Satistical modelling of clinical trials



Similar documents
Maximum Likelihood Estimation

Master s Theory Exam Spring 2006

Pure risk premiums under deductibles

Local classification and local likelihoods

What is Statistics? Lecture 1. Introduction and probability review. Idea of parametric inference

Penalized regression: Introduction

Joint Exam 1/P Sample Exam 1

i=1 In practice, the natural logarithm of the likelihood function, called the log-likelihood function and denoted by

Inference on the parameters of the Weibull distribution using records

Lecture Notes 1. Brief Review of Basic Probability

Homework set 4 - Solutions

ESTIMATION OF CLAIM NUMBERS IN AUTOMOBILE INSURANCE

Exponential Distribution

UNIT I: RANDOM VARIABLES PART- A -TWO MARKS

MATH4427 Notebook 2 Spring MATH4427 Notebook Definitions and Examples Performance Measures for Estimators...

Institute of Actuaries of India Subject CT3 Probability and Mathematical Statistics

SOCIETY OF ACTUARIES/CASUALTY ACTUARIAL SOCIETY EXAM C CONSTRUCTION AND EVALUATION OF ACTUARIAL MODELS EXAM C SAMPLE QUESTIONS

Response variables assume only two values, say Y j = 1 or = 0, called success and failure (spam detection, credit scoring, contracting.

2DI36 Statistics. 2DI36 Part II (Chapter 7 of MR)

How To Solve A Save Problem With Time T

University of Ljubljana Doctoral Programme in Statistics Methodology of Statistical Research Written examination February 14 th, 2014.

Multivariate Normal Distribution

Practice problems for Homework 11 - Point Estimation

Interpreting Kullback-Leibler Divergence with the Neyman-Pearson Lemma

Part 2: One-parameter models

A New Extension of the Exponential Distribution

CHAPTER 6: Continuous Uniform Distribution: 6.1. Definition: The density function of the continuous random variable X on the interval [A, B] is.

STAT 315: HOW TO CHOOSE A DISTRIBUTION FOR A RANDOM VARIABLE

Linear Classification. Volker Tresp Summer 2015

Exam C, Fall 2006 PRELIMINARY ANSWER KEY

Lecture 8: Gamma regression

Statistics in Retail Finance. Chapter 6: Behavioural models

Mixing internal and external data for managing operational risk

Un point de vue bayésien pour des algorithmes de bandit plus performants

The CUSUM algorithm a small review. Pierre Granjon

A Uniform Asymptotic Estimate for Discounted Aggregate Claims with Subexponential Tails

CHAPTER 2 Estimating Probabilities

Aggregate Loss Models

NUMBER OF ACCIDENTS OR NUMBER OF CLAIMS? AN APPROACH WITH ZERO-INFLATED POISSON MODELS FOR PANEL DATA

Basics of Statistical Machine Learning

LECTURE 16. Readings: Section 5.1. Lecture outline. Random processes Definition of the Bernoulli process Basic properties of the Bernoulli process

STATISTICA Formula Guide: Logistic Regression. Table of Contents

Dynamic Linear Models with R

On the mathematical theory of splitting and Russian roulette

Math 370/408, Spring 2008 Prof. A.J. Hildebrand. Actuarial Exam Practice Problem Set 5 Solutions

Maximum Likelihood Estimation by R

Important Probability Distributions OPRE 6301

Exact Confidence Intervals

Back Analysis of Material Properties

Bayes and Naïve Bayes. cs534-machine Learning

1 Prior Probability and Posterior Probability

The Kelly Betting System for Favorable Games.

From the help desk: Bootstrapped standard errors

Analysis of Reliability and Warranty Claims in Products with Age and Usage Scales

NON-LIFE INSURANCE PRICING USING THE GENERALIZED ADDITIVE MODEL, SMOOTHING SPLINES AND L-CURVES

Bayesian Information Criterion The BIC Of Algebraic geometry

Advanced statistical inference. Suhasini Subba Rao

On Marginal Effects in Semiparametric Censored Regression Models

An Internal Model for Operational Risk Computation

Chapter 4 - Lecture 1 Probability Density Functions and Cumul. Distribution Functions

SAS Software to Fit the Generalized Linear Model

Notes on the Negative Binomial Distribution

MAS2317/3317. Introduction to Bayesian Statistics. More revision material

e.g. arrival of a customer to a service station or breakdown of a component in some system.

INDIRECT INFERENCE (prepared for: The New Palgrave Dictionary of Economics, Second Edition)

STAT 830 Convergence in Distribution

L3: Statistical Modeling with Hadoop

Probability density function : An arbitrary continuous random variable X is similarly described by its probability density function f x = f X

Probabilistic concepts of risk classification in insurance

MAS108 Probability I

Lecture 6: Poisson regression

( ) = 1 x. ! 2x = 2. The region where that joint density is positive is indicated with dotted lines in the graph below. y = x

ACTUARIAL MODELING FOR INSURANCE CLAIM SEVERITY IN MOTOR COMPREHENSIVE POLICY USING INDUSTRIAL STATISTICAL DISTRIBUTIONS

Development Period Observed Payments

Sections 2.11 and 5.8

Chapter 6: Point Estimation. Fall Probability & Statistics

Course 4 Examination Questions And Illustrative Solutions. November 2000

Uncertainty quantification for the family-wise error rate in multivariate copula models

Int. Statistical Inst.: Proc. 58th World Statistical Congress, 2011, Dublin (Session STS040) p.2985

Patients Recruitment Forecast in Clinical Trials

STAT2400 STAT2400 STAT2400 STAT2400 STAT2400 STAT2400 STAT2400 STAT2400&3400 STAT2400&3400 STAT2400&3400 STAT2400&3400 STAT3400 STAT3400

2WB05 Simulation Lecture 8: Generating random variables

Permutation Tests for Comparing Two Populations

Introduction to Probability

Statistics Graduate Courses

Optimal reinsurance with ruin probability target

Example 1: Dear Abby. Stat Camp for the Full-time MBA Program

. (3.3) n Note that supremum (3.2) must occur at one of the observed values x i or to the left of x i.

Sharing Online Advertising Revenue with Consumers

Chapter 6: Multivariate Cointegration Analysis

A Model of Optimum Tariff in Vehicle Fleet Insurance

1. A survey of a group s viewing habits over the last year revealed the following

Transcription:

Sept. 21st, 2012 1/13

Patients recruitment in a multicentric clinical trial : Recruit N f patients via C centres. Typically, N f 300 and C 50. Trial can be very long (several years) and very expensive Previous models based on linear or exponential interpolation = Need for a probabilistic model that takes into account large variability of recruitment rates in different centres 2/13

Centre i opens at timeu i. Γ-model proposed by V. Anisimov (2; 1) : Recruitment processes of centres are independent Poisson processes Recruitment rate of centre i : λ i (unknown) Γ-Poisson model : (λ 1,...,λ C ) iid with Gamma distribution of parametersα and β. p α,β (x) = e βx x α 1 β α Γ(α) 1 3/13

On-going study at time t 1. Observed data is the number of patients recruited by each of C centres : (k 1,...,k C ). Independent but not identically distributed since λ L i Γ(α,β) and k L i P(λ i τ i ). Let τ i = t 1 u i (0 if negative). Estimation of (α,β) maximum likelihood technique : P[N i t 1 = k i ; 1 i C = E [ C (λ i τ i ) k i k i! log-likelihood (up to some constant) : e τ iλ i = C Γ(α+k i ) k i!γ(α) β α τ k i i (β +τ i ) α+k i L C (α,β) = α lnβ lnγ(α)+ 1 C C lnγ(α+k i ) (α+k i ) ln(β +τ i ) (ˆα C, ˆβ C ) = arg max (α,β) Θ L C (α,β) 4/13

As C +, the MLE is consistent and asymptotically normal. Approximated Fischer information matrix : if f(θ, k i,τ i ) = α lnβ lnγ(α)+lnγ(α+k i ) (α+k i ) ln(β +τ i ), then (θ = (α,β)) : and I(θ 0 ) 1 C C I i (θ 0 ) = 1 C C C(ˆθC θ 0 ) L N(0, I(θ 0 ) 1 ) E θ0 [ 2 f(θ 0, k i,τ i ). (I i ) 11 = E α0,β 0 [ψ (1) (α 0 + k i ) (I i ) 12 = (I i ) 21 = 1 β 2 0 ( 1 (I i ) 22 = α ( 0 1 β0 2 1 1+τ i /β 0 1 1+τ i /β 0 ), ), +ψ (1) (α 0 ), 5/13

Bayesian re-estimation of the distribution of λ i : forward distribution of λ i conditionnaly of the information at t 1 : Γ(α+k i,β +τ i ) Overall recruitment rate : Λ = C λ i = C Γ(α+k i,β +τ i ), that can be approximated by a Γ(A, B) distribution by matching moments. In this framework, the (remaining) recruitment time ˆT t 1 has density : Then it is easy to get : P [ˆT Tf E[ˆT x N1 1 p T (x) = Γ(A+N 1) Γ(A)Γ(N 1 ) BA (x + B) N 1+A 6/13

If P [ˆT Tf is too small (say lower than p = 95%), we open M centres. C M Λ = λ i + λ i has the forward distribution Γ(α 0 + k i,β 0 +τ i ) λ i has a Γ(α 0,β 0 ) distribution Here, centres are supposed to open instantaneously, but it is possible to assume they open later in some interval [r i, s i. If P [ˆT Tf is too high, one can close centres to save money. λ i 7/13

Sensitivity parameters (see (3)) : P [ˆT Tf and E[ˆT are calculated with (ˆα C, ˆβ C ) estimated at t 1, instead of real parameters(α 0,β 0 ). The subsequent error is evaluated thanks to sensitivity parameters (e.g. αp [ˆT Tf ). When the overall rate is approximated by a Gamma distribution : althenors m = C α+k i β +τ i et v = C αe[ˆt N α(m v ) m (m v, m )2 β E[ˆT N β(m v ) m (m v. m )2 α+k i (β +τ i ) 2 8/13

Extension of the model Pareto distribution instead of Gamma distribution : p kp,x m (x) = k px kp m 1 x xm x 1 kp opening times u i of centres unkown, but we know the time of first recruitment v i. Then we assume u i uniformly distributed in [0, v i. 9/13

(centres opening times unkown) : N = 610, C = 77, T f = 3 years Study actually finished in 2.31 years. t 1 1 1.5 2 Pareto - parameters (1.19, 1.39) (1.23, 1.30) (1.18, 1.22) Pareto - E[ˆT 2.79 2.30 2.35 Gamma - parameters (1.17, 0.25) (1.08, 0.26) (1.31, 0.33) Gamma - E[ˆT 2.81 2.34 2.36 At t 1 = 1, in the Γ-Poisson model, we get P [ˆT Tf 0.999. Closing the smallest 10 centres steal leads to P [ˆT Tf 0.999. 10/13

Model validation : ν i = number of centres having recruited exactly i patients 14 12 10 8 6 4 2 0 0 5 10 15 20 25 30 FIGURE: Green : real data ; Bleu : Gamma model ; Rouge : Pareto model 11/13

Further research : simultaneaous modelling of screened, randomized and lost patients cost modelling exogenous variables? 12/13

[1 Vladimir V. Anisimov, Using mixed poisson models in patient recruit in multicentre clinical trials, Proceegings of th World Congress on Ingineering (London, United Kingdom), vol. II, 2008. [2 Vladimir V. Anisimov and Valerii V. Fedorov, Modelling, prediction and adaptive adjustment of recruitment in multicentre trials, Stat. Med. 26 (2007), no. 27, 4958 4975. MR MR2405491 [3 Guillaume Mijoule, Stéphanie Savy, and Nicolas Savy, Models for patients recruitment in clinical trials and sensitivity analysis, Statistics in Medicine 31 (2012), no. 16, 1655 1674. 13/13