Confidence Level to t* Critical Value
The tool shows each step from confidence level to α to the tail area, cites the matching row of our t-table, and compares t* with the normal z*. Use the quick check underneath to practice picking t* without the common mix-ups.
Confidence level → t*
Confidence level Sidest* = 2.262
Solid: Student’s t at your df. Dashed: the normal curve. Red: the tail area beyond t*. For a one-sample interval, df = n − 1.
Quick check: pick the right t*
Five rounds. Each gives a confidence level and df for a two-sided interval. Pick t* from four choices: the wrong ones are the usual mix-ups (the one-tailed value, z* instead of t*, or the wrong confidence column). You get instant feedback with the steps.
Worked example
Question (illustrative numbers): a sample of n = 10 has mean 50.0 and standard deviation 4.0. Build a 95% confidence interval for the mean.
Step 1. Confidence 95% → α = 0.05 → two-sided, so α/2 = 0.025 in each tail.
Step 2. df = n − 1 = 9. In the two-tailed t-table, column α = 0.05, row 9: t* = 2.262.
Step 3. Margin of error = t* × s / √n = 2.262 × 4.0 / √10 = 2.861.
Answer: 50.0 ± 2.861, so the interval is (47.14, 52.86). Using z* = 1.960 instead would make it too narrow.
t* at common confidence levels (two-sided)
| df | 90% | 95% | 99% |
|---|---|---|---|
| 5 | 2.015 | 2.571 | 4.032 |
| 9 | 1.833 | 2.262 | 3.250 |
| 10 | 1.812 | 2.228 | 3.169 |
| 15 | 1.753 | 2.131 | 2.947 |
| 20 | 1.725 | 2.086 | 2.845 |
| 29 | 1.699 | 2.045 | 2.756 |
| 30 | 1.697 | 2.042 | 2.750 |
| 60 | 1.671 | 2.000 | 2.660 |
| 100 | 1.660 | 1.984 | 2.626 |
| ∞ (z) | 1.645 | 1.960 | 2.576 |
FAQ
How do you find t* from a confidence level?
Turn the confidence level into α = 1 − C. For a two-sided interval split α into two tails (α/2 each). Then read the t-table at that tail area and df. For 95% with df = 9: α = 0.05, α/2 = 0.025, and t* = 2.262.
What is t* for a 95% confidence interval?
It depends on df. With df = 9 (n = 10) it is 2.262, with df = 20 it is 2.086, with df = 29 it is 2.045 and with df = 100 it is 1.984. As df grows it approaches the z value 1.960.
What is the difference between one-sided and two-sided t*?
Two-sided puts α/2 in each tail. One-sided puts all of α in one tail, so its t* is smaller. At 95% and df = 9, two-sided t* is 2.262 and one-sided t* is 1.833. Confidence intervals and two-tailed tests use the two-sided value.
Why is t* bigger than z*?
The t-distribution has heavier tails because the standard deviation is estimated from the sample. You need to go further out to leave the same area in the tails. At 95% and df = 9, t* = 2.262 is 15.4% larger than z* = 1.960. The gap shrinks as df grows.
What if my df is not in the table?
Use the next lower df row. It gives a slightly larger t*, so your interval is a little wider and stays conservative. This tool has every df from 1 to 100 and selected rows above that, and it says when it uses a lower row.
How do I get t* in Excel or Google Sheets?
Two-sided: =T.INV.2T(α, df), for example =T.INV.2T(0.05, 9) returns 2.262. One-sided: =T.INV(1 − α, df), for example =T.INV(0.95, 9) returns 1.833.
Is this the same as the t-table calculator?
They give the same numbers. The t-table calculator starts from α and tails. This tool starts from the confidence level, shows each step to α and α/2, and compares t* with z*. Every value matches our t-table.
Related t-table pages
- T table (one-tailed and two-tailed): t* for every df
- T-table calculator and Student t-value calculator
- T vs z critical values chart and the t-distribution simulator
- Printable t* pocket card · degrees of freedom for the t-table
- Practice: DF Race and Guess the Critical t
- For z: the inverse normal calculator on z-table.com · full t-tests at StatCalculators