Independent t Test in SPSS

Описание: Learn how to conduct the independent samples t test in SPSS in this video. Interpret the results of the t test and Levene's test of equal variances. For our SPSS video series, click here:

SPSS Inferential Statistics Videos: http://tinyurl.com/lm9hpwc

Channel Description:    / statisticsinstructor  
Subscribe today!

Video Transcript: In this video, we'll take a look at another example of the independent samples t-test in SPSS. And in this example we have the variables treatment and pain level. And we have two groups, as we always do with the independent t, for the variable treatment, where I entered value labels and you can see that the first group all receive the treatment of acupuncture, whereas the second group all received the treatment of massage therapy. And after receiving this treatment for a period of two weeks, then they responded on a 1 to 7 scale the amount of pain they were currently experiencing at the end of the last treatment, where 7 indicates the highest degree of pain, and 1 indicates the lowest degree. So you can see here that the first person, who happened to receive acupuncture, had a pain level of 6 at the conclusion of the treatment. The second person had a pain level of 5, and so on. The first person in the massage therapy group had a pain level of 6, the second person had a pain level of 5, the third person a pain level 7, and so on. So let's go ahead and run the independent samples t-test. So we select Analyze, Compare Means, Independent-Samples T Test, and then here pain level is going to go in our Test Variable(s) box, so we'll move that over there, and then treatment is going to go into our Grouping Variable, as this is the variable that separates people into the two groups. Now we can see here that we use the values of 1 and 2 to separate our two groups. So go ahead and click on Define Groups and enter a 1 for group 1 and then a 2 for group 2. And then click Continue and then OK. Our output opens and we can see here that there was a very small difference between our two means, where the acupuncture group reported a higher joint pain than did the massage therapy group, but that difference is pretty small. Moving to our Independent Samples T Test table, here we're going to interpret whether or not the test is statistically significant. First recall that we interpret the results of our Levene's test. And, as a reminder, the decision rule is as follows: if p is less than or equal to .05, the variances are significantly different and we want to interpret the bottom row of results for t, whereas if p is greater than .05, the variances are not significantly different and we want to interpret the top row of results for t. Looking at these two conditions here, which does ours fall into? We have a p of .873, and that falls into the second condition here, so therefore the variances are not significantly different, and we'll go ahead and interpret the top row of results for t. So we're going to look at these values here in the top row for t. And recall the decision rule for assessing of the t is significant, using alpha .05, is we look at this p-value, and if p is less than or equal to .05, the test is significant, which indicates the pain levels differ significantly for the acupuncture and massage therapy groups. Whereas if p is greater than .05, the test is not significant, indicating that the pain levels do not differ significantly for the two groups. So we see a p of .494 and you should see that, of these two conditions, .494 is in fact greater than .05, therefore the test is not significant, meaning that the pain levels do not differ significantly for the acupuncture and massage therapy groups. Next we'll write these results using APA format. We could write these results as follows: There was not a significant difference in the reported pain levels for those who received acupuncture and massage therapy as treatment. Then here we have t, once again indicating that we have an independent samples t test, 28 degrees of freedom, which is equal to the total sample size of 30-2, We have a t of .69, which is given here rounded to two decimal places, and finally our p-value of .494, which is shown here. Now you can state p is greater than .05, instead of stating the exact p-value if you prefer. However, as always, stating the exact p-value is more informative. So, once again in summary, our test here showed that there was not a significant difference in the joint pain between the acupuncture and massage therapy groups. This concludes the presentation on the independent samples t test in SPSS. Thanks for watching.