Difference between revisions of "R"
From Script | Spoken-Tutorial
Sudhakarst (Talk | contribs) |
Sudhakarst (Talk | contribs) |
||
| Line 5: | Line 5: | ||
'''R''' is the most preferred open source language for analytics and data science. At Microsoft, R is used by its data scientists, who apply machine learning to data from Bing, Azure, Office, and the Sales, Marketing, and Finance departments. Twitter has been using R for measuring user-experience. On the other hand, the cross-platform compatibility of R and its capacity to handle large and complex data sets make it an ideal tool for academicians to analyze data in their labs. | '''R''' is the most preferred open source language for analytics and data science. At Microsoft, R is used by its data scientists, who apply machine learning to data from Bing, Azure, Office, and the Sales, Marketing, and Finance departments. Twitter has been using R for measuring user-experience. On the other hand, the cross-platform compatibility of R and its capacity to handle large and complex data sets make it an ideal tool for academicians to analyze data in their labs. | ||
| − | R can be used for simple calculations, matrix calculations, differential equations, optimisation, statistical analysis, plotting graphs, etc. Also, it is useful to anybody who wishes to undertake extensive statistical computations and data visualization. | + | '''R''' can be used for simple calculations, matrix calculations, differential equations, optimisation, statistical analysis, plotting graphs, etc. Also, it is useful to anybody who wishes to undertake extensive statistical computations and data visualization. |
Revision as of 15:27, 18 April 2019
Introduction to R
R ( http://www.r-project.org/) is an open source software- a well organized and sophisticated package- that facilitates data analysis, modeling, inferential testing and forecasting. It is a user friendly software which allows to create new function commands to solve statistical problems. It runs on a variety of UNIX platforms(and similar systems such as LINUX), Windows and Mac OS.
R is the most preferred open source language for analytics and data science. At Microsoft, R is used by its data scientists, who apply machine learning to data from Bing, Azure, Office, and the Sales, Marketing, and Finance departments. Twitter has been using R for measuring user-experience. On the other hand, the cross-platform compatibility of R and its capacity to handle large and complex data sets make it an ideal tool for academicians to analyze data in their labs.
R can be used for simple calculations, matrix calculations, differential equations, optimisation, statistical analysis, plotting graphs, etc. Also, it is useful to anybody who wishes to undertake extensive statistical computations and data visualization.
Basic Level
Introductory sessions in R
- Installing R
- Downloading and installing R
- Basic operations in the R console
- To open the R console
- To run commands in R
- To correct errors made in the R commands
- To save work done in R
- To quit the R console
- Documentation and Packages in R
- To access installed documentation and packages in R
- To install and load packages in R
- Data structures
- Variables and Vectors in R
- Creation and deletion of variables and vectors
- Listing the vectors
- Modifying vectors
- Creating row and column vectors
- Vector Algebra and Matrices in R
- Vector algebra
- Creating matrices
- Matrix operations
- Sequences, lists, strings and dates in R
- Creation of sequences and lists
- Modifying lists, selecting elements from a list
- Modifying strings, substrings
- Date-string conversion
- Other functions related to dates
- Handling data in R
- Creating and modifying data frames
- Reading data stored in files of different formats
- Basic computations in R
- Elementary operations in R
- Arithmetic
- Higher powers and roots of a number
- Logarithms and exponentials
- Operations on complex numbers
- Measures of central tendency and dispersion
- Mean, median and mode
- Variance, standard deviation and quantiles
- Probability distributions
- Discrete probability distributions:Binomial,Poisson and Geometric
- Binomial,Poisson and Geometric densities, distribution and quantile functions, random variables
- Discrete probability distributions:Negative Binomial and Hypergeometric
- Negative Binomial and Hypergeometric densities, distribution and quantile functions, random variables
- Continuous probability distributions
- Normal, Chi squared, F and t densities, distribution and quantile functions, random variables
- Log-normal, logistic, exponential and gamma densities, distribution and quantile functions, random variables
- Beta, cauchy and weibull densities, distribution and quantile functions, random variables
- Graphical representation of information using R
- Histograms, barcharts and box plots
- Creating histograms, addding density estimate to a histogram
- Creating and colouring bar charts, adding confidence intervals
- Creating box plots
- Scatter diagrams, regression lines and Q-Q plots
- Plotting a scatter digram, adding title, label, grid and a legend
- Graphing a function, a regression line (superimposing on scatter plot)
- Creating Q-Q plots
- Econometrics in R
- Simple and multiple linear regression
- OLS, log-linear, log-log and semi-log regressions
- Dummy variable regression, regression through the origin and with standardised coefficients
- Regression Analysis
- Confidence intervals
- P-values and power functions
- Tests for heteroskcedasticity
- Park test
- Goldfeld-Quandt test
- Breusch-Pagan-Godfrey test
- White’s General Heteroskcedasticity test
- Tests for autocorrelation and specification errors
- Durbin Watson test
- Ramsey reset specification test
ADVANCED LEVEL TUTORIALS
- Models of microeconometrics
- Bayesian Econometrics
- Time series Econometrics
- Programming your own analysis
