statistical methods in clinical trials continuous data
TRANSCRIPT
![Page 1: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/1.jpg)
Statistical Methods in Clinical Trials
Continuous Data
![Page 2: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/2.jpg)
Types of Data
ContinuousBlood pressureTime to event
Ordered CategoricalPain level
DiscreteNo of relapses
Categoricalsex
quantitative qualitative
![Page 3: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/3.jpg)
Types of data analysis (Inference)
ParametricVs
Non parametric
FrequentistVs
Bayesian
Model basedVs
Data driven
![Page 4: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/4.jpg)
Continuous Data
Part I Classical InferencePart II Bayesian Inference
![Page 5: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/5.jpg)
Part IClassical Inference
1. One sample
2. Paired data
3. Two samples
4. Many samples» One way anova» Two way anova» Ancova
![Page 6: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/6.jpg)
One sample
From a population of patients we draw a sample of size n of patients and measure some response on each of these. We want to test whether the average response in this population is equal to (or is larger or smaller than) some predefined value μ0 (e.g. the corresponding value in the healthy population).
![Page 7: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/7.jpg)
Estimation• Assume is a sample (i.i.d) of
size n from some distribution F with mean μ and standard deviation σ. Then
and
• Are (i) unbiased and (ii) consistent estimators of μ and σ² i.e.
(i)
(ii) (LLN)
![Page 8: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/8.jpg)
Estimation in general
• The maximum likelihood method• The moment method• Uniformly Minimum Variance Unbiased
estimators• Least squares • etc
![Page 9: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/9.jpg)
Hypothesis testing
We can e.g. test the null hypothesis
using the test statistic
when n is large, T follows, under the null hypothesis, the standard normal distribution (CLT).
against
![Page 10: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/10.jpg)
Hypothesis testing
For moderate values of n assuming
follow a normal distribution, then
follows, under the null hypothesis, the t (student) distribution with (n-1) degrees of freedom.
![Page 11: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/11.jpg)
The true distribution among the patients(exponential with mean 0.5.)
The distribution of the average whenn is large
![Page 12: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/12.jpg)
Confidence intervals• A (1-α)100% confidence interval for μ has
the form
(i)
(ii)
when n is large
when n moderate but sample normally distributed.
A hypothesis (or a confidence interval) can be one sided or two sided
![Page 13: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/13.jpg)
95% confidence interval
1-α=0.95
The normaldistribution
The tdistribution
1-α=0.95
![Page 14: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/14.jpg)
Correspondence TheoremHypothesis testing and confidence intervals
are two sides of the same coin!
Parameter value according to null hypothesis not included in
confidence interval (α)
Reject null hypothesis (α)
![Page 15: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/15.jpg)
Paired data
• Sometimes we measure a response at baseline and at the end of the treatment. A suitable analysis can be to consider the endpoint changes from baseline.
• and to use the (one sample) test statistic
![Page 16: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/16.jpg)
Two independent samples
From two populations/distributions we draw two samples of sizes n1 and n2 of patients and measure some response on each of these. We want to test whether the average responses, μ1 and μ2, in these two populations are equal. The population variances are denoted by σ1² and σ2² respectively.
H (null)0 H (alternative)A
1 2 1 2
1 2
1 2
1 2
1 2
![Page 17: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/17.jpg)
Two samples (continued)
• When both sample sizes are large we can use the central limit theorem according to which the test statistic below follows the standard normal distribution
• When the sample sizes are moderate but normal with equal variances we can use the t-statistic (having n1+n2-2 d.f.) and the pooled variance.
• The remaining case can be handled using a method known as Satterwaite’s confidence intervals.
![Page 18: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/18.jpg)
Many samplesOne way analysis of variance
• Here we want to compare several (k) groups (treatments) with respect to the average response in each group. The following model is assumed
![Page 19: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/19.jpg)
Anova1
![Page 20: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/20.jpg)
Anova1 continued
• The deviation of an individual observation from the overall mean can be described by
• The null hypothesis and the alternative hypothesis can be formulated as
SST/SST SSA/SSB SSE/SSW
![Page 21: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/21.jpg)
Anova 1 continued
• Manipulating these gives:
MSA
• When the null hypothesis is false we expect the ratio MSA/MSE to be large. To calculate exact significance levels we use the fact that it F-distributed with (k-1,N-k) d.f.
MSE MSA
![Page 22: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/22.jpg)
Anova table
Source of variation
Sum of squares
d.f. Mean squares
F/p-value
Treatment SSA K-1 MSA F0=MSA/MSE /p
Error SSE N-k MSE
Total SST N-1
![Page 23: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/23.jpg)
• Example: 3 groups with the same mean 20 and the same standard deviation 2. We reject for large values of F0.
Source of variation
Sum of squares
d.f. Mean squares
F0/p-value
Treatment 9.56 2 4.78 1.22/ 0.29
Error 4671.1 1197 3.9
Total 4680.65 1199
F is F-distributed and F0 the value of MSA/MSE
We cannot reject
![Page 24: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/24.jpg)
• Example: 3 groups with means 20, 20 and 20.5 and the same standard deviation 3.
Source of variation
Sum of squares
d.f. Mean squares
F/p-value
Treatment
59.4 2 29.7 3.25/ 0.039
Error 10942.8 1197 9.14
Total 11002.3 1199We can reject
![Page 25: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/25.jpg)
We can reject
![Page 26: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/26.jpg)
Multiple comparisons
• When we reject the null hypothesis we only know that the groups are not equal but some of them might still be. To find out more we have to consider all the pairwise comparisons between the groups. With k groups this gives m=k(k-1)/2 such comparisons. How do we do this and still have a reasonable overall significance level? The simplest way to deal with this is using Bonferroni’s inequality. This implies that when performing m tests if each test is at the 1-α/m level then the tests taken simultaneously will be on the 1- α level. We will deal with problem in detail later on.
![Page 27: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/27.jpg)
Two way anova
• Here we assume that individuals can differ with respect to two factors (two drugs, treatment and centre). The following model is usually suitable for this situation
• As before the deviation of an individual observation from the overall average can be decomposed into terms related to the effects of treatment, center, treatment by center as well as to a pure random component.
![Page 28: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/28.jpg)
Anova2
• We use a similar notation as before
![Page 29: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/29.jpg)
• Tests of treatment effect, center effect or treatment by center interaction can be performed by using the appropriate ratio between mean square values.
![Page 30: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/30.jpg)
Anova2
• As an example assume we want to test if there is a treatment effect:
• This can be tested using the test statistic
• Which has under the null hypothesis an F distribution with (a-1) and ab(n-1) degrees of freedom.
• The various tests are summarized in the following table
![Page 31: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/31.jpg)
Two-way anova
![Page 32: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/32.jpg)
Analysis of covariance
• Here we assume that individuals can differ with respect baseline values. It is sometimes desirable to adjust the model for the endpoint measures Y so baseline values X are taken into account. The following model can then be useful
The analysis uses an F distribution based onMean sums of squares (cf. p.319)
![Page 33: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/33.jpg)
33
Various forms of models and relation between them
LM: Assumptions:
1. independence,
2. normality,
3. constant parameters
GLM: assumption 2) Exponential family
LMM: Assumptions 1) and 3) are modified
GLMM: Assumption 2) Exponential family and assumptions 1) and 3) are modified
Repeated measures: Assumptions 1) and 3) are modified
Longitudinal dataMaximum likelihood
Classical statistics (Observations are random, parameters are unknown constants)
Bayesian statistics, parameters are random
LM - Linear model
GLM - Generalised linear model
LMM - Linear mixed model
GLMM - Generalised linear mixed model
Non-linear models
Mixed models, both random and constant parameters
![Page 34: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/34.jpg)
34
The Linear Mixed-effects Model
• The linear mixed effects model is quite flexible and does not need balance, independence etc. Usually some version of maximum l likelihood is used for the inference
Average evolution Subject specific
![Page 35: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/35.jpg)
Why should we use multilevel models?
Sometimes:
single level
models can be
seriously
misleading!
![Page 36: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/36.jpg)
Intake (S5)
Exit(S7)
Source: Snijders & Bosker (1999: 28)
Conclusion based on student-level data only: Schools have adverse effect on students
![Page 37: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/37.jpg)
Intake (S5)
Exit (S7)
Source: Snijders & Bosker (1999: 28)
S1
S2
S3
S4S5
S6
S1
S2
S3
S4S5
S6
Mean of school 1
Using school-level data only: schools have adverse effect on students
![Page 38: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/38.jpg)
Intake (S5)
Exit (S7)
Source: Snijders & Bosker (1999: 28)
S1
S2
S3
S4S5
S6
S1
S2
S3
S4S5
S6
Using both student-level & school-level data: Stronger students at entry score higher at exit
![Page 39: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/39.jpg)
Part IIBayesian Inference
![Page 40: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/40.jpg)
![Page 41: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/41.jpg)
What is a probability?
1. the limit of a relative frequencyProblem: Not all events all repeatable!
2. the degree of plausibility Or of beliefProblem: subjective?
P=1/6P=?
![Page 42: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/42.jpg)
Bayes in brief
• Bayes’ conclusions were accepted by Laplace in 1781
• Rediscovered by Condorcet, and remained unchallenged until
• Boole questioned them. • Since then Bayes' techniques have
been subject to controversy.
![Page 43: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/43.jpg)
Is Classical Inference Really Classical?• Only in the sense that it started
a realtively long time ago with Fisher around 1920.
• Bayesian Statistics is even more classical since it was dominating until then.
• Classical inference was introduced as a way to introduce objectivity in the scientific process.
![Page 44: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/44.jpg)
Simplified scientific Process
1. A theory or a hypothesis needs to be tested
2. We perform an experience and obtain some data
3. Are our data in agreement with our theory?
4. If the answer to the above question is no, we reject the theory. Otherwise we cannot reject it!
![Page 45: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/45.jpg)
Falsifiability (or refutability or testability) is the logical possibility that an assertion can be shown false by an observation or a physical experiment.
For example, "all men are mortal" is unfalsifiable, since no amount of observation could ever demonstrate its falsehood. "All men are immortal," by contrast, is falsifiable, by the presentation of just one dead man
A white mute swan, common to Eurasia and North America. Two black swans, native to Australia
![Page 46: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/46.jpg)
Classical Paradigmvs
The Bayesian paradigm
• The classical paradigm is based on the consideration of
P[ Data | Theory ] (1)• How likely is the data if the theory was
to be true?
![Page 47: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/47.jpg)
Classical vs Bayesian (cont’d)
• The Bayesian paradigm is based on the consideration of
P[ Theory | Data](2)• How much support or belief is there in the
theory given the data?
![Page 48: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/48.jpg)
Bayes’ Formula
Where
T = Theory
and
D = Data
Simple formula with many interesting implications.
D] P[
] T P[ T] | D P[ D] | T P[
States that
(3)
![Page 49: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/49.jpg)
Implications of Bayes’ Formula
1. (1) and (2) are not equivalent.
2. To work out (2) we have to estimate P[ T ] i.e. we need to put a probability on our belief in the theory we are testing.
3. We cannot make P[ T ] disappear. (Similar to the uncertainty principle in quantum mechanics?)
![Page 50: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/50.jpg)
• Some toxin is associated with certain symptoms. denotes the toxin level in patients having the symptoms and 0 the toxin level in healthy individuals. We want to test if there is a difference. A test can be based on a sample of size n through
Example: p-values
![Page 51: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/51.jpg)
Under the null hypothesis
H0: = 0,
z is an observation from a t-distribution with n-1 degrees of freedom.
If, moreover, the p-value is less than 0.05 it is then customary to consider the result as significant, i.e. we reject the null hypothesis.
We return to this in moment!
![Page 52: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/52.jpg)
Preliminaries
• Consider two Hypothesis H0 and H1
D] P[
] H P[ ]H | D P[ D] | H P[ 00
0
D] P[
] H P[ ]H | D P[ D] | H P[ 11
1
![Page 53: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/53.jpg)
• We consider the odds ratio between the two
]H | D P[
]H | D P[
] H P[
] H P[
D] | H P[
D] | H P[
1
0
1
0
1
0
Odds ratio = prior odds x likelihood ratio
New old Bayes factor
![Page 54: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/54.jpg)
Result
1
0
00 BF] H P[
] H P[-11 D] | H P[
]H | P[D
]H | P[D BF
1
0
where
![Page 55: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/55.jpg)
Back to the t-test
P. M. Lee Bayesian Statistics: An Introduction
2nd Ed. London: Arnold, p. 131 (1997)
shows that in the case of the t-est and under quite
general conditions:
2
2
BFz
e
![Page 56: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/56.jpg)
Consequences
• Assume that there is no agreement on the effect of the toxin so we take P(H0)=0.5. Then:
1
2
z-
1
2
z-0
2
2 e1
e
11 D] | P[H
![Page 57: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/57.jpg)
• Assume further that the value of z in the experiment turns out to be 2. Since this leads to a p-value of 0.044 we conclude that the result is significant at the 0.05 level. Setting z=2 in the formula above leads to:
12.0e1 D] | P[H
1
2
2-
0
2
![Page 58: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/58.jpg)
Z=2P
[ H
0| D
]
P[ H0]
![Page 59: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/59.jpg)
P[
H0|
D]
P[ H0]
![Page 60: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/60.jpg)
Conclusions
• By introducing the element of degree of belief about a theory, we arrive at conclusions that do not agree with those obtained using the frequentist approach, i.e. prior knowledge matters
• Prior knowledge is part of the Bayesian approach.
![Page 61: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/61.jpg)
Backup slidesBayesian Analysis in Clinical Trials
![Page 62: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/62.jpg)
• The Advantages:– Formal system for incorporating existing information– Natural approach to inference– Generally more efficient– Well suited for decision making
• The Challenges:– Determining appropriate prior probabilities– Computational complexity– Lack of familiarity– Lack of software tools
Bayesian Framework
![Page 63: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/63.jpg)
What is the difference?
Approach Traditional Bayesian
Question How likely are the trial results given there really is no difference among treatments?
How likely is it that there is a true difference among treatments given the trial data?
Approval based on Pivotal trial (Hypothesis testing)
Weight of evidence (revising beliefs in light of new evidence)
Design Single stage Adaptive
![Page 64: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/64.jpg)
In what settings have Bayesian desings been used?
• Pharmacokinetics• Phase I (CRM)• Phase II (Thall/Simon)• Phase III (Spiegelhalter, Parmar, others)• Meta-analysis• Medical device clinical trials (guidelines
from 2006)
![Page 65: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/65.jpg)
Summary of applications
• Methods for incomplete data• Adaptive designs (including adaptive
sample size)• Confirmatory trials• Evaluating a modified version of an
approaved product• Synthesising data in post market
surveillance
![Page 66: Statistical Methods in Clinical Trials Continuous Data](https://reader035.vdocuments.us/reader035/viewer/2022062308/56649ef25503460f94c03fa6/html5/thumbnails/66.jpg)
1
0
00
1
1
00
0
11
0
00
0
11
0
1
00
1
0
1
0
1
0
BF] H P[
] H P[-11D] | H P[
]H | P[D]H | P[D
] H P[
] H P[-11
C
11
C
C1
C1
CD] | H P[
CD] | H P[CD] | H P[
D] | H P[-1C
D] | H P[]H | P[D
]H | P[D
] H P[
] H P[D] | H P[
]H | P[D
]H | P[D
] H P[
] H P[
D] | H P[
D] | H P[
Proof