Meta-Analysis

MD.AKHTARUL ISLAM
LECTURER
STATISTICS DISCIPLINE
KHULNA UNIVERSITY
KHULNA

01/06/2025 [email protected] 1
 Stat-4209: Meta-Analysis

 SECTION-A
 Introduction-Definition and purpose, Types of meta-analyses, Steps to
Perform a Meta-Analysis, Criticisms of Meta-Analyses.
 Effect, Size and Precision-Treatment effects and effect sizes,
Parameters and estimates, Outline of effect size computations, Effect
sizes based on means: Introduction, Raw (unstandardized) mean
difference D, Standardized mean difference, d and g, Response ratios
effect sizes based on binary data (2×2 tables): Introduction, Risk ratio,
Odds ratio, Risk difference, Choosing an effect size index, Effect
sizes based on correlations: Introduction, Computing r, Other
approaches.
 Converting among effect sizes-Introduction, Converting from the log
odds ratio to , Converting from to the log odds ratio, Converting from
01/06/2025 [email protected] 2
to , Converting from to .
 Treatment effects and effect sizes
 An effect size in a measure of the strength of the
relationship between two variables in a statistical
population or a sample based-estimate of that
quantity.
 The term effect size is appropriate when the index is
used to quantify the relationship between two
variables or a difference between two groups.
 By contrast, the term treatment effect is appropriate
only for an index used to quantify the impact of a
deliberate intervention.
 Thus, the difference between males and females could
be called an effect size only, while the difference
between treated and control groups could be called
either an effect size or a treatment effect.
01/06/2025 [email protected] 3
 How to choose an effect size
 Three major considerations should drive the choice of an effect size
index.
1. The effect sizes from the different studies should be comparable to
one another in the sense that they measure (at least approximately)
the same thing.
2. The estimates of the effect size should be computable from the
information that is likely to be reported in published research
reports. That is, it should not require the re-analysis of the raw data
(unless these are known to be available).
3. The effect size should have good technical properties. For example,
its sampling distribution should be known so that variances and
confidence intervals can be computed.
Additionally, the effect size should be substantively
interpretable
01/06/2025 [email protected] 4
 Raw (Unstandardized) Mean Difference D
• When the outcome is reported on a meaningful scale and all studies in
the analysis use the same scale, the meta-analysis can be performed
directly on the raw difference in means.
• Consider a study that reports means for two groups (Treated and
Control) and suppose we wish to compare the means of these two
groups. Let and be the true (population) means of the two groups.
The population mean difference is defined as
Δ= ……………….. (1)
• The primary advantage of the raw mean difference is that it is
intuitively meaningful, either inherently (for example, blood pressure,
which is measured on a known scale) or because of widespread use
(for example, a national achievement test for students, where all
relevant parties are familiar with the scale).

01/06/2025 [email protected] 5
 Computing D from studies that use independent groups
• We can estimate the mean difference D from a study that used two
independent groups as follows. Let and be the sample means of the
two independent groups. The sample estimate of D is just the
difference in sample means, namely
D = -- …………………………..……(2)
• Let and be the sample standard deviations of the two groups, and
and be the sample sizes in the two groups. If we assume that the two
population standard deviations are the same so that =σ then the
variance of D is
= ……………….……..(3)
• Where = ………………(4)

01/06/2025 [email protected] 6
• If we don’t assume that the two population standard deviations are the
same, then the variance of D is
= + ……………(5)
In either case, the standard error of D is then the square root of V,
………………..(6)
• For example, suppose that a study has sample means = 103.00,
=100.00 sample standard deviations =4.5,and sample sizes =50. The
raw mean difference D is
D=103.00- 100.00= 3.00
• If we assume that then the pooled standard deviation within groups is
• = = 5.0249

01/06/2025 [email protected] 7
The variance and standard error of D are given by

= = 1.0100
And , =1.0050
• If we don’t assume that the two population standard deviations are the
same, then the variance of D is
= + =1.0100
And , =1.0050
• In this example formulas (3) and (5) yield the same result, but this
will be true only if the sample size and/or the estimate of the
variances is the same in the two groups.

01/06/2025 [email protected] 8
Computing D from studies that use matched groups or
pre-post scores
• The previous formulas are appropriate for studies that use two
independent groups. Another study design is the use of matched
groups, where pairs of participants are matched in some way (for
example, siblings, or patients at the same stage of disease), with the
two members of each pair then being assigned to different groups.
The unit of analysis is the pair, and the advantage of this design is that
each pair serves as its own control, reducing the error term and
increasing the statistical power. The magnitude of the impact depends
on the correlation between (for example) siblings, with a higher

• The sample estimate of Δ is just the sample mean difference, D. If we

correlation yielding a lower variance (and increased precision).

have the difference score for each pair, which gives us the mean
difference and the standard deviation of these differences (S diff), then

01/06/2025 [email protected] 9
 D = ……………………….....(1)
= ……………………..…(2)
where n is the number of pairs, and
………………………..(3)

For example, if the mean difference is 5.00 with standard deviation of

the difference of 10.00 and n of 50 pairs, then
D =5.0000
= = 2.0000….......................(4)
where n is the number of pairs, and
= 1.4142 ………………..(5)

01/06/2025 [email protected] 10
• Alternatively, if we have the mean and standard deviation for each set
of scores (for example, siblings A and B), the difference is
D = -- …………………….(6)
Where the variance is again given by,
= ……………………..…(7)
where n is the number of pairs, and the standard error is given by
………………………..(8)
• However, in this case we need to compute the standard deviation of
the difference scores from the standard deviation of each sibling’s
scores. This is given by
……….(9)

• where r is the correlation between ‘siblings’ in matched pairs. If then

(9) simplifies to

01/06/2025 [email protected] 11
 …………………..(10)
• In either case, as r moves toward 1.0 the standard error of the paired
difference will decrease, and when r = 0 the standard error of the
difference is the same as it would be for a study with two
independent groups, each of size n.
• For example, suppose the means for siblings A and B are 105.00 and
100.00, with standard deviations 10 and 10, the correlation between
the two sets of scores is 0.50, and the number of pairs is 50. Then
• D= 105.00-100.00 = 5.000
= = 2.000
and
= 1.4142 ………………..(5)
• In the calculation of , the is computed using

01/06/2025 [email protected] 12
 = 10.0000
Or
=10.0000
• The formulas for matched designs apply to pre-post designs as well.
The pre and post means correspond to the means in the matched
groups, n is the number of subjects, and r is the correlation between
pre-scores and post-scores.

01/06/2025 [email protected] 13