What is the test statistic for a likelihood ratio test?

2*[l1 - l2]

The test statistic for a likelihood ratio test compares how well two nested models fit the data by using their maximum log-likelihoods. If you denote the log-likelihood under the unrestricted (alternative) model as l1 and under the restricted (null) model as l2, the statistic is -2 times the log of the likelihood ratio, which simplifies to 2 times the difference of the log-likelihoods: 2*(l1 - l2). This quantity is nonnegative and large values indicate the unrestricted model fits significantly better, supporting rejecting the null. Under large samples, it follows an approximate chi-square distribution with degrees of freedom equal to the number of extra parameters in the unrestricted model.

So the form 2*(l1 - l2) is the correct expression. The other forms don’t match the standard LR statistic: l1 - l2 lacks the factor 2 (and can be negative), ln(l1/l2) is the log of the ratio but not the LR statistic itself, and 2*(l0 - l1) would be the negative of the typical value if l1 > l0.

l1 - l2

2*[l0 - l1]

ln(l1/l2)

Want more questions?

All options are one-time payments.

$12.99

30 day pass for new members

All the basics to get you started

  • Ad-free experience
  • View your previous attempt history
  • Mobile app access
  • In-depth explanations
  • 30 day premium pass access
$29.99$92.93 usd

6 month DELUXE pass (most popular)

Full access FOR 6 MONTHS! & the ultimate digital PDF study guide (BONUS)

  • $92.93 usd value for $29.99! You save $62.94!
  • Ad-free experience
  • View your previous attempt history
  • Mobile app access
  • In-depth explanations
  • 6 months of full access
  • Ultimate digital PDF study guide included
  • Priority support
$14.99 $19.99

Ultimate digital PDF study guide

For those that prefer a more traditional form of learning

  • Available for instant download
  • Available offline
  • Hundreds of practice multiple choice questions
  • Comprehensive content
  • Detailed explanations
Image Description
Subscribe

Get the latest from Examzify

You can unsubscribe at any time. Read our privacy policy