Confidence interval = Point estimate +- t-critical * std errorWhile calculating this confidence interval is it assumed that we are using 2 tailed t test?So if we are given 5% significance level should it be taken as 5% in both tails?

yes we assume a 2 tailed t test. however you may have misunderstood something here.so in a normal distribution for example, if it is a 95% confidence interval (i.e. 5% significance level), it means it is the z-score that leaves a probability of 2.5% (α/2) on the upper tail (right-hand tail) of the standard normal distribution. it isn't 5% in each tail, but 5% in total, which means 2.5% in each tail.so that means t=1.960hope this clarifies

A CFA Level 2 Discussion About Calculating Confidence Interval

Add A Reply

This topic has 1 reply, 2 voices, and was last updated 3d by harrystyles.

Author

Posts
- SbS
  Participant
  23 Feb 2021 at 8:44 am
  Up
  8
  ::
  Confidence interval = Point estimate +- t-critical * std error
  
  While calculating this confidence interval is it assumed that we are using 2 tailed t test?
  
  So if we are given 5% significance level should it be taken as 5% in both tails?
- rahul12
  Participant
  - CFA Level 3
  24 Feb 2021 at 9:46 am
  Up
  5
  ::
  yes we assume a 2 tailed t test. however you may have misunderstood something here.
  
  so in a normal distribution for example, if it is a 95% confidence interval (i.e. 5% significance level), it means it is the z-score that leaves a probability of 2.5% (α/2) on the upper tail (right-hand tail) of the standard normal distribution. it isn’t 5% in each tail, but 5% in total, which means 2.5% in each tail.
  
  so that means t=1.960
  
  hope this clarifies
Author

Posts

Viewing 1 reply thread

You must be logged in to reply to this topic.