A t test table in APA format presents the results of a t test clearly and without unnecessary detail.
This page provides examples of:
The examples concentrate on the content and format of the tables.
If you need an explanation of t test analysis and how to interpret the results, see t Test Analysis.
An independent-samples t test compares the results for two separate groups.
Suppose you want to compare the final exam scores of students taught using two different teaching methods.
There are 80 students:
The results are shown in Table 1.
Table 1
Final Exam Scores by Teaching Method
| Outcome | Classroom | Online | t(78) | p | Cohen's d | ||
|---|---|---|---|---|---|---|---|
| M | SD | M | SD | ||||
| Exam score | 74.20 | 8.60 | 69.10 | 9.40 | 2.53 | .013 | 0.57 |
Note. n = 40 for each group. M = mean; SD = standard deviation; t = t statistic; the value in parentheses is the degrees of freedom; p = probability value; d = Cohen's d effect size.
The results in Table 1 show that:
Format the independent-samples t test table as follows:
A paired-samples t test compares two sets of scores obtained from the same participants.
Suppose 80 students complete an exam before and after taking part in a study-skills program.
Suppose 80 students complete an exam before and after taking part in a study-skills program.
The mean exam score before the program is 67.40.
After the program, the mean score is 72.60.
The results are shown in Table 2.
Table 2
Exam Scores Before and After a Study-Skills Program
| Outcome | Before | After | t(79) | p | Cohen's d | ||
|---|---|---|---|---|---|---|---|
| M | SD | M | SD | ||||
| Exam score | 67.40 | 9.80 | 72.60 | 9.10 | 6.20 | < .001 | 0.69 |
Note. N = 80. M = mean; SD = standard deviation; t = t statistic; the value in parentheses is the degrees of freedom; p = probability value; d = Cohen's d effect size.
The results in Table 2 show that:
Use the same general format as for the independent-samples t test table in APA format.
For the paired-samples table:
A t test table commonly contains several statistit test tablecal symbols and abbreviations.
M represents the mean, or average score. It lets you compare the typical result for each group or measurement.
SD represents the standard deviation. It shows how spread out the individual scores are around the mean.
t is the t statistic calculated by the test. A larger absolute t value generally indicates a larger difference relative to the variability in the data.
p is the probability value used when assessing statistical significance. A small p value indicates that the observed difference would be unlikely if there were really no difference between the groups or measurements.
d represents Cohen's d, an effect-size measure. It indicates how large the difference is, rather than simply whether the difference is statistically significant.
Use n for the number of participants in one group and N for the total sample where appropriate. Use n for the number of participants in one group and N for the total sample. Sample size matters because it affects how precisely the groups can be compared.
Formatting p Values
Report the exact p value when this is useful, usually to two or three decimal places, for example, p = .013.
Do not write a zero before the decimal point because a p value cannot be greater than 1.
For very small p values, report p < .001.
Do not report p = .000.
If the table already contains exact p values, significance asterisks are usually unnecessary. If you use asterisks, explain them in a note below the table.
A t test table in APA format provides a compact way to present the descriptive statistics and the results of a t test.
An independent-samples t test table compares two separate groups.
A paired-samples t test table compares two measurements from the same participants.
Include the information readers need to understand the comparison, such as the means and standard deviations, the t value, degrees of freedom, p value, and an effect size where appropriate.
A confidence interval for the difference can also provide useful information about the estimated difference between the groups or measurements.
Use the standard APA table format: a bold table number, an italicized title in title case, clear column headings, minimal horizontal lines, no vertical lines, and a table note when information needs to be explained.
Italicize statistical symbols such as M, SD, t, p, n, N, and d.
When should I use a table rather than report a t test in the text?
A table is particularly useful when you have several outcomes or several t tests to report.
For a single simple comparison, presenting the results in the text may be sufficient.
Your instructor may also require the results to be presented in a table.
Should I include Cohen's d in a t test table?
Including an effect size such as Cohen's d helps readers judge the size of the difference rather than relying only on the p value.
If you include Cohen's d, identify it clearly in the column heading or table note.
Should I use significance asterisks if the table already contains p values?
Usually there is little benefit in showing both.
If an exact p value is provided for each test, readers can see the level of statistical significance directly.
Asterisks may be useful in a large table where readers need to identify statistically significant results quickly. Explain any asterisks in a note below the table.
Can I include several t tests in the same table?
Yes.
For example, if you compare two groups for exam score, study time, attendance, and test anxiety, place each outcome on a separate row and use the same statistical columns for each comparison.
This is often more useful than creating a separate table for every t test.
See this example of a t test table in APA format.
How do I align a p value such as < .001 with other p values?
A decimal tab works well for ordinary values such as .013 and .247 but is less useful when a column also contains entries such as < .001.
For a short p-value column, centering the entries may give a cleaner result.
The important point is to use consistent alignment throughout the column.
What should I do if the t test table is too wide?
First remove information that is repeated unnecessarily.
For example, place the mean and standard deviation together as M (SD) rather than using separate columns if this makes the table easier to read.
You can also put a sample size that applies to every row in the table note rather than repeating it.
If the table is still too wide, consider using landscape orientation.