Back to Search
Start Over
On asymptotic validity of naive inference with an approximate likelihood
- Source :
- Biometrika. 104:153-164
- Publication Year :
- 2017
- Publisher :
- Oxford University Press (OUP), 2017.
-
Abstract
- Many statistical models have likelihoods which are intractable: it is impossible or too expensive to compute the likelihood exactly. In such settings, a common approach is to replace the likelihood with an approximation, and proceed with inference as if the approximate likelihood were the exact likelihood. In this paper, we describe conditions on the approximate likelihood which guarantee that this naive inference with an approximate likelihood has the same first-order asymptotic properties as inference with the exact likelihood. We investigate the implications of these results for inference using a Laplace approximation to the likelihood in a simple two-level latent variable model, and using reduced dependence approximations to the likelihood in an Ising model on a lattice.<br />Updated to add an additional example (inference for an Ising model on a lattice using reduced dependence approximations to the likelihood)
- Subjects :
- Statistics and Probability
Applied Mathematics
General Mathematics
05 social sciences
Inference
Mathematics - Statistics Theory
Statistical model
Statistics Theory (math.ST)
01 natural sciences
Agricultural and Biological Sciences (miscellaneous)
Statistics::Computation
010104 statistics & probability
Laplace's method
Simple (abstract algebra)
0502 economics and business
FOS: Mathematics
Statistics::Methodology
Applied mathematics
Ising model
0101 mathematics
Statistics, Probability and Uncertainty
General Agricultural and Biological Sciences
Latent variable model
050205 econometrics
Mathematics
Subjects
Details
- ISSN :
- 14643510 and 00063444
- Volume :
- 104
- Database :
- OpenAIRE
- Journal :
- Biometrika
- Accession number :
- edsair.doi.dedup.....787c1f06009edffbccaa540bf042453c