University of Hong Kong Featured PhD Programmes
University of Leeds Featured PhD Programmes
University of Edinburgh Featured PhD Programmes

PhD Discussion Forum

The following thread is brought to you by our sister Web site PostgraduateForum.com. If you wish to reply or post your own thread, you will be redirected to this site.

This Category:   PostgraduateForum.com > PhD Advice / Support


Message

Statistics help needed


User: Nishanthi - 04 December 2020 11:52

Hi, I have some data about who is attending the hospital for cervical screening. I have done the chi square to compare the two groups. But I have some missing values in the demographics and other variables. Can I do the analysis for only available values and leave the missing values? Thanks

User: PhoenixFortune - 04 December 2020 22:30

Quote From Nishanthi:
Hi, I have some data about who is attending the hospital for cervical screening. I have done the chi square to compare the two groups. But I have some missing values in the demographics and other variables. Can I do the analysis for only available values and leave the missing values? Thanks
I'm not sure about the statistical stance, but I'd say that you need to either use the data you have (and therefore not include participants with missing data in the analyses which require that missing data), or exclude participants with missing data entirely from all analyses. It kind of depends on what comparisons you are making, whether this affects the balance of the two groups etc.

User: Nishanthi - 05 December 2020 19:16

I don't want to exclude them completely because they have values for other variables and i am not doing any interaction analysis between the variables. I think, i can do the analysis with the data i have by not including the missing values in the SPSS for each variable. Is that going to be fine? Thanks in advance.

User: PhoenixFortune - 05 December 2020 20:43

Quote From Nishanthi:
I don't want to exclude them completely because they have values for other variables and i am not doing any interaction analysis between the variables. I think, i can do the analysis with the data i have by not including the missing values in the SPSS for each variable. Is that going to be fine? Thanks in advance.
I've never used missing data cells, but take a look here: https://www.spss-tutorials.com/spss-missing-values/

User: rewt - 06 December 2020 00:19

I am not that experienced with statistics but can you not separate the data sets for different analysis? Eg one study has 87 data points and the study with missing data only includes 54 data points. If you clearly state the number of participants for each data analysis it could be fine. However, I would also ask your supervisor about what is appropriate here.

User: lawlin - 11 January 2021 06:18

Hi, have you some clarity yet? I have a humanities background, so I can't be of much help here. But I have used some assistance in the past which has helped me. You could try dropping your question here - https://www.bartleby.com/subject/math/statistics. Could be helpful





FindAPhD. Copyright 2005-2021
All rights reserved.