I am trying to compare multiple mean values, variance and standard deviation values for statistical significance. For example I have the following data:

Data 1

  • Mean: 0.01304
  • Sample Variance: 0.000504324897959184
  • Standard Deviation: 0.0224571792075315

Data 2

  • Mean: 1.17498
  • Sample Variance: 0.180901244489796
  • Standard Deviation: 0.425324869352588

How can I compare them?

  • $\begingroup$ Is this a question from a course or textbook? Even if not, for questions like this you should probably add the [self-study] tag & read its wiki. $\endgroup$ Apr 6 '15 at 16:25
  • $\begingroup$ Using only sample statistics, you will need to make assumptions. You will also need the $n$'s from the 2 datasets. Do you have that? $\endgroup$ Apr 6 '15 at 16:45
  • $\begingroup$ @gung Yes I have the n's. The n for both the above data is 50. I need to compare the information above to come to a conclusion. I just don't know how to compare them. are there any formulas or techniques? I have the entire data set from which mean, variance and standard deviation was calculated. $\endgroup$ Apr 6 '15 at 16:49
  • $\begingroup$ Is this question from a course or textbook? What software do you have access to? You would do better to work with the full dataset rather than just the summary statistics. $\endgroup$ Apr 6 '15 at 16:50
  • $\begingroup$ @gung its not from any course or textbook. I collected the data myself. The data represents HTTP requests times for 2 different web frameworks. The above means, variance and standard deviation were calculated from the data set using EXCEL. $\endgroup$ Apr 6 '15 at 16:56

Because your data are durations, you should use methods from survival analysis. A $t$-test is unlikely to be appropriate. I doubt this can be done in Excel. It isn't hard to do in R, however, and R is free. You should download R from here. This guide should be simple and quick enough to give you what you will need.

What you want is to use a log rank test. In R that's ?survdiff. You may also want to plot and examine the Kaplan-Meier survival curves. In R, you can use ?survfit and then plot(). Here's a quick demonstration from the R documentation:

# install.packages(survival)  # if necessary

leukemia.surv <- survfit(Surv(time, status) ~ x, data = aml) 
  plot(leukemia.surv, lty = 2:3) 
  legend(100, .9, c("Maintenance", "No Maintenance"), lty = 2:3) 
  title("Kaplan-Meier Curves\nfor AML Maintenance Study") 

enter image description here

survdiff(Surv(time, status) ~ x, data = aml)
# Call:
#   survdiff(formula = Surv(time, status) ~ x, data = aml)
#                  N Observed Expected (O-E)^2/E (O-E)^2/V
# x=Maintained    11        7    10.69      1.27       3.4
# x=Nonmaintained 12       11     7.31      1.86       3.4
# Chisq= 3.4  on 1 degrees of freedom, p= 0.0653 

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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