Analysing data

Table of Contents

1. Analysing data
2. Contents:
3. The database:
4. Data cleaning
5. Correcting the database
6. Analysis plan
7. Describing the sample
8. Averages
9. T-test:
10. Doing the T-test yourself
11. The results of the T-test
12. Redoing the T-test
13. In Summary

Analysis plan

 

Ideally we should have made our analysis plan before we even started the evaluation. In our plan for this database we said we would:

1. Clean the data

2. Describe the sample in terms of; Average age, Sex ratio, Disease duration, Baseline wellbeing, Age at first symptoms

3. Examine if the intervention lead to a change in wellbeing compared to placebo - using a T-test.

1

Why do we make an analysis plan? a) It can be some time between planning an evaluation and getting to the analysis, sometimes you just forget what you wanted to do. So it is good to write down your ideas somewhere. b) To help the team know what the whole evaluation is about c) Just to get things clear and well thought out d) So that we don't just analyse everything in the hope something is significant. If we state our analysis in advance it minimises the posibility that we will get a significant finding by "chance". e) All proposals need an analysis plan to get funding It is to stop type 1 errors, that is fishing around in the data until something appears significant. If we do 20 tests we will get 1 to be significant just by chance. However, it is also helpful to remember what we wanted to do, to make sure things are clear and well thought out and good to include in any proposal/ evaluation plan. It is to stop type 1 errors, that is fishing around in the data until something appears significant. If we do 20 tests we will get 1 to be significant just by chance. However, it is also helpful to remember what we wanted to do, to make sure things are clear and well thought out and good to include in any proposal/ evaluation plan.Your answer has been saved.