0
$\begingroup$

I have performed paired t-test

data: compare2$average_1kpa and compare2$average_308kpa
t = 14.565, df = 21628, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 25.46339 33.38278
sample estimates:
mean of the differences 
               29.42308 

Does it mean there is a significant difference between the two columns.Also,how to analyse or figure out which rows are actually having significant difference ?

$\endgroup$
2
  • 2
    $\begingroup$ Yes the two samples are significantly different $p<2.2e-16$. The test does not tell you which pairs are different, since the t-test is a test of means. You could try plotting them. $\endgroup$ Aug 9, 2019 at 5:59
  • $\begingroup$ I plotted the data and extracted the values which are on between 95 percent confidence interval range.Are those values the cases where there is significant difference ? $\endgroup$
    – shome
    Aug 9, 2019 at 23:07

1 Answer 1

2
$\begingroup$

Yes, your test indicates that the mean difference between the two groups is 29.42 and that this difference is significant, with p < 2.2e-16. It does not make sense to ask the question "which rows are significantly different?" because doing a t-test requires multiple points from each group. Comparing just one point from each group is not really meaningful*, though as user2974951 says, you could plot your data or calculate the difference between pairs of columns to get an idea of which differences are largest.

*Technically, there are methods (from Bayesian statistics) that allow you to compare groups even if you have only one data point from each. But that requires additional assumptions and this comparison is still unlikely to tell you anything informative.

$\endgroup$
4
  • $\begingroup$ I plotted the data and extracted the values which are on between 95 percent confidence interval range. Are those values in the cases where there is a significant difference? $\endgroup$
    – shome
    Aug 9, 2019 at 23:08
  • $\begingroup$ @shome As I said above: it is not meaningful to say there is a significant difference between any pair of points. That is a claim about the population. $\endgroup$
    – mkt
    Aug 10, 2019 at 4:15
  • $\begingroup$ then, how to claim about specific data points? $\endgroup$
    – shome
    Aug 10, 2019 at 4:51
  • 1
    $\begingroup$ @shome You cannot, as I keep saying! $\endgroup$
    – mkt
    Aug 10, 2019 at 14:52

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.