1
$\begingroup$

I am conducting a meta-analysis using raw mean scores as effect sizes (i.e., reported test scores on a certain standardized test).

I found a calculation formula for sampling variances provided by, e.g., Card (2012, p. 150), Hox (2010, p. 209), and also [Calculation for the estimated sampling variance of individual group raw mean.

SEx = Sx/√N

  • where s is the standard deviation of variable X, and N is the sample size.

Especially, Card's book, Applied Meta-analysis for social science research was very helpful providing an equation for transforming scores between two different scales.

Card (2012, p. 148)

X2 = ((X1 - Min1)((Max2 - Min2)/(Max1 - Min1))+Min2

  • where, X2 is the equivalent score on the second scale
  • X1 is the score on the first scale that you wish to transform.
  • Min1 is the lowest possible score on the first scale.
  • Max1 is the highest possible score on the first scale.
  • Min2 is the lowest possible score on the second scale.
  • Max2 is the highest possible score on the second scale.

However, the book does not provide how to calculate sampling variances when ESs were transformed into a standardized value.

I would really appreciate it if you could let me know how sampling variances could be calculated for this standardized effect size. If possible, references that I can cite would be much appreciated.

$\endgroup$
2
  • 1
    $\begingroup$ SE(X2) = SE(X1)(Max2 - Min2)/(Max1 - Min1) $\endgroup$
    – user158565
    Aug 10, 2019 at 2:04
  • $\begingroup$ Thank you for your response, @user158565! Could you let me know how you find the formula? I am wondering if you know any reference that I can cite. Thank you in advance! $\endgroup$ Aug 10, 2019 at 4:19

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.