Search
  • Kalpesh Agrawal

Continuity Correction

When we use a normal approximation for continuous probability distribution we don’t have to consider any change.


But while using a normal approximation for discrete probability distribution we use continuity correction.


For example, while applying normal approximation on the binomial distribution with a large sample size, we are supposed to use continuity correction because binomial distribution only considers integers whereas normal distribution can take all the real numbers.


The following changes we need to make while calculating probability using a normal approximation in the case of discrete distribution:


Discrete

Continuous

P (X = a)

P (a - 0.5 < X < a + 0.5)

P (X < a)

P (X < a - 0.5)

P (X > a)

P (X > a + 0.5)

P (X <= a)

P (X < a + 0.5)

P (X >= a)

P (X > a - 0.5)


Written by: Sneha Khanna

Email ID: sneha12khanna@gmail.com


0 comments

Related Posts

See All