The 12th Invest in ME Research Conference June, 2017, Part 2
MEMum presents the second article in a series of three about the recent 12th Invest In ME International Conference (IIMEC12) in London.
Discuss the article on the Forums.

Effect sizes of primary outcome measures in PACE Trial?

Discussion in 'Latest ME/CFS Research' started by Tom Kindlon, Dec 22, 2016.

  1. Tom Kindlon

    Tom Kindlon Senior Member

    Messages:
    1,464
    Likes:
    8,448
    I was wondering whether anyone could calculate the effect sizes for the 2 primary outcome measures, Chalder fatigue questionnaire score and SF-36 physical functioning subscale score in the PACE Trial for baseline versus 52 weeks for (i) CBT and (ii) compared to GET specialist medical care alone.

    The full text of the paper can be read here: http://www.thelancet.com/journals/lancet/article/PIIS0140-6736(11)60096-2/fulltext

    Alternatively the figures could be calculated from the raw data. The file for this is available here:
    https://sites.google.com/site/pacefoir/pace-ipd_foia-qmul-2014-f73.xlsx
    Readme file: https://sites.google.com/site/pacefoir/pace-ipd-readme.txt

    If this could be done in the next few days it would be great.

    If you prefer you can contact me off-list.
    My email address is tomkindlon @ Gmail dot com
     
    Invisible Woman and Demepivo like this.
  2. wdb

    wdb Senior Member

    Messages:
    1,381
    Likes:
    2,981
    London
    Is this what you want ?

    Code:
    > # SF36 - comparing baseline with 52 week score for each arm
    > cohensD(subset(pace_data,arm_name=="GET")$SF36_Base,subset(pace_data,arm_name=="GET")$SF36_52w)
    [1] 0.9721292
    > cohensD(subset(pace_data,arm_name=="CBT")$SF36_Base,subset(pace_data,arm_name=="CBT")$SF36_52w)
    [1] 0.9565955
    > cohensD(subset(pace_data,arm_name=="APT")$SF36_Base,subset(pace_data,arm_name=="APT")$SF36_52w)
    [1] 0.4122312
    > cohensD(subset(pace_data,arm_name=="SMC")$SF36_Base,subset(pace_data,arm_name=="SMC")$SF36_52w)
    [1] 0.5687265
    >
    > # Chalder - comparing baseline with 52 week score for each arm
    > cohensD(subset(pace_data,arm_name=="GET")$CF_L_Base,subset(pace_data,arm_name=="GET")$CF_L_52w)
    [1] 1.285339
    > cohensD(subset(pace_data,arm_name=="CBT")$CF_L_Base,subset(pace_data,arm_name=="CBT")$CF_L_52w)
    [1] 1.213373
    > cohensD(subset(pace_data,arm_name=="APT")$CF_L_Base,subset(pace_data,arm_name=="APT")$CF_L_52w)
    [1] 0.9208464
    > cohensD(subset(pace_data,arm_name=="SMC")$CF_L_Base,subset(pace_data,arm_name=="SMC")$CF_L_52w)
    [1] 0.8436206
    >
    > # SF36 - Comparing each arm with SMC at 52 weeks
    > cohensD(subset(pace_data,arm_name=="SMC")$SF36_52w,subset(pace_data,arm_name=="GET")$SF36_52w)
    [1] 0.2693272
    > cohensD(subset(pace_data,arm_name=="SMC")$SF36_52w,subset(pace_data,arm_name=="CBT")$SF36_52w)
    [1] 0.3017153
    > cohensD(subset(pace_data,arm_name=="SMC")$SF36_52w,subset(pace_data,arm_name=="APT")$SF36_52w)
    [1] 0.1959534
    > cohensD(subset(pace_data,arm_name=="SMC")$SF36_52w,subset(pace_data,arm_name=="SMC")$SF36_52w)
    [1] 0
    >
    > # Chalder - Comparing each arm with SMC at 52 weeks
    > cohensD(subset(pace_data,arm_name=="SMC")$CF_L_52w,subset(pace_data,arm_name=="GET")$CF_L_52w)
    [1] 0.4579197
    > cohensD(subset(pace_data,arm_name=="SMC")$CF_L_52w,subset(pace_data,arm_name=="CBT")$CF_L_52w)
    [1] 0.4855782
    > cohensD(subset(pace_data,arm_name=="SMC")$CF_L_52w,subset(pace_data,arm_name=="APT")$CF_L_52w)
    [1] 0.09677324
    > cohensD(subset(pace_data,arm_name=="SMC")$CF_L_52w,subset(pace_data,arm_name=="SMC")$CF_L_52w)
    [1] 0
    >
     

See more popular forum discussions.

Share This Page