generating tables for glmer models in rempsych

[rempsyc]

generating tables for glmer models in rempsych

[markgibson9]

I will! (I've already copied the citation) I'll even thank you in the acknowledgments as well. You just helped me save hours of time, and I'm under pressure to get this one out. I owe you a drink/poutine next time I'm in Montreal (I collaborate there with UdM Linguistics, so I go a lot). Best regards, Mark

…

On Thu, Sep 28, 2023 at 11:21 PM Rémi Thériault ***@***.***> wrote: Great, thanks. You can just cite the JOSS paper in your paper if you want, that would be really helpful to me :) https://doi.org/10.21105/joss.05466 — Reply to this email directly, view it on GitHub <#23 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BC4ZE4RRAVZOGXZGEBUEZXLX4XS5XANCNFSM6AAAAAA5LMKZEM> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- *Este mensaje puede contener información confidencial. Si usted no es el destinatario o lo ha recibido por error, por favor, bórrelo de sus sistemas y comuníquelo a la mayor brevedad al remitente. Los datos personales incluidos en los correos electrónicos que intercambie con el personal de la Universidad de Navarra podrán ser almacenados en la libreta de direcciones de su interlocutor y/o en los servidores de la Universidad durante el tiempo fijado en su política interna de conservación de información. La Universidad de Navarra gestiona dichos datos con fines meramente operativos, para permitir el contacto por email entre sus trabajadores/colaboradores y terceros. Puede consultar la Política de Privacidad de la Universidad de Navarra en la dirección:  **https://www.unav.edu/aviso-legal* <https://www.unav.edu/aviso-legal>**** ** ** *This email message may contain confidential information. If you are not the intended recipient of this message or their agent, or if this message has been addressed to you in error, please immediately alert the sender by reply email and then delete this message and any attachments.  The personal information included in email messages exchanged with employees of the University of Navarra may be stored in the database of your interlocutor and/or the servers of the University for the time-period stipulated by its internal information storage policy. The University stores such data for purely administrative purposes, to facilitate e-mail contact between its employees and third parties. The University of Navarra Privacy Policy may be accessed at https://www.unav.edu/aviso-legal <https://www.unav.edu/aviso-legal>      ***** ** ** _Antes de imprimir este mensaje o sus documentos anexos, asegúrese de que es necesario. Proteger el medio ambiente está en nuestras manos. Before printing this e-mail or attachments, be sure it is necessary. _It is in our hands to protect the environment.__

[rempsyc]

Thanks for opening an issue, Mark. Can you try the following code for a starter, and then with your own data see if it works?

library(lme4)
library(report)
library(rempsyc)

model_full <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd),
             data = cbpp, family = binomial)

model_full |> 
  report_table() |>
  nice_table(highlight = TRUE)

^{Created on 2023-09-28 with reprex v2.0.2}

[rempsyc]

If you want a shorter version of the table, you can instead try the following:

library(lme4)
library(report)
library(rempsyc)

model_full <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd),
             data = cbpp, family = binomial)

model_full |> 
  report_table() |>
  summary() |>
  nice_table(highlight = TRUE)

^{Created on 2023-09-28 with reprex v2.0.2}

[markgibson9]

Yes, this works fine, I get the same table as in the message. Both work great. What I don't know though is what (incidence, size - incidence) should be replaced with from my df to shape my results to it (I've looked at the cbpp df, but I still don't have it clear). I kinda see it, but I'm getting 'unexpected symbol' errors when I try to plug in my own data.

…

On Thu, Sep 28, 2023 at 9:18 PM Rémi Thériault ***@***.***> wrote: If you want a shorter version of the table, you can instead try the following: library(lme4) library(report) library(rempsyc) gm1 <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd), data = cbpp, family = binomial) gm1 |> report_table() |> summary() |> nice_table(highlight = TRUE, short = TRUE) <https://camo.githubusercontent.com/1aaf646596d11723582fb3112e42d151270521119d3d1bcaa2fd6f5692ff32d6/68747470733a2f2f692e696d6775722e636f6d2f774c4e6d4254452e706e67> Created on 2023-09-28 with reprex v2.0.2 <https://reprex.tidyverse.org> — Reply to this email directly, view it on GitHub <#23 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BC4ZE4USDJFJ4DMPHQASCV3X4XERHANCNFSM6AAAAAA5LMKZEM> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- *Este mensaje puede contener información confidencial. Si usted no es el destinatario o lo ha recibido por error, por favor, bórrelo de sus sistemas y comuníquelo a la mayor brevedad al remitente. Los datos personales incluidos en los correos electrónicos que intercambie con el personal de la Universidad de Navarra podrán ser almacenados en la libreta de direcciones de su interlocutor y/o en los servidores de la Universidad durante el tiempo fijado en su política interna de conservación de información. La Universidad de Navarra gestiona dichos datos con fines meramente operativos, para permitir el contacto por email entre sus trabajadores/colaboradores y terceros. Puede consultar la Política de Privacidad de la Universidad de Navarra en la dirección:  **https://www.unav.edu/aviso-legal* <https://www.unav.edu/aviso-legal>**** ** ** *This email message may contain confidential information. If you are not the intended recipient of this message or their agent, or if this message has been addressed to you in error, please immediately alert the sender by reply email and then delete this message and any attachments.  The personal information included in email messages exchanged with employees of the University of Navarra may be stored in the database of your interlocutor and/or the servers of the University for the time-period stipulated by its internal information storage policy. The University stores such data for purely administrative purposes, to facilitate e-mail contact between its employees and third parties. The University of Navarra Privacy Policy may be accessed at https://www.unav.edu/aviso-legal <https://www.unav.edu/aviso-legal>      ***** ** ** _Antes de imprimir este mensaje o sus documentos anexos, asegúrese de que es necesario. Proteger el medio ambiente está en nuestras manos. Before printing this e-mail or attachments, be sure it is necessary. _It is in our hands to protect the environment.__

[rempsyc]

Ok, you can define your model the same way you did earlier,

model_full<-glmer(accuracy` ~ SNR + number_speakers + Proximity + Vowel + Level + (1|participant), 
   data=EN, family = binomial)

So no need to specify incidence, that was just to get a glmer model working. The important bit, once you have defined the model, is what follows (the report_table and nice_table functions).

[markgibson9]

Thanks so much! It works great! I'll make sure and thank you in our new paper. Best! Mark

…

On Thu, Sep 28, 2023 at 10:52 PM Rémi Thériault ***@***.***> wrote: Ok, you can define your model the same way you did earlier, model_full<-glmer(accuracy` ~ SNR + number_speakers + Proximity + Vowel + Level + (1|participant), data=EN, family = binomial) So no need to specify incidence, that was just to get a glmer model working. The important bit, once you have defined the model, is what follows (the report_table and nice_table functions). — Reply to this email directly, view it on GitHub <#23 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BC4ZE4S5TJOTDVZCVF55IKDX4XPRVANCNFSM6AAAAAA5LMKZEM> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- *Este mensaje puede contener información confidencial. Si usted no es el destinatario o lo ha recibido por error, por favor, bórrelo de sus sistemas y comuníquelo a la mayor brevedad al remitente. Los datos personales incluidos en los correos electrónicos que intercambie con el personal de la Universidad de Navarra podrán ser almacenados en la libreta de direcciones de su interlocutor y/o en los servidores de la Universidad durante el tiempo fijado en su política interna de conservación de información. La Universidad de Navarra gestiona dichos datos con fines meramente operativos, para permitir el contacto por email entre sus trabajadores/colaboradores y terceros. Puede consultar la Política de Privacidad de la Universidad de Navarra en la dirección:  **https://www.unav.edu/aviso-legal* <https://www.unav.edu/aviso-legal>**** ** ** *This email message may contain confidential information. If you are not the intended recipient of this message or their agent, or if this message has been addressed to you in error, please immediately alert the sender by reply email and then delete this message and any attachments.  The personal information included in email messages exchanged with employees of the University of Navarra may be stored in the database of your interlocutor and/or the servers of the University for the time-period stipulated by its internal information storage policy. The University stores such data for purely administrative purposes, to facilitate e-mail contact between its employees and third parties. The University of Navarra Privacy Policy may be accessed at https://www.unav.edu/aviso-legal <https://www.unav.edu/aviso-legal>      ***** ** ** _Antes de imprimir este mensaje o sus documentos anexos, asegúrese de que es necesario. Proteger el medio ambiente está en nuestras manos. Before printing this e-mail or attachments, be sure it is necessary. _It is in our hands to protect the environment.__

[rempsyc]

Great, thanks. You can just cite the JOSS paper in your paper if you want, that would be really helpful to me :)

https://doi.org/10.21105/joss.05466

[rempsyc]

Cool, looking forward! :)

[rempsyc]

Regarding your last email question,

When I save flextable as an object:

flextable::save_as_docx(my_table, path = "C://Users//mgibson//Documents//JPHON_EN_SP//nice_table.docx")

It works fine and the doc appears in the folder, but the term column, title, note on significance are missing. The terms etc. do appear in the viewer. I'm assuming it has something to do with the fact that I didn't customize it. In your tutorial I see you have this:

# Standardize variables to get standardized coefficients
mtcars.std <- lapply(mtcars, scale)
# Create a simple linear model
model <- lm(mpg ~ cyl + wt * hp, mtcars.std)
# Gather summary statistics
stats.table <- as.data.frame(summary(model)$coefficients)
# Get the confidence interval (CI) of the regression coefficient
CI <- confint(model)
# Add a row to join the variables names and CI to the stats
stats.table <- cbind(row.names(stats.table), stats.table, CI)
# Rename the columns appropriately
names(stats.table) <- c("Term", "B", "SE", "t", "p", "CI_lower", "CI_upper")

For the mtcars data, but that won't work for my data frame (I assume because my response variable is binary?)

The code I provided earlier simply printed the table to the Viewer, it did not create an object called my_table, but the way it appears in the viewer is exactly how it should appear in the Word document. It does not have to do with the fact that you did not customize the table.

Rather, to know the expected output, we should look at the example I shared earlier.

1. First of all, from the picture I shared, we can see that there is no "Term" column, because it is called "Parameter". Is that ok for you? Otherwise you can either rename by hand in the Microsoft Word output, or in the data frame before passing it to nice_table().

2. For the title, and note on significance, you have to provide those directly to the nice_table() function, like in the tutorial, using the title and note arguments.

Thus, In order to save the table to Word with the title and note, you will have to use adjusted code where you define my_table, e.g., like this:

library(lme4)
library(report)
library(rempsyc)

model_full <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd),
                    data = cbpp, family = binomial)

my_table <- model_full |> 
  report_table() |>
  summary() |>
  nice_table(highlight = TRUE,
             title = c("Table 1", "GLMER regression model"),
             note = c(
               "This is an example note about the data.",
               "* p < .05, ** p < .01, *** p < .001"
               ))

flextable::save_as_docx(my_table, path = "nice_table.docx")

^{Created on 2023-09-29 with reprex v2.0.2}

Does that help?

[markgibson9]

When I save flextable as an object:

flextable::save_as_docx(my_table, path = "C://Users//mgibson//Documents//JPHON_EN_SP//nice_table.docx")

It works fine and the doc appears in the folder, but the term column, title, note on significance are missing. The terms etc. do appear in the viewer. I'm assuming it has something to do with the fact that I didn't customize it. In your tutorial I see you have this:

# Standardize variables to get standardized coefficients
mtcars.std <- lapply(mtcars, scale)
# Create a simple linear model
model <- lm(mpg ~ cyl + wt * hp, mtcars.std)
# Gather summary statistics
stats.table <- as.data.frame(summary(model)$coefficients)
# Get the confidence interval (CI) of the regression coefficient
CI <- confint(model)
# Add a row to join the variables names and CI to the stats
stats.table <- cbind(row.names(stats.table), stats.table, CI)
# Rename the columns appropriately
names(stats.table) <- c("Term", "B", "SE", "t", "p", "CI_lower", "CI_upper")

[markgibson9]

When I run the code, the table I get in the viewer is perfect:

image.png

With significant codes at the bottom (,,).

But when I write it to a Word doc, I get this:

image.png

With no title, notes, Parameter reads row.names(stats.table) and the p-value column omits significance codes and eliminates the final 1 of <0.001. I know I have to be doing something stupid, but here is the code I'm inserting:

model_full<-glmer(accuracy ~ SNR + number_speakers + Proximity + Vowel + Level + (1|participant), data=df, family = binomial)

my_table <- model_full |>
report_table() |>
summary() |>
nice_table(highlight = TRUE,
title = c("Table 1", "Output of GLMER regression model"),
note = c(
"Significance levels.",
"* p < .05, ** p < .01, *** p < .001"
))

my_table <- nice_table(stats.table)

flextable::save_as_docx(my_table, path = "C://Users//mgibson//Documents//JPHON_EN_SP//nice_table.docx")

[rempsyc]

Ok, please try the steps below:

1. Try to type packageVersion("flextable") and post the answer here.
2. Next, install the latest flextable version by typing install.packages("flextable")
3. Restart your R session and then try your steps again to save the Word document and report on the result.

[markgibson9]

Super! It now looks perfect. Thanks a lot for all your help! Mark

…

On Sat, Sep 30, 2023 at 12:38 AM Rémi Thériault ***@***.***> wrote: Ok, please try the steps below: 1. Try to type packageVersion("flextable") and post the answer here. 2. Next, install the latest flextable version by typing install.packages("flextable") 3. Restart your R session and then try your steps again to save the Word document and report on the result. — Reply to this email directly, view it on GitHub <#23 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BC4ZE4RCFL2LOYZZW7DN24LX45EVZANCNFSM6AAAAAA5LMKZEM> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- *Este mensaje puede contener información confidencial. Si usted no es el destinatario o lo ha recibido por error, por favor, bórrelo de sus sistemas y comuníquelo a la mayor brevedad al remitente. Los datos personales incluidos en los correos electrónicos que intercambie con el personal de la Universidad de Navarra podrán ser almacenados en la libreta de direcciones de su interlocutor y/o en los servidores de la Universidad durante el tiempo fijado en su política interna de conservación de información. La Universidad de Navarra gestiona dichos datos con fines meramente operativos, para permitir el contacto por email entre sus trabajadores/colaboradores y terceros. Puede consultar la Política de Privacidad de la Universidad de Navarra en la dirección:  **https://www.unav.edu/aviso-legal* <https://www.unav.edu/aviso-legal>**** ** ** *This email message may contain confidential information. If you are not the intended recipient of this message or their agent, or if this message has been addressed to you in error, please immediately alert the sender by reply email and then delete this message and any attachments.  The personal information included in email messages exchanged with employees of the University of Navarra may be stored in the database of your interlocutor and/or the servers of the University for the time-period stipulated by its internal information storage policy. The University stores such data for purely administrative purposes, to facilitate e-mail contact between its employees and third parties. The University of Navarra Privacy Policy may be accessed at https://www.unav.edu/aviso-legal <https://www.unav.edu/aviso-legal>      ***** ** ** _Antes de imprimir este mensaje o sus documentos anexos, asegúrese de que es necesario. Proteger el medio ambiente está en nuestras manos. Before printing this e-mail or attachments, be sure it is necessary. _It is in our hands to protect the environment.__