R PROGRAMMING

Course Contents 

Predictive Modeling

 Duration: 40 Hours         

                                                 The predictive modeling helps us to analyze the business intelligence and predict with confident what happening next few years so we can plan accordingly. Our course helps you to understand the concept of statistical technique and judge independently what you can do it for given data for given problem.

“Data is an information our job is to convert our data into meaningful information”.

(Note: the practical session for these concepts will be thought through R Tool)

R Programming

  • Introduction to R
  • Getting Started – R Console
  • Importing Raw data files, SAS and SPSS files
  • Data types and Structures
  • Vector
  • Matrix
  • List
  • Data Frame
  • Exploring and Visualizing Data
  • Merging and appending  the data files
  • Programming Structures, Functions
  • Do Loops Data Relationships
  • Generating Graphs  and Reports
  1. Descriptive Statistics

Introduction to Statistics

  • Measurement of Scales
  • Measure of central Tendency
  • Measure of Dispersion
  • Exploratory Data Analysis
  • Measure of Shape Skewness and Kurtosis

Data Preparation

  • Data Handling and preparation
  • Missing value analysis and imputation
  • Outlier identification and how handle the outlier problem

Sampling Methods

  • Simple Random Sampling
  • Systematic Random sampling
  • Stratified Random sampling
  • Probability Proportional Sampling(Neyman and Allocation)
  • Cluster Random Sampling
  • Non Random samplings: Quota, Judgment, Convince and Snow ball sampling

II Statistical Inference

Parametric tests

  • One sample t test
  • Independent of two sample tests ( t test & Z tests)
  • Paired t test
  • Binomial Proportion test(One and two sample)
  • One Way ANOVA
  • Two ways ANOVA

Non parametric Tests

  • Chi square Test
  • Fisher exact Test
  • Mcnemar Test
  • Median Test
  • Mann Whitney U Test
  • Wilcoxon Test
  • Krushal walis test For Anova

III. Predictive Modeling technique
IV.  Simple and Multiple Linear regression

  • Assumption of OLS
  • OLS method
  • MLE
  • Checking Assumption of OLS
  • Problem of Homoscedasticity
  • Problem of Autocorrelation
  • Problem of Multicollinearity
  • Data Transformation
  • Weighted Least Square regression
  • Robust regression
  • Mixed model
  • Median Regression
  • Ridge regression
  • Principal Component Regression
  • Remedy For Violation Of Assumptions of OLS
  1. Logistic Regression for Classification and Prediction
    • Assumptions Of Logistic Regression
    • Binary Logistic Regression
    • Nominal Logistic Regression
    • Ordinal Logistic Regression

 Model Validation

  • Odds Ratio
  • Receiver Operating characteristic(ROC) curve
  • Lift Chart
  • Misclassification Matrix
  • Sensitivity
  • Specificity
  • False Positive
  • False Negative
  • Quasi Problem
  1. Forecasting Technique (Time series Analysis)
  • Assumptions And Model Diagnosis
  • Trend analysis Seasonality analysis Random analysis Cyclical analysis
  • Moving Average and Exponential smoothing (Single Double and Triple)
  • ARIMA Modeling
  • Random Walk Additive and Multiplicative Model

VII. Multivariate Techniques

  • Factor Analysis for Data Reduction
  • Principle Component Analysis
  • Cluster Analysis for Market segmentation Hierarchical and Non Hierarchical
  • Discriminate Analysis for classification and Prediction
  • Conjoint analysis for Product design
  • Canonical correlation for set of group correlation
  • CHIAD (Decision tree)
  • CART(Classification And Regression Tree)
  • Random Forest
  • Neural Network (Artificial knowledge) Machine Learning
  • Market Basket Analysis for Customer Behavior
  • Multidimensional scaling