sem-in-r / seminr

Natural feeling domain-specific language for building structural equation models in R for estimation by covariance-based methods (like LISREL/Lavaan) or partial least squares (like SmartPLS)
58 stars 19 forks source link

Error in as.POSIXlt.character(x, tz, ...) : character string is not in a standard unambiguous format" #352

Open rcomeau2024 opened 4 days ago

rcomeau2024 commented 4 days ago

Hello,

I'm trying to resolve an issue while running estimate_pls() in RStudio. From browsing the internet, this error occurs when variables have dates. My data constructs don't have any dates in them. Both measurement and structural model load fine.

The data is coming from an SPSS SAV file, which I have loaded in a dataframe. I even extracted the data frame into an Excel file to reload the excel file in my data frame. I still get the same error.

Thank you!

Here's part of my code after loading the data:

MM <- constructs( composite("MSR", single_item("MANIP_SR")), composite("CSR_Importance", multiitems(("CSRIMP"),1:13), weights = mode_B), composite("Psych_Contract", multiitems(("PSYCCON"), 1:9), weights = mode_B), composite("Affect_Commit", multiitems(("AFFECT"), 1:8), weights = mode_B), composite("Job_Satisfaction", multiitems(("CONTIN"),1:9), weights = mode_B), composite("Trust_Management", multiitems(("TRUSTINMG"),1:6), weights = mode_B), composite("JA", single_item(("JOB_AVAIL"))), composite("Turnover_intentions", multiitems(("TURNOVIN"),1:3)), interaction_term(iv = "Psych_Contract", moderator = "CSR_Importance", method = two_stage), interaction_term(iv = "TURN", moderator = "JA", method = two_stage))

turnover_intentions_sm_mod <- relationships( paths(from = c("MSR"), to = c("Psych_Contract")), paths(from = c("CSR_Importance", "Psych_Contract", "CSR_ImportancePsych_Contract"), to = c("Psych_Contract")), paths(from = c("Psych_Contract", "Job_Satisfaction"), to = c("Turnover_intentions")), paths(from = c("Psych_Contract", "Affect_Commit"), to = c("Turnover_intentions")), paths(from = c("Psych_Contract", "Trust_Management"), to = c("Turnover_intentions")), paths(from = c("JA", "Turnover_intentions", "JATurnover_intentions"), to = c("Turnover_intentions")) )

turnover_intentions_pls_model_mod <- estimate_pls ( data = csr, measurement_model = MM, structural_model = turnover_intentions_sm_mod, inner_weights = path_weighting, missing = mean_replacement, missing_value = "-99" )