Is there a way to predict Missing values with Community structure in networks?

I have a data set with a couple dozen variables, such as age, level of education, self-assessed (via a Likert scale) measures of technical ability, experience, willingness to share personal information, etc etc. Naturally, this data exhibit missing values.

My question:

Q1. What is the influence of those missing values on the network?

Q2. On the other way, Is there a way to predict the missing values using the constructed network?

  • $\begingroup$ + please forgive me that I am not a native English speaker :) $\endgroup$ – Dov Feb 24 '15 at 11:22
  • $\begingroup$ You haven't specified what determines community structure or relationships. Is your data for a population of people? Do they have social relationships of their choosing (friends) or their circumstances (family)? Or are you associating people by similarity of traits? $\endgroup$ – MrMeritology Feb 28 '15 at 12:51
  • $\begingroup$ Following @MrMeritology comment, it seems that you are talking about clusterization (grouping data in some space - the values of your variables). "Community structure" and "network" are terms usually used when you have only metric information - the distance or the existence of a relation between the entities in your set. Thus "clusterization" is finding groups based on peoples characteristics such as gender, level of education, salary, technical ability. "Community detection" is when you have to find groups based on the information of whether two people answered the same question in CV. $\endgroup$ – Jacques Wainer Feb 28 '15 at 15:26
  • $\begingroup$ cont. This naming rule is not 100% right but it will help you find information or get the appropriate help. $\endgroup$ – Jacques Wainer Feb 28 '15 at 15:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.