Setting Control Limits Using Bayesian Methods When Most Observations Are Below the Limit of Quantitation Steven Novick, Harry Yang, and Wei Zhao May 18,

Slides:



Advertisements
Similar presentations
Estimation of Means and Proportions
Advertisements

Copyright © Cengage Learning. All rights reserved.
458 Fitting models to data – II (The Basics of Maximum Likelihood Estimation) Fish 458, Lecture 9.
Chapter 7 Sampling and Sampling Distributions
Point and Confidence Interval Estimation of a Population Proportion, p
Basics of Statistical Estimation. Learning Probabilities: Classical Approach Simplest case: Flipping a thumbtack tails heads True probability  is unknown.
Results 2 (cont’d) c) Long term observational data on the duration of effective response Observational data on n=50 has EVSI = £867 d) Collect data on.
Statistical inference form observational data Parameter estimation: Method of moments Use the data you have to calculate first and second moment To fit.
Class notes for ISE 201 San Jose State University
CONFIDENCE INTERVALS What is the Purpose of a Confidence Interval?
Equivalence margins to assess parallelism between 4PL curves
Inferences About Process Quality
Bayesian Analysis of Dose-Response Calibration Curves Bahman Shafii William J. Price Statistical Programs College of Agricultural and Life Sciences University.
T T Population Variance Confidence Intervals Purpose Allows the analyst to analyze the population confidence interval for the variance.
Oscar Go, Areti Manola, Jyh-Ming Shoung and Stan Altan
Generalized Linear Models
Bootstrapping applied to t-tests
1 1 Slide Statistical Inference n We have used probability to model the uncertainty observed in real life situations. n We can also the tools of probability.
1 SAMPLE MEAN and its distribution. 2 CENTRAL LIMIT THEOREM: If sufficiently large sample is taken from population with any distribution with mean  and.
Estimation in Sampling!? Chapter 7 – Statistical Problem Solving in Geography.
1 SMU EMIS 7364 NTU TO-570-N Inferences About Process Quality Updated: 2/3/04 Statistical Quality Control Dr. Jerrell T. Stracener, SAE Fellow.
Biostatistics Class 3 Discrete Probability Distributions 2/8/2000.
1 Chapter 1: Introduction to Design of Experiments 1.1 Review of Basic Statistical Concepts (Optional) 1.2 Introduction to Experimental Design 1.3 Completely.
Exploratory Data Analysis Observations of a single variable.
1 Since everything is a reflection of our minds, everything can be changed by our minds.
- 1 - Bayesian inference of binomial problem Estimating a probability from binomial data –Objective is to estimate unknown proportion (or probability of.
Limits to Statistical Theory Bootstrap analysis ESM April 2006.
Statistics 300: Elementary Statistics Sections 7-2, 7-3, 7-4, 7-5.
Quality control & Statistics. Definition: it is the science of gathering, analyzing, interpreting and representing data. Example: introduction a new test.
The generalization of Bayes for continuous densities is that we have some density f(y|  ) where y and  are vectors of data and parameters with  being.
Bayesian Travel Time Reliability
Sampling and estimation Petter Mostad
Statistics for Engineer. Statistics  Deals with  Collection  Presentation  Analysis and use of data to make decision  Solve problems and design.
Exact PK Equivalence for a bridging study Steven Novick, Harry Yang (MedImmune) and Xiang Zhang (NC State) NCB, October 2015.
Doing the Right Thing! … statistically speaking...
Statistical NLP: Lecture 4 Mathematical Foundations I: Probability Theory (Ch2)
Statistical Inference for the Mean Objectives: (Chapter 8&9, DeCoursey) -To understand the terms variance and standard error of a sample mean, Null Hypothesis,
A correction on notation (Thanks Emma and Melissa)
Sullivan – Fundamentals of Statistics – 2 nd Edition – Chapter 9 Section 4 – Slide 1 of 11 Chapter 9 Section 4 Putting It All Together: Which Procedure.
Dr. Justin Bateh. Point of Estimate the value of a single sample statistics, such as the sample mean (or the average of the sample data). Confidence Interval.
Multilevel modelling: general ideas and uses
Richard K Burdick Elion Labs MBSW Meetings May 2016
Applications of Microbiolgical Data
MCMC Stopping and Variance Estimation: Idea here is to first use multiple Chains from different initial conditions to determine a burn-in period so the.
Chapter 4. Inference about Process Quality
Figure Legend: From: Bayesian inference for psychometric functions
Al-Imam Mohammad Ibn Saud University Large-Sample Estimation Theory
Hypothesis Testing and Confidence Intervals (Part 1): Using the Standard Normal Lecture 8 Justin Kern October 10 and 12, 2017.
Generalized Linear Models
CPSC 531: System Modeling and Simulation
Chapter 7: Sampling Distributions
Combining Random Variables
Lecture 4 1 Probability (90 min.)
Statistical Methods Carey Williamson Department of Computer Science
Goodness-of-Fit Tests
CONCEPTS OF ESTIMATION
More about Posterior Distributions
Review: What influences confidence intervals?
Discrete Event Simulation - 4
Putting It All Together: Which Method Do I Use?
Statistical NLP: Lecture 4
Ch13 Empirical Methods.
PSY 626: Bayesian Statistics for Psychological Science
Lecture 4 1 Probability Definition, Bayes’ theorem, probability densities and their properties, catalogue of pdfs, Monte Carlo 2 Statistical tests general.
Carey Williamson Department of Computer Science University of Calgary
What are their purposes? What kinds?
Lecture 4 1 Probability Definition, Bayes’ theorem, probability densities and their properties, catalogue of pdfs, Monte Carlo 2 Statistical tests general.
CS639: Data Management for Data Science
Jung-Ying Tzeng, Daowen Zhang  The American Journal of Human Genetics 
Classical regression review
Presentation transcript:

Setting Control Limits Using Bayesian Methods When Most Observations Are Below the Limit of Quantitation Steven Novick, Harry Yang, and Wei Zhao May 18, 2016 MBSW 1

Manuscript submitted PDA Journal of Pharmaceutical Science and Technology Awaiting decision… 2

Aseptic environment regulations 2004: FDA Guidance for industry. Sterile Drug Products Produced by Aseptic Processing — Current Good Manufacturing Practice 2008: EU Guidelines to Good Manufacturing Practice Medicinal Products for Human and Veterinary Use -- Annex 1 Manufacture of Sterile Medicinal Products (corrected version) 2013: USP "Microbiological Control and Monitoring of Aseptic Processing Environments“ 3

Purpose of environmental monitoring program Oversight for microbiological cleanliness of manufacturing operation Document the state of control of the facility 4

Data collection for surface sampling Surfaces of equipment may contain microbiological contaminants. For a particular testing occasion, several swabs are taken and assayed on a piece of equipment. Testing is performed over time 5 Test 1 Test 2 Test I …

Key to the success Establishment of alert and action control limits. “[…] usually at a distance of ±3 standard deviations […] from the […] mean.” 6

Some agreement in EM literature Let Y = microbial assay response (from a swab) Step 1: Model the data with a distribution Step 2: Create control limits from quantiles – Alert limits: upper 95% quantile of Y – Action limits: upper 99% quantile of Y Many Y values < limit of quantitation (LOQ) 7

Literature 2003: Christensen, et. al. “Environmental monitoring based on a hierarchical Poisson-Gamma model”, J. Qual Technol 2004: Hoffman, D. “Negative binomial control limits for count data with extra-Poisson variation”, Pharmaceutical Statistics. 2013: Yang, et. al. “Environmental Monitoring: Setting Alert and Action Limits Based on a Zero- Inflated Model”, PDA J Pharm Sci and Tech 8

9 Some authors set Y < LOQ to Y = 0. Many Y values < limit of quantitation (LOQ) Negative Binomial = Gamma-Poisson Y ~ Poisson( i ) i ~ gamma( ,  ) Or zero-inflated NB LOQ

10 When Y values are set to 0, Normal distribution not appropriate Mean +/- 3SD = (-13, 21) LOQ Use a counting distribution? Log-normal not appropriate (deal with 0s in the data)..or is it?

Tobit likelihood (Tobin, 1958) 11 Observed responses Left-censored responses

12 LOQ

Data collection for surface sampling Testing is performed over time with sub-sampling Suggesting: two variance components (2VC) – Testing occasion – Swab within testing occasion 13 Test 1 Test 2 Test I …

Tobit likelihood for 2VC 14 Observed responses Left-censored responses Integrate over this

Go Bayes! Software: STAN via rstan Weakly informative priors for ( ,  T,  e ) 4 independent MCMC chains – Burnin = 20,000 – Thinning = 25 – Posterior draws after thinning = 10,000 Total posterior draws = 40,000 – Effective sample sizes all > 10,000 15

Stan model pseudo-code 16 Integrate over this Likelihood for observed responses Likelihood for left-censored responses

Sample from posterior distribution 17

18 Example data I =194 testing occasions 1-16 swabs/test. ~97.5% of Values < LOQ = 6  g/25cm 2

19

Alert/Action limits Lower 95% credible limit of quantiles 95%-ile = 2.6 < LOQ 99%-ile = 6.9 (just barely above LOQ) 99.5%-ile = 9.4 (maybe…) 20 Action Limit Alert Limit

97.5% of Values < LOQ ? 21

22 Conditional distribution 95%-ile = 18 99%-ile = %-ile = 35 Lower 95% credible limit of conditional quantiles

So much data! Do we really need two variance components? 23

Model log(Y ij ) ~ N(Mean= , SD=  Total ) ? 24

25

26 2VC 1VC 2VC 1VC 95%-ile = %-ile = %-ile = 35 39

Will this hold true with massive left-censoring? Short answer: Yes Long answer: Yes, but… 27

Simulations: 1VC Generally ok Coverage for AL may be inadequate when  T is large. Too confident. Better for situation with small  T. 28

Simulations: 2VC Generally ok. When (% Y < LOQ) is very large, # test occasions and/or # swabs/test is small, not enough data to support the model. Good for situations with enough data to provide estimate for  T and  e. 29

Summary Tobit likelihood: models observed and left-censored observations. Bayes: useful for calculating lower 95% credible interval of alert/action limits. 1VC may be adequate for some EM data (when  T ) is small. 2VC works well when the data can support the model (i.e., there must be enough Y  LOQ). 30

Possible Extensions For discrete data, instead of zero-inflated NB, apply Tobit likelihood to NB. For discrete data, model components of variability through the mean parameter. 31

Thank you! 32