Hi Morgan,
- It looks like your null and alternative hypotheses somehow got deleted. Without more information, we should assume test is two-tailed.
- Two ways to do this—first way is to use a TI-80s series calculator. Go to STAT-EDIT-input sample 1 values into L1, input sample 2 values into L2. Then, go to STAT-TESTS-2SampTtest—enter “Data,” change alternative to mu1 not equal to mu2, Pool: no; calculate. You will get t-test statistic, p-value, sample means and standard deviations, and degrees of freedom.
Second way is longer, but you may have to use it if you do not have a TI-80s series calculator.
Formula is:
T = (xbar1 -xbar2) - 0 / sqrt[s12/n1) + (s22/n2)]
Xbar1= Sample 1 Mean
Xbar2= Sample 2 Mean
S1= Sample 1 standard deviation
S2= Sample 2 standard deviation
N1= Sample 1 Size = 3
N2= Sample 2 Size = 3
You can compute sample means readily enough by just adding the values together and dividing by 3. You may want to use a calculator or software for standard deviations, as they involve differences of squares, which can induce errors. Both sample sizes are 3.
#4. P-value can be found in calculator as described above or from statistical software. You can also get it from a t-table but this is less precise—you can only get a range, not an actual p-value that you can round to 4 decimals.
#5 and 6. This depends on your p-value. Your problem does not specify an alpha, that is, a rejection cutoff for p-value, but the most common p-value cutoff is 0.05, so I’ll go with it here. If your p-value falls below 0.05, reject H0. If it exceeds 0.05, fail to reject H0. If you reject, there is sufficient evidence that population mean 1 differs from population mean 2. If you fail to reject, there is not sufficient evidence that population mean 1differs from population mean 2.
I hope this helps.