NONMEM Users Network Archive

Hosted by Cognigen

Taca Training Workshop on Pharmacometric Statistics

From: adrian.dunne
Date: Wed, 31 Jan 2018 15:40:43 -0000





Registration is now open for this 3 day workshop to be held from 16th to
18th October (inclusive) 2018 in Dublin, Ireland.


The aim of this 3 day workshop is to give pharmacometricians a good
understanding of the statistical concepts upon which their work is based and
which are of great importance in everything they do. The emphasis will be on
concepts with an absolute minimum of mathematical details.

Attendees need only have studied statistics at foundation level prior to
taking this course.

The topics covered include;


1) Why use statistics?


2) Probability and statistical inference.


3) Laws of probability and Bayes theorem.


4) Univariate probability distributions - Expected value and variance.


5) Multivariate probability distributions - joint, marginal and conditional
distributions. The covariance matrix. Independence and conditional


6) Modelling, estimation, estimators, sampling distributions, bias,
efficiency, standard error and mean squared error. Consistency.


7) Point and interval estimators. Confidence intervals.


8) Hypothesis testing, null and alternative hypotheses. P-value, Type I and
Type II errors and power.


9) Likelihood inference, maximum likelihood estimator (MLE), likelihood
ratio. BQL and censored data.


10) Invariance of the likelihood ratio and the MLE.


11) The score function, hessian, Fisher information, quadratic approximation
and standard error.


12) Wald confidence intervals and hypothesis tests.


13) Likelihood ratio tests.


14) Profile likelihood, nested models.


15) Model selection, Akaike and Bayesian Information Criteria (AIC & BIC).


16) Maximising the likelihood, Newton's method.


17) Mixed effects models.


18) Estimation of the fixed effects, conditional independence, prior and
posterior distributions.


19) Approximating the integrals, Laplace and first order (FO & FOCE)
approximations, numerical quadrature.


20) The Expectation Maximisation (EM) algorithm.


21) MU-Modelling, Iterative Two Stage (ITS)


22) Monte Carlo EM (MCEM), Importance Sampling, Direct Sampling, SAEM,
Markov Chain Monte Carlo (MCMC).


23) Estimating the random effects, empirical bayes estimates (EBE) and


24) Minimum Sufficiency, asymptotic properties of the MLE, efficiency, the
Cramer-Rao Lower Bound (CRLB), consistency, normality.


25) Robustness of the MLE, the Kullback-Liebler distance. Quasi likelihood
and the robust or sandwich variance estimator.



For further details and to register please go to our website


Feedback from previous attendees is also available on our website.


Early registration is advised because the number of places is limited.


Adrian Dunne


Received on Wed Jan 31 2018 - 10:40:43 EST

The NONMEM Users Network is maintained by ICON plc. Requests to subscribe to the network should be sent to:

Once subscribed, you may contribute to the discussion by emailing: