Load data.

Descriptives

How many participants in each condition?

## Source: local data frame [4 x 3]
## Groups: training_condition [?]
## 
##   training_condition          experiment   n()
##                (chr)               (chr) (int)
## 1      active_active positive_rh_passive    50
## 2      active_active      random_passive    48
## 3    passive_passive positive_rh_passive    50
## 4    passive_passive      random_passive    45

How long did each condition take?

## Source: local data frame [4 x 4]
## Groups: training_condition [?]
## 
##   training_condition          experiment m_train_time m_exp_time
##                (chr)               (chr)        (dbl)      (dbl)
## 1      active_active positive_rh_passive    0.6306516   4.383012
## 2      active_active      random_passive    0.6530123   4.719400
## 3    passive_passive positive_rh_passive    0.5764330   4.403786
## 4    passive_passive      random_passive    0.6121737   4.380315

SS level filtering

Remove: - Participants who were scored perfect on the pretest - Participants who’s difference scores were 3 SD away from the mean difference score

Visualization

Relational test broken down by question and block

Entity tests broken down by question and block

Overall accuracy analysis for each test

Within subjects change scores for all shapes

Accuracy on the learned shape

Relational tests for learned shape

Entity tests for learned shape

Overall accuracy change on Rhombus

Within subjects change scores for Rhombus

Exploratory Analyses

Overall accuracy analysis collapsing across entity and relational tests shape learned

Overall accuracy for shape learned collapsing across tests

Total difference score analysis

Total difference score analysis for learned shape

Plot

Separate by question

Separate by shape tested

Analysis based on individual ss pretest knowledge of rhombus (entity)

Does your pretest rhombus knowledge predict how you will do at test? Do we see condition differences based on pretest rhombus knowledge

Analysis based on evidence given or selected

Munge training data, so we can score them.

Score the training data for each participant

Models (todo)

Predict overall accuracy based on condition and test type

Predict accuracy for learned shape based on condition and test type

Predict change scores for learned shape based on condition and test type