Title/link | Description (taken from source) |
---|---|

Meta-Analysis (RLO) | This RLO provides an introduction to the basic concepts of meta-analysis, which is an important and valuable tool for summarising data from multiple studies. |

Steps in Conducting a Systematic Review (RLO) | This RLO outlines the five fundamental steps to conducting a systematic review of health care research so as identify, select and critically appraise relevant research. |

Egger M, Davey Smith G, Phillips AN. Meta-analysis: Principles and Procedures. BMJ 1997;315:1533-1537 |
This publication is one in a series of seven articles examining the procedures in conducting reliable meta-analysis in medical research |

Cochrane Collaboration | The Cochrane Library contains high-quality, independent evidence to inform healthcare decision-making. It includes reliable evidence from Cochrane and other systematic reviews. |

Centre for Reviews and Dissemination | The CRD undertakes reviews of research about the effects of interventions used In health and social care. |

NHS Health Technology Assessment Programme | The HTA programme works to provide all those who make decisions in the NHS with high-quality information on the costs, effectiveness and broader impact of health care treatments and tests. |

**Risk ratio**- the risk ratio determines the strength of the association between the intervention group (or risk factor) and a binary outcome. It can be estimated by dividing the risk of the outcome in the intervention group (or exposed group) by the risk of the outcome in the control group (or unexposed group). The risk of the outcome is the proportion or percentage of people with the outcome.-
**Risk difference**- the risk difference is the estimated by subtracting the risks of the outcome in the two groups, i.e. risk of outcome in the intervention group (or exposed group) minus risk of outcome in the control group (or unexposed group). **Mean difference**- the mean difference is used for continuous outcomes, and is estimated as the difference in the means of the outcome between the two groups i.e. the mean of the outcome in the intervention group (or exposed group) minus the mean of the outcome in the control group (or unexposed group).-
**Standardised mean difference**- this is similar to the mean difference but used when the units of the continuous outcome are not the same across the studies. This is estimated as: [mean of the outcome in the intervention group (or exposed group) minus the mean of the outcome in the control group (or unexposed group)] all divided by the pooled standard deviation for the two groups.

RLO Transcript (2.2Mb)