Introduction to R Software

R is a open source statistical software. R
software can be downloaded from the following link . https://www.r-project.org/

There are few GUI available for R software

Starting the R environment (This page uses the R-Studio GUI for examples )

Please double click the the R-Studio icon and the following window opens

The left top most window is called 'source' where the r codes are usually written and left bottom window is the R-Console

where the codes are executed. Press the run button in the source window to run the code

Basic Concepts

There are few GUI available for R software

Starting the R environment (This page uses the R-Studio GUI for examples )

Please double click the the R-Studio icon and the following window opens

The left top most window is called 'source' where the r codes are usually written and left bottom window is the R-Console

where the codes are executed. Press the run button in the source window to run the code

Basic Concepts

**1. Package and Library**

R software uses the concept called packages for various operations which needs to be downloaded and installed in the space

called R Library. To use the package, type the following syntax and press run

library

2.

**Frequently used packages**

The following are the frequently used packages

S.No | Package | Type | remarks |

1 | stat | Basic Statistical function | Builtin |

2 | Randomforest | Classification and regression | |

3 | foreign | Data Connection | Read and write data from other packages such as SPSS and SAS |

4 | XL connect | Data Connection | Read and write data from excel |

5 | RODBC | Data Connection | Connect to a database through ODBC |

6 | xtable | Data Handling | |

7 | hmisc | Data Handling | |

8 | rcurl | Data Handling | |

9 | plyr | Data Handling | |

10 | pastecs | Descriptive Statistics | Display summary statistics |

11 | ggplot2 | Graphical display | Graphical display of data |

12 | lattice | Graphical Display | Graphical display of data |

13 | mlogit | Logit Model | Maximum Likelihood |

14 | nlme | Mixed Effects Model | Linear and Nonlinear |

15 | lme4 | Mixed Effects Model | Linear and Generalized S4 models |

16 | caret | Predictive Modeling | Predictive Modeling |

17 | xml | Reading and creating xml and html files | |

18 | Design | Regression | |

19 | Survey | Survey | |

20 | Survival | Survival Analysis | Survival Analysis |

21 | tm | Text Mining | Text Mining package |

**3. Data in R**

Data is stored and represented as vector in R software. The function "c" can be used to store the data as vector.

For example if want to store the age of 5 patients

> age = c(50,45,30,41,24)

*# R code*

Here the age will be stored as vector age[].

**>**[1] 5

*# R output*

**Age of first patient can be obtained by specifying the vector element age[1].**

We can also use the following function to store data

1. Data entry through key in

age = scan()

# R code 2. Entry through data editor

age = c(0) # R code initial value of age to be changed in the editor

Data.entry(age) # R code

**4. Basic Functions on Data**

We can apply basic function on our data

**>max(age)**

*# R code maximum*

>min(age)

*# R code minimum*

>mean(age)

*# R code mean*

>sd(age)

*# R code mean*

>median(age)

*# R code median*

>table(age)

*# R code frequency table*

>summar(age) # R code to list summary - mean,max,min,median,1st quartile, 3quartile