Estimation in discretely observed diffusions killed at a threshold
From MaRDI portal
bootstrapdiffusion processesfirst-passage timesmodel misspecificationsequential estimationstochastic neuron models
Diffusion processes (60J60) Point estimation (62F10) Asymptotic properties of parametric estimators (62F12) Bootstrap, jackknife and other resampling methods (62F40) Sequential estimation (62L12) Markov processes: estimation; hidden Markov models (62M05) Applications of statistics to biology and medical sciences; meta analysis (62P10)
Abstract: Parameter estimation in diffusion processes from discrete observations up to a first-hitting time is clearly of practical relevance, but does not seem to have been studied so far. In neuroscience, many models for the membrane potential evolution involve the presence of an upper threshold. Data are modeled as discretely observed diffusions which are killed when the threshold is reached. Statistical inference is often based on the misspecified likelihood ignoring the presence of the threshold causing severe bias, e.g. the bias incurred in the drift parameters of the Ornstein-Uhlenbeck model for biological relevant parameters can be up to 25-100%. We calculate or approximate the likelihood function of the killed process. When estimating from a single trajectory, considerable bias may still be present, and the distribution of the estimates can be heavily skewed and with a huge variance. Parametric bootstrap is effective in correcting the bias. Standard asymptotic results do not apply, but consistency and asymptotic normality may be recovered when multiple trajectories are observed, if the mean first-passage time through the threshold is finite. Numerical examples illustrate the results and an experimental data set of intracellular recordings of the membrane potential of a motoneuron is analyzed.
Recommendations
- On the asymptotic behavior of the parameter estimators for some diffusion processes: application to neuronal models
- Maximum likelihood drift estimation for a threshold diffusion
- Maximum likelihood estimation for an Ornstein-Uhlenbeck model for neural activity
- Estimation of the killing rate parameter in a diffusion model
- Parameter estimation for threshold Ornstein-Uhlenbeck processes from discrete observations
Cites work
- A new integral equation for the evaluation of first-passage-time probability densities
- A theory of the term structure of interest rates
- An improved technique for the simulation of first passage times for diffusion processes
- An unbiased estimator for the drift of a stopped Wiener process
- Asymptotics of hitting probabilities for general one-dimensional pinned diffusions
- Boundary crossing random walks, clinical trials, and multinomial sequential estimation
- Diffusion approximation and first-passage-time problem for a model neuron. III: A birth-and-death process approach
- Estimating functions for diffusion-type processes
- First-passage-time density and moments of the ornstein-uhlenbeck process
- How sample paths of leaky integrate-and-fire models are influenced by the presence of a firing threshold
- scientific article; zbMATH DE number 3736679 (Why is no real title available?)
- scientific article; zbMATH DE number 3103824 (Why is no real title available?)
- Markov Chains and Stochastic Stability
- Markov stopping sets and stochastic integrals. Application in sequential estimation for a random diffusion field
- On a set of data for the membrane potential in a neuron
- On asymptotics of estimating functions
- On evaluations and asymptotic approximations of first-passage-time probabilities
- On Maximum Likelihood Estimation in Randomly Stopped Diffusion-Type Processes
- On the bias of maximum likelihood estimation following a sequential test
- On the comparison of Feller and Ornstein-Uhlenbeck models for neural activity
- On the evaluation of first-passage-time probability densities via non-singular integral equations
- On the First Passage Time Probability Problem
- Parameter estimation and bias correction for diffusion processes
- Parameters of the Diffusion Leaky Integrate-and-Fire Neuronal Model for a Slowly Fluctuating Signal
- Sequential estimation of the parameters of diffusion processes
- Some Properties of Regular Markov Chains
- The most likely voltage path and large deviations approximations for integrate-and-fire neurons
- The parameters of the stochastic leaky integrate-and-fire neuronal model
- The Spike-Triggered Average of the Integrate-and-Fire Cell Driven by Gaussian White Noise
- Two singular diffusion problems
- Unbiased Estimates for Certain Binomial Sampling Problems with Applications
Cited in
(12)- On the asymptotic behavior of the parameter estimators for some diffusion processes: application to neuronal models
- A review of asymptotic theory of estimating functions
- Inference and rare event simulation for stopped Markov processes via reverse-time sequential Monte Carlo
- Inference on the effect of non homogeneous inputs in Ornstein-Uhlenbeck neuronal modeling
- Estimation of the killing rate parameter in a diffusion model
- A new firing paradigm for integrate and fire stochastic neuronal models
- A copula-based method to build diffusion models with prescribed marginal and serial dependence
- Stochastic integrate and fire models: a review on mathematical methods and their applications
- How sample paths of leaky integrate-and-fire models are influenced by the presence of a firing threshold
- Boundary crossing random walks, clinical trials, and multinomial sequential estimation
- On decomposition of the last passage time of diffusions
- Bayesian parameter inference for partially observed stopped processes
This page was built for publication: Estimation in discretely observed diffusions killed at a threshold
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4923054)
