Data Analysis / Statistics

Home › forum / support › b) MEA – forum and support › Data Analysis / Statistics

Tagged: 

Viewing 9 reply threads
  • Author
    Posts
    • February 10, 2016 at 5:32 pm #213
      fabian
      Keymaster

      Here you may post your questions / findings / solutions regarding data analysis and statistical procedures. Thanks!

    • April 12, 2016 at 6:46 pm #261
      Asef Antonio
      Participant

      Dear Fabian, I’m new using MEA and would like to ask about the method to take data from the program to enter it in a statistical software.
      What statistical software do you recommend for analysis ?
      regards
      Asef

    • June 6, 2016 at 12:14 pm #265
      fabian
      Keymaster

      Dear Asef,
      The most convenient way is to use R.
      Cross-correlation analysis may be done with e.g. the “ccf” function.
      A scripted version for the synchrony-analysis in R will be published in the near future.
      Best, Fabian

    • March 16, 2018 at 5:53 pm #342
      fabian
      Keymaster

      Some things take longer than anticipated …
      The script I have been talking about is now available on CRAN:

      https://CRAN.R-project.org/package=rMEA

      Cheers, Fabian

    • October 2, 2018 at 2:15 pm #365
      EdithHerden
      Participant

      Dear Fabian,

      I analysed a video with the MEA program and would like to controle the raw DATA now. For this i downloaded rMEA from CRAN but I do not know how to open the program. Do I need an additional program to see the raw data?

      Cheers, Edith

      • October 12, 2018 at 8:52 am #367
        fabian
        Keymaster

        Hi Edith,
        Yes, you need the program R.
        It is freely available and runs on all popular platforms. I suggest using R-Studio, which has a very nice user interface.

        Best, Fabian

    • October 4, 2018 at 11:06 am #366
      EdithHerden
      Participant

      Do I need a version of r to see my Data as graphs?

      • October 12, 2018 at 9:06 am #368
        fabian
        Keymaster

        rMEA works with the current version of R (3.5.x), and it should run on older versions too. Please refer to the rMEA documentation for further details.
        A paper describing rMEA is coming soon. We will announce it here, once it is ready.

    • March 19, 2019 at 4:21 pm #385
      carolinegos
      Participant

      Hi,

      I’m just wondering how to extract the data from MEA into R? I’ve downloaded the crqa package but I’m not sure how to link the data in from MEA into R. Do I need to label the raw data in a certain way?

      Best wishes

    • March 20, 2019 at 11:17 am #386
      fabian
      Keymaster

      Hi, I am not sure what you mean by “extract”?
      If you want to access your MEA-data in R, you simply have to save the results of your MEA-analysis as a .txt-file. Then you point your R-package/analysis to this file/folder and from there, you’ll be able to run your statistical analyses.
      This is really simple in rMEA: use readMEA and specify the parameters of your choice.
      In CRQA, this will be probably similar, please refer to the information available for the CRQA-package.

      Best, Fabian

    • June 24, 2022 at 12:12 pm #648
      James Smith
      Participant

      I used the MEA programme to analyse a movie, and now I want to have control over the raw data.
      magento 2 development services

      • August 15, 2022 at 5:22 pm #658
        fabian
        Keymaster

        Hi,
        Once you save your raw-data (as a .txt-file in the MEA-application), you will have full control over your data.
        I suggest using the R-package rMEA: This will allow you to check and analyze your raw-data from MEA in a convenient way.
        https://cran.r-project.org/web/packages/rMEA/index.html

        Cheers, Fabian

    • October 1, 2022 at 3:07 am #667
      minisharmaa
      Participant

      Dear Fabian,
      In our experiment, we are analyzing the mother-child interaction. As we know MEA only performs quantitative analyses, not qualitative analyses. That means even if two participants will move randomly together without actually getting into synch then also it will show the synchronization between the participants. My question is when we draw the ROI for a mother and a child the area of the mother’s ROI is always greater than the child’s ROI. so when they will move randomly the pixel change in the mother’s ROI will always be greater than the child’s ROI. Is there any way to normalize these two-time series? Also, does the function rescaled in your package perform the same as normalization at its default setting?
      Thank you for the help!

      • October 11, 2022 at 7:06 am #671
        fabian
        Keymaster

        Dear minisharmaa,
        You are correct in what you state above. The most straightforward solution to the problem of different sized ROIs is using rMEA (R-package), where you can apply the z-transformation of your raw MEA-data (withoug centering the data).
        e.g. –>
        ## rescale with standard deviation
        mea_scaled = MEAscale(mea_raw, scale = “sd”, center = F, removeNA = TRUE)

        For more details, see:
        Kleinbub, J. R., & Ramseyer, F. T. (2021). rMEA: An R package to assess nonverbal synchronization in motion energy analysis time-series. Psychotherapy Research, 31(6), 817-830. doi:10.1080/10503307.2020.1844334

        Best, Fabian

  • Author
    Posts
Viewing 9 reply threads
  • You must be logged in to reply to this topic.