How to Analyze Data Using t-test in SPSS
GSHontiveros
Independent samples t-test is a statistical test used to compare two treatments.
Null hypothesis (Ho): There is no significant difference between the treatments.
Alternate hypothesis (Ha): There is a significant difference between the treatments.
1. Tabulate the results of the sensory evaluation in MS Excel.
Refer to file: Dry Lab- Acceptability scores
2. Run SPSS and choose Type in Data.
3. Make sure that you are in Data View (buttons in bottom screen) and paste all the scores from
MS Excel.
You may use the keyboard shorts Ctrl + C or V here. Leave the first column blank.
Arrange all scores in one column. Clear other columns that are not in use (right-click option).
4. In the first column, indicate the treatment assignments: 1 for milkfish bone meal, 2 for goatfish
bone meal.
5. Shift to Variable View and specify parameters, such as Name, Decimals, and Measure.
“Name” of Columns should have no special characters and spaces.
Selection of decimals depends on the data. Reflect the maximum number of decimal places used in
your data.
For this example, we use a Likert scale (hedonic rating), which is an ordinal measurement. Other
options are nominal (categories like height, gender, color, etc.) and scale (infinite numbers: negative,
zero, or positive).
6. Click Analyze > Compare Means > Independent-Samples T Test
Define the Test (Dependent) Variable. In this case, we have the Acceptability of Flavor scores.
Define the Grouping (Independent) Variable. In this case, it is the Treatment.
You can specify the parameters by dragging them to their respective boxes or by clicking the arrows.
SPSS will ask you to Define Groups. You may use “1” for Group 1 and “2” for Group 2. Click
Continue, then OK.
7. SPSS will now show you a new window with the results of the t-test.
You may select which data you need and copy this to and MS Word document.
8. Make the necessary edits and add discussion to your results.
T-Test
Group Statistics
Treatment N Mean Std. Deviation Std. Error Mean
1 50 8.20 .606 .086
Acceptability of Flavor
2 50 7.40 .670 .095
Group Statistics show how many treatments there are, number of replicates per treatment, treatment
means, group standard deviation (SD), and standard error of the mean (SEM).
Independent Samples Test
Levene's Test for t-test for Equality of Means
Equality of
Variances
F Sig. t df Sig. (2- Mean Std. Error 95% Confidence
tailed) Difference Difference Interval of the
Difference
Lower Upper
Equal variances
1.225 .271 6.261 98 .000 .800 .128 .546 1.054
assumed
Acceptability of Flavor
Equal variances
6.261 97.030 .000 .800 .128 .546 1.054
not assumed
Levene’s Test for Equality of Variances tells us whether to assume or not that the variances of
treatment means are equal or not.
Sig > 0.05: Equal variances assumed
Sig < 0.05: Equal variances not assumed
Sig. or the p-value is needed to conclude if there is a significant difference in treatment means. Go back
to the question:
Is there a significant difference on the acceptability of the flavor of luncheon meat from milkfish
bone meal and goatfish bone meal?
Sig > 0.05: no sig diff
Sig < 0.05: sig diff
Since p= 0.00, we reject the Ho and accept the Ha. We can conclude that:
There is a significant difference between the treatments.
Check the mean hedonic rating of the treatments:
Treatment 1 (Milkfish bone meal): 8.20
Treatment 2 (Goatfish bone meal): 7.40
This means that:
Luncheon meat with milkfish bone meal has a significantly better flavor than the treatment with
goatfish bone meal (p<0.05).
