Suppose a question is given to find the confidence interval at 95% confidence level.
If it is a one tailed test, how to calculate the confidence interval?
The critical value will be 1.645 or 1.96 in this case?
I am very confused , as , in one tailed test the rejection region is only seen in one side.
If you assume a normal (i.e., Gaussian distribution), you find that about $95\%$ of the occurrences fall above $\mu + 1.65 \cdot \sigma$, where we indicate the mean as $\mu$ and the standard deviation as $\sigma$.
Now, if you are going to perform a one tailed hypothesis test (if you think you should do so, instead of performing a standards two tailed test), you need to decide which one you prefer, Chi-squared tests or F-tests?
If we are talking about the latter, you have to keep in mind that a smaller t-value is needed (1.725) in order to produce a statistically significant result in the right tail than the two-tailed test (2.086).
Everything is explained in the linked article (see below), and this would answer to your question, providing enough clarifying information to manage to solve these kind of tasks by yourself: One-Tailed Hypothesis Tests