Basic Statistical Concepts
description
Transcript of Basic Statistical Concepts
Basic Statistical Concepts
Chapter 2 Reading instructions
• 2.1 Introduction: Not very important• 2.2 Uncertainty and probability: Read• 2.3 Bias and variability: Read• 2.4 Confounding and interaction: Read• 2.5 Descriptive and inferential statistics:
Repetition• 2.6 Hypothesis testing and p-values: Read• 2.7 Clinical significance and clinical
equivalence: Read• 2.8 Reproducibility and generalizability: Read
Bias and variability
Bias: Systemtic deviation from the true value
ˆE
Design, Conduct, Analysis, Evaluation
Lots of examples on page 49-51
Bias and variabilityLarger study does not decrease bias
nˆ ; n
Drog X - Placebo
-7 -4-10 mm Hg -7 -4-10
Drog X - Placebo
mm Hg mm Hg
Drog X - Placebo
-7 -4-10
n=40 n=200 N=2000
Distribution of sample means: = population mean
Population mean
bias
Bias and variabilityThere is a multitude of sources for bias
Publication bias
Selection bias
Exposure bias
Detection bias
Analysis bias
Interpretation bias
Positive results tend to be published while negative of inconclusive results tend to not to be published
The outcome is correlated with the exposure. As an example, treatments tends to be prescribed to those thought to benefit from them. Can be controlled by
randomizationDifferences in exposure e.g. compliance to treatment could be associated with the outcome, e.g. patents
with side effects stops taking their treatment
The outcome is observed with different intensity depending no the exposure. Can be controlled by
blinding investigators and patients
Essentially the I error, but also bias caused by model miss specifications and choice of estimation
technique
Strong preconceived views can influence how analysis results are interpreted.
Bias and variability
Amount of difference between observations
True biological:
Temporal:
Measurement error:
Variation between subject due to biological factors (covariates) including the treatment.
Variation over time (and space)Often within subjects.
Related to instruments or observers
Design, Conduct, Analysis, Evaluation
Raw Blood pressure data
Baseline 8 weeks
Placebo
Drug XDBP(mmHg)
Subset of plotted data
Bias and variability
XY
Unexplained variation
Variation in observations
= Explained variation
+
Bias and variability
Drug A
Drug B
Outcome
Is there any difference between drug A and drug B?
Bias and variability
Y=μA+βx
Y=μB+βx
μA
μB
x=age
Model: ijijiij xY
Confounding
Predictors of
treatment
Predictors of outcome
Confounders
Treatmentallocation
Treatmentallocation
A
B
Outcome
Example
Variable Non smokers Cigarette smokers
Cigar or pipe smokers
Mortality rate* 20.2 20.5 35.5
Cochran, Biometrics 1968*) per 1000 person-years %
Smoking Cigaretts is not so bad but watch out for Cigars or Pipes (at least in Canada)
ExampleSmoking Cigaretts is not so bad but watch out for Cigars or Pipes (at least in Canada)
Variable Non smokers Cigarette smokers
Cigar or pipe smokers
Mortality rate* 20.2 20.5 35.5
Average age 54.9 50.5 65.9
Cochran, Biometrics 1968*) per 1000 person-years %
ExampleSmoking Cigaretts is not so bad but watch out for Cigars or Pipes (at least in Canada)
Variable Non smokers Cigarette smokers
Cigar or pipe smokers
Mortality rate* 20.2 20.5 35.5
Average age 54.9 50.5 65.9
Adjusted mortality rate*
20.2 26.4 24.0
Cochran, Biometrics 1968*) per 1000 person-years %
Confounding
The effect of two or more factors can not be separated
Example: Compare survival for surgery and drug
R
Life long treatment with drug
Surgery at time 0
•Surgery only if healty enough•Patients in the surgery arm may take drug•Complience in the drug arm May be poor
Looks ok but:
Survival
Time
Confounding
Can be sometimes be handled in the design
Example: Different effects in males and females
Imbalance between genders affects result
Stratify by gender
R
A
BGender
M
F
R
R
A
A
B
B
Balance on average Always balance
InteractionThe outcome on one variable depends on the value of another variable.
ExampleInteraction between two drugs
R
A
A
B
B
Wash out
A=AZD1234
B=AZD1234 + Clarithromycin
Interaction
Mean
0
1
2
3
4
5
0 4 8 12 16 20 24
Time after dose
Plas
ma
conc
entr
atio
n (µ
mol
/L)
line
ar s
cale
AZD0865 alone
Combination of clarithromycinand AZD0865
19.75 (µmol*h/L)
36.62 (µmol*h/L)
AUC AZD0865:
AUC AZD0865 + Clarithromycin:
Ratio: 0.55 [0.51, 0.61]
Example: Drug interaction
InteractionExample:Treatment by center interaction
Treatment difference in diastolic blood pressure
-25
-20
-15
-10
-5
0
5
10
15
0 5 10 15 20 25 30
Ordered center number
mm
Hg
Average treatment effect: -4.39 [-6.3, -2.4] mmHg
Treatment by center: p=0.01
What can be said about the treatment effect?
Descriptive and inferential statistics
The presentation of the results from a clinical trial can be split in three categories:
•Descriptive statistics•Inferential statistics•Explorative statistics
Descriptive and inferential statistics
Descriptive statistics aims to describe various aspects of the data obtained in the study.
•Listings.•Summary statistics (Mean, Standard Deviation…).•Graphics.
Descriptive and inferential statistics
Inferential statistics forms a basis for a conclusion regarding a prespecified objective addressing the underlying population.
Hypothesis Results
Confirmatory analysis:
Conclusion
Descriptive and inferential statistics
Explorative statistics aims to find interesting results thatCan be used to formulate new objectives/hypothesis for further investigation in future studies.
Results Hypothesis
Explorative analysis:
Conclusion?
Hypothesis testing, p-values and confidence intervals
ObjectivesVariableDesign
Statistical ModelNull hypothesis
Estimatep-value
Confidence interval
ResultsInterpretation
Hypothesis testing, p-values
Statistical model: Observations nn RXX ,1X
from a class of distribution functions
:P
Hypothesis test: Set up a null hypothesis: H0: 0and an alternative H1: 1
Reject H0 if 0|cSP Xnc RS X
p-value:
Rejection region
The smallest significance level for which the null hypothesis can be rejected.
Significance level
What is statistical hypothesis testing?
A statistical hypothesis test is a method of making decisions using data from a scientific study.
Decisions: Conclude that substance is likely to be
efficacious in a target population.
Scientific study:Collect data measuring efficacy of a
substance on a random sample of patients representative of the target population
Formalizing hypothesis testing
We try to prove that collected data with little likelihood can correspond to a statement or a hypothesis which we do not want to be true!
Hypothesis:•The effect of our substance has no effect on blood pressure compared to placebo •An active comparator is superior to our substance
What do we want to be true then?•The effect of our substance has a different effect on blood pressure compared to placebo •Our substance is non-inferior to active comparator
Formalizing hypothesis testing cont. Formalizing it even further…
As null hypothesis, H0, we shall choose the hypothesis we want to reject
H0: μX = μplacebo
As alternative hypothesis, H1, we shall choose the hypothesis we want to prove.
H1: μX ≠ μplacebo
(two sided alternative hypothesis)
μ is a parameter that characterize the efficacy in the target population, for example the Mean.
H0: Treatment with substance X has no effect on blood pressure compared to placebo
Example, two sided H1:
H1: Treatment with substance X influence blood pressure compared to placebo
0 Difference in BP
H0: Treatment with substance X has no effect on blood pressure compared to placebo
Example: one sided H1
H1: Treatment with substance X decrease the blood pressure more than placebo
0Difference in BP
Structure of a hypothesis test Given our H0 and H1
Assume that H0 is true H0: Treatment with substance X has no effect on
blood pressure compared to placebo (μX = μplacebo)
1) We collect data from a scientific study. 2) Calculate the likelihood/probability/chance that data would actually turn out as it did (or even more extreme) if H0 was true;
P-value:Probability to get at least as extreme as what
we observed given H0
How to interpret the p-value?P-value:Probability to get at least as extreme as what we observed given H0
P-value small: Correct: our data is unlikely given the H0. We don’t believe in unlikely things so something is wrong. Reject H0.Common language: It is unlikely that H0 is true; we should reject H0
P-value large: We can´t rule out that H0 is true; we can´t reject H0
A statistical test can either reject (prove false) or fail to reject (fail to prove false) a null hypothesis, but never prove it true (i.e., failing to reject a null hypothesis does not prove it true).
How to interpret the p-value? Cont.
Expected outcome of the study if H0 is true (μX = μplacebo )
Likely outcome if the treatments are equal:The p-value is big
Expected outcome of the study for some H1 (μX < μplacebo )
Unlikely outcome if thetreatments are equal:The p-value is small
From the assumption that if the treatment does not have effect we calculate: How likely is it to get the data we collected in the study?
μX = μplaceboμX μplacebo
Risks of making incorrect decisionsWe can make two types of incorrect decisions:
1)Incorrect rejection of a true H0 “Type I error”; False Positive
2) Fail to reject a false null hypothesis H0 “Type II error”; False Negative
These two errors can´t be completely avoided.
We can try to control and minimize the risks of making error is several ways:
1) Optimal study design 2) Deciding the burden of evidence in favor of
H1
required to reject H0
Misconceptions and warnings
Easy to misinterpret and mix things up(p-value, size of test, significance level, etc).
P-value is not the probability that the null hypothesis is true
P-value says nothing about the size of the effect.A statistical significant difference does not need to be clinically relevant!
A high p-value is not evidence that H0 is true
H0: Treatment with substance X has no effect on blood pressure compared to placebo
Example:
0Difference in BP
Distribution of average effect if Ho is true
Xobs=10.4mmHg
p=0.0156
•If the null hypothesis is true it is unlikely to observe 10.4•We don’t believe in unlikely things so something is wrong•The data is ”never” wrong•The null hypothesis must be wrong!
H0: Treatment with substance X has no effect on blood pressure compared to placebo
Example:
0Difference in BP
Distribution of average effect if Ho is true
Xobs=3.2mmHg
p=0.35
•If the null hypothesis is true it is not that unlikely to observe 3.2•Nothing unlikely has happened•There is no reason to reject the null hypothesis•This does not prove that the null hypothesis is true!
Confidence intervals
A confidence set is a random subset covering the true parameter value with probability at least .
XC
1
Let rejectednot : if 0
rejected : if 1,
*0
*0*
H
HX (critical function)
Confidence set: 0,: XXC
The set of parameter values correponding to hypotheses that can not be rejected.
Example
• We study the effect of treatment X on change in DBP from baseline to 8 weeks
• The true treatment effect is: d = μX – μplacebo
• The estimated treatment effect is:
– How reliable is this estimation?
mmHgxx placeboX 5.7
Hypothesis testing
• Test the hypothesis that there is no difference between treatment X and placebo
• Use data to calculate the value of a test function: High value -> reject hypothesis, since it is unlikely given not true difference
• For a long time it was enough to present the point estimate and the result of the test– Previous example: The estimated treatment
effect is 7.5 mmHg, which is significantly different from zero at the 5% level.
Famous (?) quotes
“We do not perform an experiment to find out if two varieties of wheat or two drugs are equal. We know in advance, without spending a dollar on an experiment, that they are not equal” (Deming 1975)
“Overemphasis on tests of significance at the expense especially of interval estimation has long been condemned” (Cox 1977)
“The continued very extensive use of significance tests is alarming” (Cox 1986)
41
Estimations + Interval
Better than just hypothesis test• The estimation gives the best guess of the
true effect• The confidence interval gives the accuracy
of the estimation, i.e. limits within which the true effect is located with large certainty
• One can decide if the result is statistically significant, but also if it has biological/clinical relevance
• Now required by Regulatory Authorities, journals, etcNeyman, Jerzy (1937). "Outline of a Theory of Statistical Estimation Based on the Classical Theory of Probability". Philosophical Transactions of the Royal Society of London. Series A.
Example
• The 95% confidence interval is [-9.5, -4.9] mmHg (based on a model assuming normally distributed data)
• With great likelihood (95%), the interval [-9.5, -4.9] contains the true treatment effect μX – μplacebo
• Provided that our model is correct…
Drug X Placebo
Model:
μX μplacebo
σ σ
0-9.5 -4.5
General principle
• There is a True fixed value that we estimate using data from a clinical trial or other experiment
• The estimate deviates from the true value (by an unknown amount)
• If we were to repeat the study a number of times, the different estimates would be centred around the true value
• A 95% confidence interval is an interval estimated so that if the study is repeated a number of times, the interval will cover the true value in 95% of these
General principle• Estimate a parameter, for
example – Mean difference,– Relative risk reduction, – Proportion of treatment
responders, etc
• Calculate an interval that contains the true parameter value with large probability
General principle
Estimate ± Quantile * Variability
Model
Depends on confidence level
Of the estimate
-/ n+/ n
~67%
General principle – Normal model
Mean ± 1 *
Normal model, σ known
67% confidence level
SD of the mean
n
-1.96/ n +1.96/ n
95%
General principle – Normal model
Mean ± 1.96 *
Normal model, σ known
95 % confidence level
SD of the mean
n
General principle – Normal model
Mean ± t(1-α/2, n-1) *
Normal model, σ not
known
(1-α)% confidence level
SD of the mean
n
sd
Width• The width of the confidence
interval depends on:– Degree of Confidence (90%,
95% or 99%)– Size of the sample– Variability– Statistical model– Design of the study
95% 90% 17% narrower
95% 80% 36% narrower
95% 99% 35% wider
Effect of confidence level
51
(normal model, n=30)
“Excuse me, professor. Why a 95% confidence interval and not a 94% or 96% interval?”, asked the student.
“Shut up,” he explained.
Sample size
Double SD double width, etc
Double 30% narrower
+50% 20% narrower
+30% 12% narrower
Effect of Sample size and SD
52
Model Dependence• Can we assume normally distributed data?• Is the variability the same in all treatment
groups?• Are there important covariates, e.g. baseline
level or confounders?• Can we assume a covariance structure e.g.
repeated measurements per individual?• For time to event data – can we assume
proportional hazards?• Multiple events data – can we assume that
there is no overdispersion?
Model Dependence• Statistical packages provides confidence
intervals for most models• But assumptions are not always easily
checked and you usually have to pre-specify the model
• Given a sufficient sample size you may still ‘get away with it’, since mean values are approximately normally distributed (or a log transform might do the trick)
• Otherwise you may want to use a non-parametric method which does not depend on a (possibly approximate) model
median
Non-parametric CIs - ExampleCalculated using the available values.
Example - say we have calculated the following the following treatment differences (in sorted order):
-7.8 -6.9 -4.7 3.7 6.5 8.7 9.1 10.1
10.8 13.6 14.4 15.6
20.2
22.4
23.5
Confidence level (interval for the median)
99.2% 96.5% 88.2%
Analogy with tests• For most statistical tests there is a
corresponding confidence interval• If a 95% confidence interval does not
cover ‘the zero’, the corresponding test is to give a p-value < 0.05.
• If for example your p-value is based on the median and the confidence interval is based on the mean you can get conflicting results = trouble
Comparing two CIs • Can we judge whether groups are significantly
different depending on whether or not their confidence intervals overlap? - Not always.
• Parallel group:– Non-overlapping confidence intervals -
significantly different.– Overlapping confidence intervals - not
certain. – Depends on the confidence level of the
individual CIs: Comparing two 84% confidence intervals corresponds to a test at the 5% level (approximately)
Sample size• Based on the precision of the interval instead
of the power of a test
• Examples: – Interval of treatment difference not wider
than x, with some probability– Lower limit/mean > 0.6 and upper
limit/mean < 1.4 with at least 80% probability* - suitable when estimating geometric means
* Based on ‘FDA recommendation’ for pediatric PK studies
Example
yij = μ + τi + β (xij - x··) + εij
Variable: The change from baseline to end of study in sitting DBP (sitting SBP) will be described with an ANCOVA model, with treatment as a factor and baseline blood pressure as a covariate
Null hypoteses (subsets of ):H01: τ1 = τ2 (DBP)H02: τ1 = τ2 (SBP)H03: τ2 = τ3 (DBP)H04: τ2 = τ3 (SBP)
Objective: To compare sitting diastolic blood pressure (DBP) lowering effect of hypersartan 16 mg with that of hypersartan 8 mg
Model:treatment effecti = 1,2,3 {16 mg, 8 mg, 4 mg}
Parameter space: 4R
4R
0321
Example continedHypothesis Variable LS Mean CI (95%) p-value
1: 16 mg vs 8 mg Sitting DBP
-3.7 mmHg [-4.6, -2.8] <0.001
2: 16 mg vs 8 mg Sitting SBP
-7.6 mmHg [-9.2, -6.1] <0.001
3: 8 mg vs 4 mg Sitting DBP
-0.9 mmHg [-1.8, 0.0] 0.055
4 : 8 mg vs 4 mg Sitting SBP
-2.1 mmHg [-3.6, -0.6] 0.005This is a t-test where the test statistic follows a t-distribution
Rejection region: cT XX :
001.0P-value: The null hypothesis can pre rejected at
XT0-c c
21 0-4.6 -2.8
P-value says nothing about the size of the effect!
No. of patients per group Estimation of effect p-value
10 1.94 mmHg 0.376
100 -0.65 mmHg 0.378
1000 0.33 mmHg 0.129
10000 0.28 mmHg <0.0001
100000 0.30 mmHg <0.0001
A statistical significant difference does NOT need to be clinically relevant!
Example: Simulated data. The difference between treatment and placebo is 0.3 mmHg
Statistical and clinical significance
Statistical significance:
Clinical significance:
Health ecominical relevance:
Is there any difference between the evaluated treatments? Does this difference have any meaning for the patients?Is there any economical benefit for the society in using the new treatment?
Statistical and clinical significance
A study comparing gastroprazole 40 mg and mygloprazole 30 mg with respect to healing of erosived eosophagitis after 8 weeks treatment.
Drug Healing rategastroprazole 40 mg
87.6%
mygloprazole 30 mg
84.2%
Cochran Mantel Haenszel p-value = 0.0007
Statistically significant!
Health economically relevant??
Clinically significant?