Difference between revisions of "Randomization in SurveyCTO"
Mrijanrimal (talk | contribs) |
Mrijanrimal (talk | contribs) |
||
| Line 1: | Line 1: | ||
During surveys, you might often need to randomize various aspects of the questionnaire. While SurveyCTO has a random number generator, is is usually not recommended that you use it. | During surveys, you might often need to randomize various aspects of the questionnaire. While SurveyCTO has a random number generator, is is usually not recommended that you use it. | ||
== Randomization using SurveyCTO== | == Randomization using SurveyCTO== | ||
Revision as of 19:27, 31 January 2017
During surveys, you might often need to randomize various aspects of the questionnaire. While SurveyCTO has a random number generator, is is usually not recommended that you use it.
Randomization using SurveyCTO
If you need to randomize certain things in your questionnaire, randomization using SurveyCTO is not recommended. The best way to randomize things in a questionnaire is by using Stata. The reason that Stata is preferable is because the randomization in Stata is transparent and easily reproducible which is not only necessary for impact evaluation projects but also for publishing research. Randomization in Stata is also done before a survey so there is time to check for errors/bugs and also to ensure that there is balance in the dataset. When Stata is not available, Excel can also be used but randomization done in Excel is not as reproducible as randomization in Stata.
Back to Parent
This article is part of the topic Randomized Control Trials