Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/neuropsychology/Psycho.jl
The Julia Toolbox for Psychological Science
https://github.com/neuropsychology/Psycho.jl
Last synced: 16 days ago
JSON representation
The Julia Toolbox for Psychological Science
- Host: GitHub
- URL: https://github.com/neuropsychology/Psycho.jl
- Owner: neuropsychology
- License: mit
- Created: 2018-09-01T08:13:10.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2018-11-14T12:47:00.000Z (almost 6 years ago)
- Last Synced: 2024-08-01T00:57:37.504Z (3 months ago)
- Language: Julia
- Homepage: https://neuropsychology.github.io/Psycho.jl/latest/
- Size: 502 KB
- Stars: 7
- Watchers: 2
- Forks: 2
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
*
The Julia Toolbox for Psychological Science*
# Psycho.jl
[](https://travis-ci.org/neuropsychology/Psycho.jl)
[](https://ci.appveyor.com/project/DominiqueMakowski/psycho-jl)
[](https://neuropsychology.github.io/Psycho.jl/latest/)
[](https://codecov.io/gh/neuropsychology/Psycho.jl)
[](http://hits.dwyl.io/neuropsychology/neuropsychology/psycho.jl)
# Goal
***"From Julia to Manuscript"***
`Psycho`'s primary goal is to fill the gap between Julia's output and the formatted result description of your manuscript, with the automated use of **best practices** guidelines, ensuring standardization and quality of results reporting.
It also provides useful tools and functions for psychologists, neuropsychologists and neuroscientists for their everyday data analyses.
# Contribute
`Psycho.jl` **is a young package in need of affection**. You can easily hop aboard the [developpment](.github/CONTRIBUTING.md) of this open-source software and improve psychological science by doing the following:
- Create or check existing 
issues to report, replicate, understand or solve some bugs.
- Create or check existing 
issues to suggest or discuss a new feature.
- Check existing 
issues to see things that we'd like to implement, but where help is needed to do it.
- Check existing 
issues to give your opinion and participate in package's design discussions.
Don't be shy, try to code and submit a pull request (See the [contributing guide](.github/CONTRIBUTING.md)). Even if unperfect, we will help you make it great! All contributors will be very graciously rewarded someday :smirk:.
# Installation
```
pkg> add https://github.com/neuropsychology/Psycho.jl.git
```
# Documentation
- Reports: Interpret and report your models
- Effect Sizes: Rules of thumb and interprettation
- Signal Detection Theory: SDT's related indices
# Examples
## Report all the things 
### Data
```julia
using Psycho
# Simulate some data
data = simulate_data_correlation([[0.3], [0.1]])
# Standardize the results
standardize!(data)
# Describe the data
report(data)
```
```
The data contains 200 observations of the following variables:
- y (Mean = 0 ± 1.0 [-2.92, 3.07])
- Var1 (Mean = 0 ± 1.0 [-2.35, 3.25])
- Group (1FD, 50.0%; 2HA, 50.0%)
```
### Linear Models (GLM)
```julia
using GLM
# Fit a Linear Model
model = lm(@formula(y ~ Var1 * Group), data)
# Report the results
results = report(model)
```
```
We fitted a linear regression to predict y with Var1 and Group (Formula: y ~ 1 + Var1 + Group + Var1 & Group).
The model's explanatory power (R²) is of 0.05 (adj. R² = 0.04). The model's intercept is at 0.0. Within this model:
- Var1 is significant (Coef = 0.3, t(196) = 3.05, 95% CI [0.11; 0.49], p < .01) and can be considered as small (Std. Coef = 0.3).
- Group: 2HA is not significant (Coef = 0, t(196) = 0, 95% CI [-0.27; 0.27], p > .1) and can be considered as very small (Std. Coef = 0).
- Var1 & Group: 2HA is not significant (Coef = -0.2, t(196) = -1.44, 95% CI [-0.47; 0.07], p > .1) and can be considered as very small (Std. Coef = -0.2).
```
## Signal Detection Theory (SDT)
```julia
sdt_indices(hit=6, fa=7, miss=8, cr=9)
```
```
Dict{String,Float64} with 10 entries:
"hit_rate" => 0.428571
"fa_rate" => 0.4375
"dprime" => -0.0235319
"beta" => 0.995497
"c" => 0.191778
"c_relative" => -8.14973
"Xc" => 0.180012
"aprime" => 0.490992
"bpp" => 0.263158
"pr" => -0.00892857
"br" => 0.433628
"dprime_glm" => -0.0227017
"Xc_glm" => 0.157311
```