mmi_tvalue: Multimodel averaging with t-values
In jpwrobinson/funk: James Robinson's functions, attributed where stolen

Function builds GLM, runs multi-model inference to produce: 1. Standardized t-values (and standard error) for each covariate across full model set (effect sizes) 2. R-squareds of each model < 7 AICc of top model 3. Predicted y across each covariate, weighted by AIC for all models < 7 AICc of top model (and variance in predictions)

mmi_tvalue(
  M_FULL,
  dataset,
  exp.names,
  ranef,
  indicator,
  family,
  t.subset = FALSE
)

`dataset`	= dataset containing y and all x covariates. should be scaled and centered (mean = 0, sd = 1)
`exp.names`	= explanatory covariate names, passed as vector of characters
`indicator`	= y variable of interest (character)
`family`	= GLM family distribution, takes 'gaussian' or 'Gamma'