I have some surveys with missing data, l want to know how to deal with missing data in surveys using SPSS or any other software, what about Multiple Imputation or any other method, and why should the missing data not exceed more than 30%??
Thanks in advance
Multiple imputation can be used. If the missing data exceeds more than 30% reliability of the data set reduces.
Hi Louai, as an add-on to Daniel's answer: to get a meaningful suggestion here you need to specify what type of data you are talking about (survey=questionaire OR survey=study with e.g. chemical measurement values), which allows to infer the reason for missing data (as Daniel pointed out). Also, you should state what you intend to do with the data/type of analyses. Only than you can expect hints regarding do's and dont's or alternative methods (which potentially can deal with missing data). Your aim should be to avoid getting a 'significant' result as an artifact of imputation and this you can only achieve by understanding where you come from data wise and where you go with your analysis. Bests, Jan
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS