Digiroof

1 - machine learning, some common terms, predictor & response, simple & multiple linear regression

2 - some more terminologies, dependent & independent variables, linear & non linear regression

3 - some more basics, supervised & unsupervised learning method, positive & negative relationship

4 - course objective, course content, who is going to benefit from this course?

5 - Introduction to two components of Regression Line - Slope & Intercept

Ch 01 (Exercise Files)

6 - Relevance of clean and complete data, types of distribution graphs

7 - understand Normal Distribution, Variance & Standard Deviation

8 - Properties of normally distributed data

9 - what property to apply on a small data, t-distribution

10 - Need of making regression model

11 - Comparing Variance from Mean with Variance from Regression Model

12 - Understand the formula of slope in Least Square Method (First example)

13 - Using excel to calculate variance and covariance in the slope formula, calculate intercept (First example)

14 - Use slope and intercept value to make regression line, Different ways to interpret the slope value (First example)

15 - How to calculate error, present error in a scatterplot (First example)

16 - Why the error term needs to be squared, Origin of slope formula (First example)

17 - Introduction to R, Make a random dataset inside R (second example)

18 - Make a scatterplot, calculate the value of slope (second example)

19 - Interpret slope value, calculate intercept, make regression line (second example)

Ch 03 (Exercise Files)

Ch 03 (Exercise Files)

20 - compare mean model with regression model, Understanding and calculating the sum of squares (First Example)

21 - calculate the sum of squares (Second Example)

22 - understand & calculate R2 and correlation (first & second example)

23 - Introduction to F-statistic, understand and calculate degree of freedom, calculate F-ratio

24 - consolidate the learning (real world example), Going through the data

25 - calculate slope & intercept, make regression line (real world example)

26 - check the regression model using sum of squares, R2, correlation, F-ratio (real world example)

Ch 04 (Exercise Files)

27 - Introduction to t-statistic, meaning of population

28 - formula for t-test, components of the formula, understand standard error & central limit theorem

29 - How to calculate standard error (theoretical method & feasible method), calculate t-value

30 - interpret standard error, dissect t-table, find the value for degree of freedom, understand p-value

31 - probability value & significance value, how to interpret t-ratio

32 - understand error term

33 - interpreting slope value based on units of predictor & response, standard error of intercept

35 - output of summary function, understand exponents

Ch 05 (Exercise Files)

36 - Introduction to Multiple Linear Regression, When Simple Linear Models are not useful ?

37 - When simple linear models are not useful? How to select predictor variables?

38 - Make multiple linear model inside R, Improve the model, Interpret the slope value

39 - Why make multiple linear models? Another Example to demonstrate multiple linear model

40 - Improvise the model, How to make 3d scatterplots inside R

Ch 06 (Exercise Files)

41 - Impact of missing data on regression model, Discuss the reasons of missing data (MCAR, MAR, and NMAR)

42 - continue discussing the reason for missing data (MCAR, MAR, and NMAR)

43 - Identify & understand missing data using md_pattern function, How to get the data in order?

44 - Output of md_pattern function, Another way to identify and understand missing data using aggr function

45 - How to use regression model for filling the missing data?

46 - Continue filling the missing data using regression model, Understand symnum function

47 - Example where data needs to be modified for making a better regression model (change the entries in categorical variable)

48 - Example where data needs to be modified for improving the analysis (change the entries in variables giving age)

Ch 07 (Exercise Files)

49 - na.omit function to remove rows with missing data, Remove columns with excessive missing data

50 - Impute function to replace empty cells with mean/median value

51 - K nearest neighborhood imputation for filling the empty cells

52 - mice function for filling empty cells, understand predictive mean matching

53 - continue looking at the mice function

54 - Using the output from mice function to make a better regression model than before

55 - Recursive partitioning for filling empty cells

56 - missmap function in amelia, amelia function for filling empty cells

Ch 08 (Exercise Files)

58 - runif function for dividing the data, Going though examples to look at the complete process

Ch 09 (Exercise Files)

59 - Discussion on residuals, vif function for checking collinearity

60 - Using some examples to understand vif function, An introduction to outliers

61 - How to access residuals in the training and testing data, Using raw residuals to identify outliers

62 - using the value of standardized residuals and leverage for identifying outliers

63 - Using studentized residuals and cooks distance for identifying outlier values

64 - identify outliers using residual values (Second Example), understand average leverage

65 - use covariance ratio to identify outliers, consolidate the learning, Durbin Watson test, Average vif

66 - Placing residuals in plots for identifying outliers

Ch 10 (Exercise Files)

67 - Different ways to identify whether data transformation is needed or not

68 - Basics of log transformation

69 - Various methods for log transforming the variables used in regression model

70 - Continue discussing log transformation of variables

Ch 11 (Exercise Files)

71 - Different kinds of scatterplots, Plotting transformed data

72 - More ways of making plots

73 - plotting residuals

Ch 12 (Exercise Files)

74 - residual-related concerns

75 - Missing data problem, Interaction among predictors

76 - qqplot for identifying data problems, qqnorm function

77 - Some more discussion on qqnorm function

Ch 13 (Exercise Files)

78 - introduction to confidence interval, calculate interval for standard error of slope

79 - continue discussing confidence interval

80 - confidence interval of intercept

81 - calculate margin of error, sample statistic

82 - Using more examples to create confidence intervals

83 - Bootstrapping confidence interval

84 - Examples to demonstrate bootstrapping

Ch 14 (Exercise Files)

Goodbye