Add an evaluation criterion to a hypothesis in a study object
add_eval(study, type, evaluation, description = "", hypothesis_id = NULL)
study | A study list object with class scivrs_study |
---|---|
type | "corroboration" or "falsification" (or "c"/"f") |
evaluation | A logical representation of these conditions using the criteria IDs, parentheses, &, | and ! (e.g., "(c1 & c2) | (c3 & !c4)") |
description | A verbal description of the conditions for corroborating the hypothesis |
hypothesis_id | The id for the hypothesis (index or character) if NULL, assigns to the last hypothesis in the list |
A study object with class scivrs_study
s <- study() %>% add_hypothesis("H1", "Petal width and length will be positively correlated.") %>% add_analysis("A1", cor.test(dat$Petal.Width, dat$Petal.Length)) %>% add_criterion("sig", "p.value", "<", 0.05) %>% add_criterion("pos", "estimate", ">", 0) %>% add_eval("corroboration", "sig & pos", "Petal width is significantly and positively correlated to length" ) %>% add_eval("falsification", "sig & !pos", "Petal width is significantly and negatively correlated to length" ) s#> Demo Study #> ---------- #> #> * Hypotheses: H1 #> * Data: None #> * Analyses: A1 #> #> Hypothesis H1: Petal width and length will be positively correlated. #> #> Criterion sig: #> * p.value < 0.05 is unknown #> * p.value = p.value #> #> Criterion pos: #> * estimate > 0 is unknown #> * estimate = estimate #> #> Conclusion: You may need to run `study_analyse()` #> * Corroborate (sig & pos): #> * Falsify (sig & !pos):