acmilannesta / patzer-txteam-codes

Useful programming codes for various analysis

Programming Codes Repository

This is the repository for sharing programming codes (mainly in SAS, R or Python) for statistical analysis. You are more than welcome to add your code to the repository.

Current covered topics include:

1. Survival analysis
   1.1. Cox PH regression
   1.2. Cumulative incidence curve
   1.3. Competing risk moel (Fine & Gray model, SIPW Cox model, etc.)
   1.4. Adjusted survival curves
2. Generalized Linear model
   2.1 Check linear assumptions
   2.2 Generalize linear model examples
3. Data visualisation (currently only GGplot in R)
4. Multiple imputation
   4.1 Multiple imputation using proc logistic and phreg
   4.2 MICE (multiple imputation chain equations)
   4.3 Random forest multiple imputation ("ranger")
5. Machine learning
   5.1 Light gradient boosting model (LGBM)
   5.2 Categorical gradient boosting model (Catboost)
   5.3 NLP LSTM model
   5.4 NLP Bert model
6. Data manipulation (cuurently only cover R package "dplyr")
7. Journal style reporting in R
   7.1 Table 1 reporting (Characteristics of subjects by main exposure)
   7.2 Model effect size table

How to create a folder in repository

1. Create new file
2. type "FOLDER_NAME/FILE_NAME"
3. committ new file

How to access this repository

1. Install git
   Windows: https://git-scm.com/download/win
   MAC: https://git-scm.com/download/mac
2. Make sure you add git to your environmental variable
3. Open command windown and type git clone https://github.com/acmilannesta/Patzer-TxTeam-Codes local_path