# T test result interpretation

• Aug 14th 2012, 11:40 AM
Jahid
T test result interpretation
I am doing a T Test for a before and after study. My objective is to prove that before and after are not equal. so if my null hypothesis is same, how would i reject that based on the T test (Two-Sample Assuming Unequal Variances) results. (any source or help on explaining it)
• Aug 14th 2012, 02:49 PM
pickslides
Re: T test result interpretation
For a before and after study, try a paired T-test. Reject the null hypothesis if your p-value is very small i.e. p< 0.001 or the absolute value of your calculated T value is bigger than the absolute value of your critical T value.
• Aug 21st 2012, 09:59 AM
Jahid
Re: T test result interpretation
t stat and Calculated T values are they same ? My P Value (P(T<=t) two-tail) is 0.681113 is more than .001 That means I should accept the null hypothesis. following is the result from excel.

Variable 1 Variable 2
Mean 15.25 16
Variance 11.92857143 10
Observations 8 6

Hypothesized Mean Difference 0
df 11
t Stat -0.422059043
P(T<=t) one-tail 0.340556458
t Critical one-tail 1.795884814
P(T<=t) two-tail 0.681112916
t Critical two-tail 2.200985159
• Aug 21st 2012, 10:07 AM
richard1234
Re: T test result interpretation
Quote:

Originally Posted by Jahid
t stat and Calculated T values are they same ? My P Value (P(T<=t) two-tail) is 0.681113 is more than .001 That means I should accept the null hypothesis. following is the result from excel.

A p-value of 0.68 doesn't mean that you "accept" the null hypothesis. It simply means you don't have enough evidence to reject the null hypothesis.