[R-sig-ME] Dyadic growth curve

[Marta Vigier]

Dear R Experts,

I fitted a dyadic growth curve (two intercept model) with stability and
influence model (R. Garcia) and found a lagged synchrony between doctors'
and patients' Heart Rate Variability (HRV).
I have been wondering if it would be possible to adapt the syntax in order
to see when do the doctors predict patients' HRV. In other words, if
patients follow their doctors when doctors' HRV is higher or lower.
Also, the patients are nested within doctors (18 doctors and 103 patients,
one with many design), thus I created a DocID for each doctor. How could I
include this into the syntax?
I would be very grateful for any help or advice.

log_RMSSDms.2 -patients' HRV
Doc_Pat.1 -string variable with role function DOC or PAT
Clog_RMSSDms.1_lag-centered and lagged doctors' HRV
Clog_RMSSDms.2_lag cantered and lagged patients' HRV

Here is my model:
library(dyadr)
library(dplyr)
library(nlme)


ctrl <- lmeControl(msMaxIter=10000,
                   MaxIter=100000,
                   msMaxEval=10000,
                   returnObject=TRUE,
                   niterEM=10000,
                   nlmStepMax=1000)

stab_infl_2int  <- lme(log_RMSSDms.2 ~ Doc_Pat.1 +
Doc_Pat.1:Clog_RMSSDms.2_lag
                       + Doc_Pat.1:Clog_RMSSDms.1_lag - 1,
                       data = Final_data_moderators_1,
                       random = ~ Doc_Pat.1 + Doc_Pat.1:Clog_RMSSDms.2_lag
                       + Doc_Pat.1:Clog_RMSSDms.1_lag - 1|Dyad_ID,
                       correlation = corCompSymm(form = ~1|Dyad_ID/obs_ID),

                       weights = varIdent(form = ~1|Doc_Pat.1),
                       na.action = na.omit,
                       control = ctrl)
smallsummary(stab_infl_2int)

Best regards,

Marta



<https://goo.gl/maps/Zssze>

	[[alternative HTML version deleted]]