updated course for r&d practical statistical tools for ... · practical statistical tools for...
TRANSCRIPT
SPEAKERS:
Dr Christopher BurgessBurgess Analytical Consultancy
Dr Joachim ErmerSanofi, Germany
23 - 24 June 2016, Heidelberg, Germany
Practical Statistical Tools for Analytical Laboratories
Updated Course for R&D and QC Laboratories
Performance Evaluation and Monitoring for compliant Analytical Procedures and Processes
1,
21,
,
( )
( 1 )( 1)
where = 1,...r outliers
is the 100 percentage point of the distribution
with degrees of freedom and 12( 1)
n i pi
n i p
p
t n i
n i t n i
it p t
pn i
ν
λ
αν
− −
− −
−=
− − + − +
= − − +
wa/vers1/0411.2015 This education course is recognised for the ECA GMP Certification Programme „Certified Quality Control Manager“. Please find details at www.gmp-certification.eu
LEARNING OBJECTIVES:
� Participants should gain an understanding of – Basic statistical fundamentals – Distribution of data and its parameters – Accuracy and precision – Variability and precision levels – Reportable result – Linear and non-linear models – Performance requirements for analytical
procedures � Participants will be shown how to
– apply statistical principles scientifically and pragmatically in their day-to-day business – use statistical simulations – optimise the reportable result for minimum
variability – trend data – perform Design of Experiments (DoE) – compare data and methods – establish reliable Reporting/Quantitation Limits – apply statistical tools for analytical lifecycle
management
Objectives
Statistical calculations and tools are applied extensively in pharmaceutical analysis including:
� Method development and validation � Transfer of analytical procedures � Setting or verification of specification limits � Data evaluation, comparison and trending
The ICH Q10 Guideline “Pharmaceutical Quality System”, the FDA Guidances on Process Validation and Methods Validation require monitoring of “process performance and product quality” and “Trend analysis on method per-formance” throughout the product lifecycle. Hence the appropriate use of statistical trending and evaluation tools has become mandatory.
Consequently, a thorough understanding of statistical fundamentals is essential in order to be able to select parameters and test methods that are ‘fit for purpose’.
Do you speak statistics?In addition, such an understanding facilitates the com-munication with other technical and regulatory functions applying statistical tools in order to ensure an overall consistent approach.
Background
The course will provide the participants with recommen-dations, tools and examples to apply scientifically and pragmatically sound statistical principles to their day-to-day business as well as to meet future challenges de-scribed above.
The relevance of such statistical tools is also increasingly recognised by the Compendia, as reflected, for example, in the USP General Information Chapter <1010> “Inter-pretation and treatment of analytical data” and the re-cently introduced <1033> “Biological assay validation” together with USP Medicines Compendium, <10> “As-sessing Validation Parameters for Reference and Accept-able Procedures”.
Statistical tools are needed, for example, to evaluate:
� Distribution of data and its parameters � How to detect outliers and trends? � How to establish the total variability of the method? � How to identify method parameters that must be controlled?
� Method performance and specification limits – Which accuracy and precision is needed to achieve
an acceptable risk of OOS results? – Scientifically based justification and optimisation of
the reportable result (single or average?) – What are the requirements for impurity methods?
� Comparison of methods and data � What are the requirements for calibration models? � How to optimise the number of calibration replicates on a scientific basis?
A brief discussion of supporting software tools (e.g. Excel, Minitab, JMP) to facilitate the generation of statisti-cal information in a consistent manner will be undertak-en. One of the main features of this new course is the balance of presentations and more than five hours of practical exercise workshops which will allow partici-pants to gain ‘hands on’ practical experience in applying the statistical methods described. By means of statistical simulation tools, the participants will gain intuitive un-derstanding of the consequences of appropriate and inappropriate performance parameters, for example the relationship between precision and OOS results.
For this reason, the course is limited to 30 participants so that individual attention and support can be given. In order to fully benefit from the workshops, attendees should preferably bring a notebook with Excel® 2007 or later.
Target Audience
This best practice oriented course is designed for analyti-cal laboratory managers and their colleagues charged with the day to day management and evaluation of labo-ratory data throughout the lifecycle, i.e. in method devel-opment, validation, transfer, specification setting, batch release and stability, continuous performance verifica-tion and change control.
QA, manufacturing and regulatory affairs professionals will benefit from participation by gaining a clear under-standing of the statistical fundamentals which are impor-tant to implement scientifically sound and pragmatic tools to conform to GMP and regulatory requirements for example Product Quality Review.
Moderator
Dr Christopher Burgess, Burgess Analytical Consultancy Ltd., UK
Practical Statistical Tools for Analytical Laboratories 23 - 24 June 2016, Heidelberg, Germany
Programme
(Normal) Distribution of Data and its Parameters � Data shape and its importance � Characterisation of distributions (Location and Dispersion)
� Probability considerations; all measurements are subject to error
� Populations and samples � Confidence intervals � What is an outlier? � Error of the error
WORKSHOP I: Understanding the Variability (Statistical Simulations)
� Range of expected data � Variability of standard deviations � Number of data and reliability of calculated standard deviations
Calculation and Evaluation of Precision Levels � System precision, repeatability, intermediate precision, reproducibility
� ANOVA: Identification of relevant variance compo-nents from injection, measurement, sample prepara-tion, intermediate conditions
� Total variability: precision of the reportable result and its optimisation
� Optimisation of single-point calibration � Relationship between precision and probability of OOS results
� Practically relevant acceptance criteria for precision
WORKSHOP II: Optimisation of Variability
� Statistically based format of the reportable result (single or average)
� Number of determinations for various levels � Probability of results outside established limits
Trending of Data � Why trend? � Evaluation; do we expect a trend or not? � Statistical Process Control principles � Types of Control charts and their application � Application to stability testing
WORKSHOP III: Control Charts & Trending
� Interactive workshop based on supplied real data sets for interpretation
� Use of Minitab for control charting � Team working on evaluation and interpretation of trend data
Design of Experiments (DoE) Principles and the Investigation of Robustness
� Why do we need Design of Experiments? � Basics of DoE � What is robustness? � Worked example of DoE to the investigation of robustness
Comparison of Data & Accuracy � Significance (F- and t-test) and equivalence tests � Statistical significance and practical relevance � Differences caused by random variability: observed and true bias
� Applications in transfer and cross-validation
WORKSHOP IV: Comparison of Data (Statistical Simulations)
� Significance and equivalence tests: influence of number of data and series
� Differences between means and variability
Calibration Models, Linear and non-Linear � What is a calibration model? � What is the difference between linear and non-linear models?
� The principle of least squares and why it is important � Applying the principles to linear and non-linear models
WORKSHOP V: Linearity (Statistical Simulations)
� Regression range and evaluation of the intercept � Extrapolation effects
Performance Requirements for Impurity Procedures � Concentration dependence of precision (Horwitz relation)
� Detection and Quantitation Limits
WORKSHOP VI: Quantitation Limit
� Basics to consider for calculation from linearity � How to determine appropriately from precision
Summary Workshop & Discussion: Appropriate Choice of Tests/Calculations
� Practical objectives and data sets are provided � The participants will discuss and define appropriate tests and parameters to be calculated
� The participants are given the calculation results and are asked to make an evaluation
� The defined tests and results are discussed in the audience
Speakers
Dr Christopher BurgessBurgess Analytical Consultancy, UKHe is a Chartered Chemist and has more than 38 years experience in the pharma-ceutical industry initially with Glaxo in Quality Assurance and Analytical R&D and then 20 years in international consul-
tancy. He is a “Qualified Person” in the European Union and a member of the European QP Association advisory board. He has been appointed to the United States Phar-macopoeia’s Council of Experts 2010 to 2015 and is a vis-iting professor of the University of Strathclyde’s School of Pharmacy and Biomedical Sciences (SIPBS). In addition, he is the chairman of the ECA Analytical Quality Control Group and a member of the Executive committee of Eu-ropean Compliance Academy. He is also a member of the USP Expert Panel on Validation and Verification en-trusted to revise General Chapters <1224>, <1225> and <1226>.
Dr Joachim ErmerSanofi, Frankfurt, GermanyHead of Quality Control Services Chemis-try, Sanofi-Aventis Deutschland GmbH, Frankfurt, Germany, and Global Reference Standards Coordinator of Sanofi. He stud-ied biochemistry at University of Halle
and has more than 25 years experience in pharmaceuti-cal analytics including development products, global re-sponsibilities as Director of Analytical Processes and Technology, and Head of Quality Control. He is member of the USP Expert Panel on Validation and Verification and of the EFPIA Quality by Design working group.
Literature
Participants of this Course can pur-chase the new Edition of Dr Ermer’s book “Method Validation in Pharma-ceutical Analysis” (Wiley VCH, Wein-heim 2014, ISBN: 978-3-527-33563-3) at a 15% reduced price! You will receive the order form for this book at the course.
Social Event
On Thursday, 23 June 2016, you are cordially invited to a social event. This is an excellent oppor-tunity to share your experiences with colleagues from other com-panies in a relaxed atmosphere.
Date
Thursday, 23 June 2016, 09.00 - 18.00 h (Registration and coffee 08.30 – 09.00 h)Friday, 24 June 2016, 08.30 - 16.00 h
Venue
NH Hotel HeidelbergBergheimer Strasse 9169115 Heidelberg, GermanyPhone +49 (0) 6221 1327 0Fax +49 (0) 6221 1327 100
Fees (per delegate plus VAT)
ECA Members € 1,490APIC Members € 1,590Non-ECA Members € 1,690EU GMP Inspectorates € 845
The conference fee is payable in advance after receipt of invoice and includes conference documentation, dinner on the first day, lunch on both days and all refreshments. VAT is reclaimable.
Accommodation
CONCEPT HEIDELBERG has reserved a limited number of rooms in the conference hotel.
You will receive a room reservation form when you have registered for the event. Please use this form for your room reservation to receive the specially negotiated rate for the duration of your stay.
Reservation should be made directly with the hotel. Early reservation is recommended.
Registration
Via the attached reservation form, by e-mail or by fax message. Or you register online atwww.gmp-compliance.org.
Conference Language
The official conference language will be English.
Organisation and Contact
ECA has entrusted Concept Heidelberg with the organisation of this event.
CONCEPT HEIDELBERGP.O.Box 10 17 64 69007 Heidelberg, Germany, Phone +49 (0)6221/84 44-0Fax +49 (0)62 21/84 44 [email protected]
For questions regarding content:Dr Günter Brendelberger (Operations Director) at ++49-62 21 / 84 44 40 or at [email protected].
For questions regarding reservation, hotel, organisation etc.:Mr Rouwen Schopka (Organisation Manager) at ++49-62 21 / 84 44 13 or per e-mail at [email protected].
Heidelberg – Optimal Accessibility via Frankfurt
Airport Shuttle Service PCShttp://www.pcs-hd.de/Phone: +49 (0)6221 – 16 46 64, [email protected]
TLS Airport Shuttle Service Heidelbergwww.tls-heidelberg.dePhone +49 (0)6221 77 00 77, [email protected]
Lufthansa Bus Airport Shuttlehttp://www.transcontinental-group.com/en/ frankfurt-airport-shuttlesTel. +49 (0)6152 – 97 69 099, [email protected]
TrainYou can get on the train directly at the airport. Trains leave up to two times per hour and it takes less than one hour to get to Heidelberg. www.bahn.de
Easy Registration
Reservation Form:CONCEPT HEIDELBERGP.O. Box 10 17 6469007 HeidelbergGermany
Reservation Form:+ 49 6221 84 44 34 @ e-mail:
[email protected] Internet:www.gmp-compliance.org
wa/vers1/0411.2015
#
Rese
rvat
ion
Form
(Ple
ase
com
ple
te in
full)
Prac
tica
l Sta
tist
ical
To
ols
for A
nal
ytic
al L
abo
rato
ries
23 -
24 Ju
ne 2
016
, Hei
del
ber
g, G
erm
any
*
Mr
*M
s
Title
, firs
t nam
e, s
urna
me
Co
mp
any
D
epar
tmen
t
Imp
ort
ant:
Ple
ase
ind
icat
e yo
ur c
om
pan
y’s
VA
T ID
Nu
mb
er
P
O N
um
ber
if a
pp
licab
le
Stre
et/P
.O. B
ox
City
Z
ip C
od
e C
oun
try
Pho
ne
Fax
E-M
ail (
ple
ase
fill i
n)
If th
e b
ill-t
o-a
dd
ress
dev
iate
s fr
om
the
spec
ifica
-tio
ns o
n th
e rig
ht, p
leas
e fil
l out
her
e:
C
ON
CEP
T H
EID
ELBE
RG
P.O
. Box
1017
64
Fax
+49
(0) 6
2 21
/84
44 3
4
D
-690
07
Hei
del
ber
g
GER
MA
NY
+
49
6221
84
44 3
4
Gen
eral
term
s an
d c
ond
itio
nsIf
you
cann
ot a
ttend
the
conf
eren
ce y
ou h
ave
two
optio
ns:
1. W
e ar
e ha
ppy
to w
elco
me
a su
bst
itute
col
leag
ue a
t any
tim
e.2.
If y
ou h
ave
to c
ance
l ent
irely
we
mus
t cha
rge
the
follo
win
g pr
oces
sing
fe
es: C
ance
llatio
n -
until
2 w
eeks
prio
r to
the
conf
eren
ce 10
%,
- un
til 1
wee
ks p
rior t
o th
e co
nfer
ence
50
%-
with
in 1
wee
k p
rior t
o th
e co
nfer
ence
100
%.
CO
NC
EPT
HEI
DEL
BERG
rese
rves
the
right
to c
hang
e th
e m
ater
ials
, ins
truc
-to
rs, o
r sp
eake
rs w
ithou
t not
ice
or to
can
cel a
n ev
ent.
If th
e ev
ent m
ust b
e ca
ncel
led
, reg
istr
ants
will
be
notifi
ed a
s so
on a
s po
ssib
le a
nd w
ill re
ceiv
e a
full
refu
nd o
f fee
s p
aid
. CO
NC
EPT
HEI
DEL
BERG
will
not
be
resp
onsi
ble
for
dis
coun
t airf
are
pen
altie
s or
oth
er c
osts
incu
rred
due
to a
can
cella
tion.
Te
rms
of p
aym
ent:
Pay
able
with
out d
educ
tions
with
in 10
day
s af
ter r
ecei
pt
of in
voic
e.
Imp
ort
ant:
Thi
s is
a b
ind
ing
regi
stra
tion
and
ab
ove
fees
are
due
in c
ase
of
canc
ella
tion
or n
on-a
ppea
ranc
e. If
you
can
not t
ake
part
, you
hav
e to
info
rm
us in
writ
ing.
The
can
cella
tion
fee
will
then
be
calc
ulat
ed a
ccor
din
g to
the
poin
t of t
ime
at w
hich
we
rece
ive
your
mes
sage
. In
case
you
do
not a
ppea
r at
the
even
t with
out h
avin
g in
form
ed u
s, y
ou w
ill h
ave
to p
ay th
e fu
ll re
gis-
trat
ion
fee,
eve
n if
you
have
not
mad
e th
e pa
ymen
t yet
. Onl
y af
ter w
e ha
ve
rece
ived
you
r pay
men
t, yo
u ar
e en
title
d to
par
ticip
ate
in th
e co
nfer
ence
(r
ecei
pt o
f pay
men
t will
not
be
confi
rmed
)! (A
s of
Janu
ary
2012
)
Priv
acy
Polic
y: B
y re
gist
erin
g fo
r thi
s ev
ent,
I acc
ept t
he p
roce
ssin
g of
my
Pers
onal
Dat
a. C
once
pt H
eid
elb
erg
will
use
my
dat
a fo
r the
pro
cess
ing
of th
is o
rder
, for
whi
ch I
here
by
dec
lare
to a
gree
that
my
pers
onal
dat
a is
st
ored
and
pro
cess
ed. C
once
pt H
eid
elb
erg
will
onl
y se
nd m
e in
form
atio
n in
rela
tion
with
this
ord
er o
r sim
ilar o
nes.
My
pers
onal
dat
a w
ill n
ot b
e d
iscl
osed
to th
ird p
artie
s (s
ee a
lso
the
priv
acy
polic
y at
http
://w
ww
.gm
p-co
mpl
ianc
e.or
g/ec
a_pr
ivac
y.ht
ml).
I n
ote
that
I ca
n as
k fo
r the
mod
ifica
tion,
cor
rect
ion
or d
elet
ion
of m
y d
ata
at a
ny ti
me
via
the
cont
act f
orm
on
this
web
site
.
#