Scribd
Upload
46 views22 pages

Sample Size Determination India 2007

Calculate the sample size needed for each case

Uploaded by

Priyanka Divekar
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
46 views22 pages

Sample Size Determination India 2007

Calculate the sample size needed for each case

Uploaded by

Priyanka Divekar
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 22

Sample Size Determination

The Fundamentals of Biostatistics in


Clinical Research Workshop
India, March 2007
Mario Chen
Framework

z Objectives
z Type of Inference: Estimation or
Hypothesis Testing
z Study Design: Type of Study and
Sample Size
z Data Collection
z Data Management
z Data Analysis
Selection of summary measure

Objective
Objective Population
Population

Endpoint
Endpoint Individual
Individual

Summarymeasure*
Summary measure* Sample
Sample

Parameter
Parameter Population
Population

* Depends of primary analysis method


Sample Size for Estimation

Necessary Components:
1. Indicator or summary measure of interest
(proportions or means)
2. Desired Confidence Level (1-α)
3. Desired Precision Level (d)
4. Expected Variability in the study population:
z For means (σ)

z For proportions (P)


Sample Size for Estimation
(Proportions)
Example:
1. Summary measure: Prevalence of Vibrio
Cholerae
2. Confidence Level: 95%
n = 523
3. Precision Level:
d = 3 percent points, i.e. 0.03
4. Variability: Estimate of P = 15% (from
previous studies)
Recommendation: IfIf there
Recommendation: there is
is not
not aa good
good estimate
estimate
for P,
for P, use
use PP closest
closest to
to 50%
50% to to be
be conservative
conservative
Sample Size for Estimation
(Means)
Example:
1. Summary measure: Mean hydrocele size
among filariasis infected patients
2. Confidence Level: 95%
3. Precision Level: d = 1.5 mm.
4. Variability: Estimate for σ = 5.7 mm.
n = 58
To estimate
To estimate σσ we
we can
can use
use previous
previous studies,
studies,
expert advice,
expert advice, or
or aa pilot
pilot study
study
Sample Size for Hypothesis
Testing
Necessary Components:
1. Summary measure of interest (proportions
or means)
2. Statistical Hypotheses
3. Significance Level (α)
4. Desired Power (1-β)
Sample Size for Hypothesis
Testing
Necessary Components (cont’d):
5. Effect Size: Smallest difference worth
detecting (clinically)
What is a clinically important
difference to detect?
z Standarddrug has 75% Cure rate
z And New treatment . . .
z 76%?. . . 77%? . . . 78%? . . . 79%?
z 87%? . . . 88%? . . . 89% . . . 90%?
Cured rate for the New Treatment?

z “Ridiculous notion” . . .
z “How would I know this – I’m doing the study
to estimate the effect.”
z “I have no data on which to base an estimate.”
--------------------True, but----------------------
z You do not estimate the cure rate for the new
treatment!
z You determine the cure rate reflecting the
clinically important difference to detect, which
may have no relation to the actual cure rate
Example

z Standard drug
z Cost of $30.00 for 28 days
z 2 oral doses per day

z Minimal side effects

z New treatment
z Cost of $500.00 for 28 days
z A single oral dose per day

z Neutropenia, blurred vision, and proteinuria


What is a clinically important
difference to detect?
z Standarddrug has 75% Cure rate
z And New treatment . . .
z 76%?. . . 77%? . . . 78%? . . . 79%?
z 87%? . . . 88%? . . . 89% . . . 90%?

z We believe 15% represents a clinically


important difference to detect
z If the difference is greater then changes will occur
z If the difference is smaller, groups are considered
“equivalent” (status quo preserved)
Sample Size for Hypothesis
Testing
Necessary Components (cont’d):
6. Variability expected in the population
z For means (σ1, σ2)
z For proportions (P1, P2)
Sample Size for Hypothesis
Testing
Example for proportions:
1. Summary measure: Proportion Cured
2. Statistical Hypotheses:
H0: Proportion cured is the same with both the
new treatment and the standard treatment
H1: Proportion cured is higher with the new
treatment than with the standard treatment

One sided
One sided vs.
vs. two
two sided
sided Alternative
Alternative
Hypothesis.
Hypothesis.
Sample Size for Hypothesis Testing
(cont-d)

3. Significance Level: α = 5%

4. Power: 1-β = 90%


(never lower than 80%)

5. Effect size: P2 – P1 = 15% n = 109

6. Variability:
Estimate for P1 = 75%
Estimate for P2 = 90%
Recommendation:
Recommendation:
a)Define
a) Definelevel
levelfor
forPPfor
forthe
the““baseline” group
baseline” group
b)Use
b) Useeffect
effectsize
sizeto
toobtain
obtainlevel
levelof
ofPPfor
forthe
the““study”
study”
group
group
Main Determinant of Study Size
Recommendations when budget is not enough:
1. (Estimation) Lower desired precision.
2. (Hypothesis Testing) Lower desired power or increase
minimum detectable effect size.
3. It is not recommended to change confidence levels,
significance levels, or variance estimates.
4. If after all these changes, budget is still insufficient,
one has to decide between:
• Not conducting the study until enough budget has
been obtained, or
• go ahead with the study knowing that the results
are likely to be inconclusive (pilot study or
exploratory).
Adjustments to Sample Size

z Non-Response (and attrition):


n2 = n1/(1-NR)
n2 = final size, n1 = effective size
NR = Non-response (and attrition) rate
Other Considerations

z Data dependencies (e.g., Matching, Repeated


Measures).
z Multivariate methods (e.g., control for
confounding).
z Multiplicity issues (e.g., Multiple testing,
endpoints, treatments, interim analyses).
z Other variables of interest (e.g., time to
event).
z Other hypotheses (e.g., equivalence).
Software

z PASS
(www.ncss.com/pass.html)
z nQUERY
(www.statsolusa.com/nquery/nquery.htm)
z EPI-INFO
(www.cdc.gov/epiinfo)
z EPIDAT
(www.paho.org/English/SHA/epidat.htm)
What should be included in the
protocol?
z Justification in terms of power or precision for
the primary endpoint
z Method used to calculate the sample size
z should be consistent with the primary method for
data analysis and appropriate for the study design
z Historical data to support the assumptions
z Justification in terms of feasibility
Questions?
Exercise: Case Scenarios

z StatisticalHypotheses
z Significance level and desired power
z Effect size discussion

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy