angelospsy/multifear

A suite of functions for running multiverse analyses for fear conditioning data.

Welcome fellows

My name is Angelos and I am currently working at Utrecht University and KU Leuven. I am mostly interested in avoidance learning, pain, fear, anxiety disorders, and computational modelling. If you want to know more about me, check my website at https://www.akrypotos.com.

multifear's Issues

Implement the updated version of the rep measures ANOVA

New method is described here: https://psyarxiv.com/fb8zn/

Issue with basic example

Hi!
Thank you for putting together the package, I'm really excited about it. Today I tried to use it for the first time, but run into an error message. Can you help me solve it?

Error in dplyr::mutate(., method = ttl$alternative, x = "cs", y = dv, : object 'ttl' not found
6.
dplyr::mutate(., method = ttl$alternative, x = "cs", y = dv, exclusion = exclusion, cut_off = cut_off, model = "t-test", controls = NA, framework = "NHST")
5.
dplyr::select(., x, y, exclusion, cut_off, model, controls, method, p.value, effect.size, effect.size.ma, effect.size.ma.lci, effect.size.ma.hci, estimate, statistic, conf.low, conf.high, framework)
4.
dplyr::mutate(., data_used = list(data))
3.
ttl %>% dplyr::mutate(method = ttl$alternative, x = "cs", y = dv, exclusion = exclusion, cut_off = cut_off, model = "t-test", controls = NA, framework = "NHST") %>% dplyr::select(x, y, exclusion, cut_off, model, controls, method, p.value, effect.size, ...
2.
multifear::t_test_mf(cs1 = cs1, cs2 = cs2, data = data, subj = subj, paired = paired, phase = phase, exclusion = exclusion, cut_off = cut_off, meta.effect = meta.effect)
1.
multifear::universe_cs(cs1 = cs1, cs2 = cs2, data = Mega_wideNA, subj = "ID_Maya", group = NULL, phase = "recall", include_bayes = FALSE)

Confirm that all the selection criteria used in the literature are applied

more functionality?

Excellent work, I greatly appreciate all your effort you put into this project!
I have a few ideas on how to expand the relevant functionalities:
What about including the option of having more than two CS, e.g. a three CS design or a 2x2 design, e.g. using CS+/CS- as one within-subjects factor and female/male face as another within-subjects factor? This would certainly add even more possible statistical comparisons, but the whole package would become even more flexible and stronger. What do you think?

Best wishes!
Christian

Create specification curve analysis

Speed Up Bayesian ANOVA

Solved with 2549a50

Use example_data, run all analyses in JASP and check the results with the ones returned by the function

Create summary statistics for Bayesian results

Breaking bayestestR update

Hi, we're about to update bayestestR on CRAN, which will break one example and two tests in your package due to the following change: the Bayes factors functions now return the column log_BF instead of BF (and the log has to be exponentiated to get back to "normal" BFs).

Apologies for the breaking change, and let us know if you need any help to fix it :)

Package: multifear
Check: examples
New result: ERROR
  Running examples in ‘multifear-Ex.R’ failed
  The error most likely occurred in:
  
  > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
  > ### Name: rm_banova_mf
  > ### Title: rm_banova_mf
  > ### Aliases: rm_banova_mf
  > 
  > ### ** Examples
  > 
  > # Briefly define argument values that will be plugged in later on in the functions.
  > # We only use two trials as the function takes a long time to run.
  > 
  > cs1 <- paste0("CSP", 1:2)
  > cs2 <- paste0("CSM", 1:2)
  > subj <- "id"
  > 
  > # Bayesian Repeated measures ANOVA without groups
  > rm_banova_mf(cs1 = cs1, cs2 = cs2, subj = subj,
  + data = example_data, time = TRUE)
  Error: Can't subset columns that don't exist.
  ✖ Column `BF` doesn't exist.
  Backtrace:
       â–ˆ
    1. ├─multifear::rm_banova_mf(...)
    2. │ └─`%>%`(...)
    3. ├─dplyr::select(., BF)
    4. └─dplyr:::select.data.frame(., BF)
    5.   └─tidyselect::eval_select(expr(c(...)), .data)
    6.     └─tidyselect:::eval_select_impl(...)
    7.       ├─tidyselect:::with_subscript_errors(...)
    8.       │ ├─base::tryCatch(...)
    9.       │ │ └─base:::tryCatchList(expr, classes, parentenv, handlers)
   10.       │ │   └─base:::tryCatchOne(expr, names, parentenv, handlers[[1L]])
   11.       │ │     └─base:::doTryCatch(return(expr), name, parentenv, handler)
   12.       │ └─tidyselect:::instrument_base_errors(expr)
   13.       │   └─base::withCallingHandlers(...)
   14.       └─tidyselect:::vars_select_eval(...)
   15.         └─tidyselect:::walk_data_tree(expr, data_mask, context_mask)
   16.           └─tidyselect:::eval_c(expr, data_mask, context_mask)
   17.             └─tidyselect:::reduce_sels(node, data_mask, context_mask, init = init)
   18.               └─tidyselect:::walk_data_tree(new, data_mask, context_mask)
   19.                 └─tidyselect:::as_indices_sel_impl(...)
   20.                   └─tidyselect:::as_indices_impl(x, vars, strict = strict)
   21.                     └─tidyselect:::chr_as_locations(x, vars)
   22.                       └─vctrs::vec_as_location(x, n = length(vars), names = vars)
   23.                         └─(function () ...
   24.                           └─vctrs:::stop_subscript_oob(...)
   25.                             └─vctrs:::stop_subscript(...)
  Execution halted

Package: multifear
Check: tests
New result: ERROR
    Running ‘testthat.R’ [37s/37s]
  Running the tests in ‘tests/testthat.R’ failed.
  Complete output:
    > library(testthat)
    > library(multifear)
    > 
    > test_check("multifear")
    �� Failed tests ����������������������������������������������������������������
    ── Error (test.output.R:47:3): rm_banova_mf works ──────────────────────────────
    Error: Can't subset columns that don't exist.
    ✖ Column `BF` doesn't exist.
    Backtrace:
         â–ˆ
      1. ├─testthat::expect_known_output(...) test.output.R:47:2
      2. │ ├─base::append(act, eval_with_output(object, print = print, width = width))
      3. │ └─testthat:::eval_with_output(object, print = print, width = width)
      4. │   ├─withr::with_output_sink(temp, withVisible(code))
      5. │   │ └─base::force(code)
      6. │   └─base::withVisible(code)
      7. ├─multifear::rm_banova_mf(cs1, cs2, subj = subj, data = example_data)
      8. │ └─`%>%`(...)
      9. ├─dplyr::select(., BF)
     10. └─dplyr:::select.data.frame(., BF)
     11.   └─tidyselect::eval_select(expr(c(...)), .data)
     12.     └─tidyselect:::eval_select_impl(...)
     13.       ├─tidyselect:::with_subscript_errors(...)
     14.       │ ├─base::tryCatch(...)
     15.       │ │ └─base:::tryCatchList(expr, classes, parentenv, handlers)
     16.       │ │   └─base:::tryCatchOne(expr, names, parentenv, handlers[[1L]])
     17.       │ │     └─base:::doTryCatch(return(expr), name, parentenv, handler)
     18.       │ └─tidyselect:::instrument_base_errors(expr)
     19.       │   └─base::withCallingHandlers(...)
     20.       └─tidyselect:::vars_select_eval(...)
     21.         └─tidyselect:::walk_data_tree(expr, data_mask, context_mask)
     22.           └─tidyselect:::eval_c(expr, data_mask, context_mask)
     23.             └─tidyselect:::reduce_sels(node, data_mask, context_mask, init = init)
     24.               └─tidyselect:::walk_data_tree(new, data_mask, context_mask)
     25.                 └─tidyselect:::as_indices_sel_impl(...)
     26.                   └─tidyselect:::as_indices_impl(x, vars, strict = strict)
     27.                     └─tidyselect:::chr_as_locations(x, vars)
     28.                       └─vctrs::vec_as_location(x, n = length(vars), names = vars)
     29.                         └─(function () ...
     30.                           └─vctrs:::stop_subscript_oob(...)
     31.                             └─vctrs:::stop_subscript(...)
    ── Error (test.output.R:51:3): rm_banova_mf for groups works ───────────────────
    Error: Can't subset columns that don't exist.
    ✖ Column `BF` doesn't exist.
    Backtrace:
         â–ˆ
      1. ├─testthat::expect_known_output(...) test.output.R:51:2
      2. │ ├─base::append(act, eval_with_output(object, print = print, width = width))
      3. │ └─testthat:::eval_with_output(object, print = print, width = width)
      4. │   ├─withr::with_output_sink(temp, withVisible(code))
      5. │   │ └─base::force(code)
      6. │   └─base::withVisible(code)
      7. ├─multifear::rm_banova_mf(...)
      8. │ └─`%>%`(...)
      9. ├─dplyr::select(., BF)
     10. └─dplyr:::select.data.frame(., BF)
     11.   └─tidyselect::eval_select(expr(c(...)), .data)
     12.     └─tidyselect:::eval_select_impl(...)
     13.       ├─tidyselect:::with_subscript_errors(...)
     14.       │ ├─base::tryCatch(...)
     15.       │ │ └─base:::tryCatchList(expr, classes, parentenv, handlers)
     16.       │ │   └─base:::tryCatchOne(expr, names, parentenv, handlers[[1L]])
     17.       │ │     └─base:::doTryCatch(return(expr), name, parentenv, handler)
     18.       │ └─tidyselect:::instrument_base_errors(expr)
     19.       │   └─base::withCallingHandlers(...)
     20.       └─tidyselect:::vars_select_eval(...)
     21.         └─tidyselect:::walk_data_tree(expr, data_mask, context_mask)
     22.           └─tidyselect:::eval_c(expr, data_mask, context_mask)
     23.             └─tidyselect:::reduce_sels(node, data_mask, context_mask, init = init)
     24.               └─tidyselect:::walk_data_tree(new, data_mask, context_mask)
     25.                 └─tidyselect:::as_indices_sel_impl(...)
     26.                   └─tidyselect:::as_indices_impl(x, vars, strict = strict)
     27.                     └─tidyselect:::chr_as_locations(x, vars)
     28.                       └─vctrs::vec_as_location(x, n = length(vars), names = vars)
     29.                         └─(function () ...
     30.                           └─vctrs:::stop_subscript_oob(...)
     31.                             └─vctrs:::stop_subscript(...)
    
    [ FAIL 2 | WARN 1 | SKIP 0 | PASS 15 ]
    Error: Test failures
    Execution halted

Add all analyses as regressions

• Did that for t-test.
• For the ANOVAs we have the mixed models which is the same