Longitudinal Multilevel Modeling in R Studio (PART 1)

[@hotelsleeperwy3409]

I declare you the GOAT of MML. You helped me so much out with my master thesis and my first study to publish. Thank you!!!

[@gothicpriestess16]

Excellent video!! Really helps understand every aspect of the modeling and the interpretation of the output

[@jonbstatsandpsych6340]

Thank you for watching and for your feedback!

[@flaviethevenard5109]

Thank you very much for such a precise crash sourse on longitudinal modelling, forever grateful !

[@shikharbhagoliwal6608]

This was an amazing video to watch and got a clear understanding of Longitudinal data. Can I please get the data set so that I can practice the models with this data set?

[@taiwankyh]

Very nice and clear explanation

[@arikimelman3640]

This is incredible, thank you

[@jasonmoy8639]

For whoever see this video later than I am, you don't need to manually calculate ICC. Use the ICC function in the performance package. Also, people have argued the benefit of using lme (if your data is inherently multilevel) even with low ICC.

[@kar2194]

Hi Jon, first thank you for the wonderful video! A question from me and I would really appreciate if you could help. What is the data type of the Job site, ID, Days_of_Training? are they , , ? I am actually confused with data type for multilevel modeling, My dataset has 4 columns, example: Countries levels: Australia, US, Thailand, Malaysia.. Status levels: Developed, Developing, Year : 2000, 2001, 2002, 2003, 2004 Life expectancy : 87, 76, 69, 64 Should I just convert Year to numeric, and having 2000 as 0, 2001 as 1, 2002 as 2, 2004 as 4 ? Many thanks mate

[@rezat.ashtiani1338]

Thank you. It was really helpful

[@nhelsabeck]

I have a question, if we have missing values in our outcome, nlme gives an error message. From what I have read online the suggestion is to set the argument na.action to equal na.omit. However, that eliminates the missing values. Shouldn't setting method to ML as you do in this video allow for the model to accommodate those missing values?

[@shannongutenkunst3050]

I have the same question.

[@alejandrarodriguezsanchez6667]

just clarification. in the null model there is a random intercept effect. it is even estimated. if you want to take it out, then -1 should be set as an option after random= ... other than that, great video!

[@DemetriusKGreen]

Great video! Does the "Time" variable need to be continuous like you have them labeled in the data (0, 1, 2, 3) or can they be factors (month_year, quarter, season, etc.) I know factors require dummy variables so I'm interested to know best practices.

[@navotnaor]

Hi, these are great videos, quick question, if wanted to also fit a quadratic model, how would i do that? Thank you

[@juditm9290]

Hallo, thanks for the video this is super helpful! What happens when the intercept in the unconditional model is not significant? Do i just ignore and proceed with building the models?

[@milanfilipovic3648]

Since some people missed days of training, why didn't you need to include an na.exclude argument in your lme function?

[@lailimade]

i think lme function defaults to na.omit

[@katiekurczynski]

This was SUPER helpful for me. Now can you do one with a mediational hypothesis 😝 thanks for the videos!!

[@jonbstatsandpsych6340]

Thanks for watching! And thanks for the comment! Much appreciated!

[@MP-wf8sw]

Great! Thank you!!

[@jaquelinearagoni5226]

thank you very much!!

[@leonieg3218]

This is great. Thank you!

[@audreyaday6543]

Awesome video. Super helpful! :-)

[@borjaaramburumunoa1291]

Does anybody knows where can I find the data frame with wich he is working in the video?

[@MZ-pj4eq]

Thanks for the videos^^

[@jonbstatsandpsych6340]

Appreciate the comment! Thanks for watching.

[@fansofihp1404]

Nice