Error in eigen(if (doDykstra) R else Y, symmetric = TRUE) : infinite or missing values in 'x'

[shrutisram]

I am running into an error when trying to run a Network Comparison Test among men and women in a total sample of N = 1013 (men = 175; women = 838). The dataset includes 40 variables (not including gender) coded on a Likert scale.

When I try to run the following code: set.seed(13) comparison <- NCT(men, women, binary.data=FALSE, it=5000, test.edges=TRUE, edges = 'all')

plot(comparison, what ="network")

I get the following error: Error in eigen(if (doDykstra) R else Y, symmetric = TRUE) : infinite or missing values in 'x'

I have seen other threads relating this error with missing data. However, I have no missing data in this dataset (so there are no NAs in the dataset). Could there be any other reason this error was caused?

[cvborkulo]

Hi Shrutisram,

Maybe one of your variables have very little variance. Could you check?

Best, Claudia

Outlook voor iOShttps://aka.ms/o0ukef downloaden

---

Van: shrutisram @.> Verzonden: Friday, February 18, 2022 7:05:15 PM Aan: cvborkulo/NetworkComparisonTest @.> CC: Subscribed @.***> Onderwerp: [cvborkulo/NetworkComparisonTest] Error in eigen(if (doDykstra) R else Y, symmetric = TRUE) : infinite or missing values in 'x' (Issue #31)

I am running into an error when trying to run a Network Comparison Test among men and women in a total sample of N = 1013 (men = 175; women = 838). The dataset includes 40 variables (not including gender) coded on a Likert scale.

When I try to run the following code: set.seed(13) comparison <- NCT(men, women, binary.data=FALSE, it=5000, test.edges=TRUE, edges = 'all')

plot(comparison, what ="network")

I get the following error: Error in eigen(if (doDykstra) R else Y, symmetric = TRUE) : infinite or missing values in 'x'

I have seen other threads relating this error with missing data. However, I have no missing data in this dataset (so there are no NAs in the dataset). Could there be any other reason this error was caused?

— Reply to this email directly, view it on GitHubhttps://github.com/cvborkulo/NetworkComparisonTest/issues/31, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ABPVHTBJFVGSPDLAVTTRIL3U32C5XANCNFSM5OYVEWBQ. Triage notifications on the go with GitHub Mobile for iOShttps://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Androidhttps://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.***>

[shrutisram]

Thank you! On a cursory review and after I generated a summary of the data, it does look like there is sufficient variance in the range of responses. However, is there a certain variance threshold that is considered ideal? I have attached the dataset in case it would be helpful. Gender NCT.csv

[cvborkulo]

Can you just estimate the two networks without problems?

From: shrutisram @.> Date: Wednesday, 23 February 2022 at 22:26 To: cvborkulo/NetworkComparisonTest @.> Cc: Claudia van Borkulo @.>, Comment @.> Subject: Re: [cvborkulo/NetworkComparisonTest] Error in eigen(if (doDykstra) R else Y, symmetric = TRUE) : infinite or missing values in 'x' (Issue #31)

Thank you! On a cursory review and after I generated a summary of the data, it does look like there is sufficient variance in the range of responses. However, is there a certain variance threshold that is considered ideal? I have attached the dataset in case it would be helpful. Gender NCT.csvhttps://github.com/cvborkulo/NetworkComparisonTest/files/8127905/Gender.NCT.csv

— Reply to this email directly, view it on GitHubhttps://github.com/cvborkulo/NetworkComparisonTest/issues/31#issuecomment-1049231064, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ABPVHTA6OIZZ5RQTBP6BLQ3U4VGJBANCNFSM5OYVEWBQ. Triage notifications on the go with GitHub Mobile for iOShttps://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Androidhttps://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.***>

[TingyanY]

Hi Claudia,

I encountered the same error and I have no problem with estimating the two networks. Similar to Shrutisram, I did not find any missing value in my matrix. Do you have any idea about the potential issue? Thanks!

Kind regards, Tingyan