) of the distribution of scores and you have scores on both questions by all subjects then you could use the Wilcoxon signed rank test which is a paired test. If not all subjects answered both questions the unpaired Wilcoxon rank sum test is a reasonable choice.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

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