Appraise

Introduction

Ask

Find

Appraise

APPRAISE (RCTs) page 32 of 100

APPRAISING RCTs

Introduction (21pages)

Appraising randomisation (11pages)

Blinding and intention to treat (16pages)

Measures of risk/benefit (23pages)

Statistical significance (25pages)

Summary

APPRAISING ECONOMIC EVALUATIONS (EE)

Introduction (12pages)

Different types of EE (7pages)

Comparators & timescales
(9pages)

Assessing costs (16pages)

Assessing outcomes (17pages)

Time & models (10pages)

Measures of cost effectiveness (10pages)

Using economic analysis

Back

Next

So, what else have we learnt?

	Randomisation is essential to ensure that the control and experimental groups are the same at the start of the trial.
	*This eliminates selection* bias from the sample.**
	Good allocation concealment is needed to make sure that the people enrolling patients cannot introduce selection bias by varying their judgement of who is eligible for the trial.
	Block randomisation can be used to keep the numbers of patients in each group balanced at all times.
	Stratified randomisation can be used to make sure that known confounders are evenly distributed amongst the groups.
	You should check the characteristics of each group to see if there are any clinical differences between them.

This page updated on 25/11/05