Examples
Examples
Try the starting example
- Study effect estimates
- 0.2,0.4,0.1
- Study standard errors
- 0.1,0.15,0.12
- Model (0=fixed,1=DerSimonian–Laird random)
- 0
- Pooled estimate
- 0.209091
- Pooled standard error
- 0.068376
- 95% lower
- 0.075076
- 95% upper
- 0.343106
- Cochran Q
- 2.454545
- I² (%)
- 18.518519
- Estimated between-study variance tau²
- 0.003358
Try another scenario
- Study effect estimates
- 1.2,0.4,0.1
- Study standard errors
- 0.1,0.15,0.12
- Model (0=fixed,1=DerSimonian–Laird random)
- 0
- Pooled estimate
- 0.676623
- Pooled standard error
- 0.068376
- 95% lower
- 0.542608
- 95% upper
- 0.810639
- Cochran Q
- 53.883117
- I² (%)
- 96.288262
- Estimated between-study variance tau²
- 0.383316
Calculation method
Calculation method
Pooled estimate
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
Pooled standard error
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
95% lower
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
95% upper
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
Cochran Q
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
I² (%)
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
Estimated between-study variance tau²
Inverse-variance fixed or DerSimonian–Laird random-effects pooling with normal Wald interval; Q, I² and nonnegative tau².
Symbols and units
- a
- Study effect estimates
- b
- Study standard errors
- c
- Model (0=fixed,1=DerSimonian–Laird random)
Use the units shown. A list keeps the order in which you enter its values. The symbol ^ means “raised to the power of”.
Assumptions & limits
Assumptions & limits
- Independent effect estimates on a common additive scale. Normal approximation, no Hartung–Knapp interval. Supported limits: All required fields must be finite values of the exact declared type and within displayed bounds. Lists contain1–1000 finite numbers. JSON tables are numeric rectangular rows, at most100 rows and30 columns; individual tools have stricter shape/domain constraints. Independent effect estimates on a common additive scale. Normal approximation, no Hartung–Knapp interval.
Are these inputs private?
These calculations run in your browser. A shared link contains the values you choose to share. Only questions submitted to the separate AI finder are sent to OpenAI.
Further reading
Background reading; this does not imply endorsement or independent review of SumFizz.