Linear Regression with R - Model assumptions check-up

R Tutorial 15.0

In the previous blog, we learned making a linear regression model. The only thing we left was necessary testing of certain assumption. Testing these assumptions is equivalent to health check-up of the model ; a healthy model is supposed to be a robust model.

Let's play doctor-doctor!

Linear Regression with R

R Tutorial 14.0

I have been a "Jabra Fan"(die hard fan) of Linear Regression, ever since I have started working in analytics space. The breadth and depth of OLS have been covered already in various of our blogs. In this blog we would understand "How to perform Linear Regression in R"

It is always a good feeling to write on your favorite topic !

Ghost Story of Heteroskedasticity

The word itself was so scary to me that I could never gather the courage to explore about it. But then I gradually overcame my fear and decided to study the concept of Heteroskedasticity.

I have  tried to make this concept as simple as possible for you so the next time if you see a person with a Hetroskedasticity phobia you are able to calm him down.

So are ready to dare ?

Outlier Detection &Treatment - Part 2 - Multivariate

We have already covered basics about outliers and uni-variate approach for outlier detection in one of our previous articles.

In this article we would understand the multi-variate approach for outlier detection and then finally the outlier treatment methods.

I find the subject of multi-variate detection of outlier to be too difficult to make easy, in order to do so, a supporting article has been written covering practical application of uni-variate method and emphasizing on the need of multi-variate methods of outlier detection. Now we would take the topic forward, in conjunction of both the previous articles.

Meaning of term "Linear" in Linear Regression

One of the most frequently asked questions in analytics interviews that interviewers use to confuse people :
What do you mean by term "Linear" in Linear Regression ? 

Few interviewers phrase the question in another way  :
If you regress a Y variable with X-square or Log(X) as one of the independent variables, would the equation Y = Beta(0) + Beta(1) X-Square + Beta(2) &%$#*&^ .....  be considered as a equation of linear regression ?

For complete explanation :

Seasonality Index and Trend Variables

Think of a time-series and the first term that comes to our statistical mind is ARIMA. Right ?

We would cover ARIMA soon on our blog, but its applicability is limited to forecasting. Also, it is a uni-variate practice that doesn't consider external factors. 

More often we need to study the effect of external factors on the a time-series such as sales, revenue etc. In such cases, we can use regression analysis while at the same time considering the key elements of time-series :  Seasonality and Trend.  Let's learn do we calculate these variables.

Proc Expand - Quite useful in modeling

Ques:  How would you create lag(s) of various orders of a variable in SAS ?
Ans  :  Using lag n (x) function, Simple !

Ques:  How would you create moving average of a variable in SAS?
Ans  :  Will take various lag, and then will take average ?

Ques : How will you create lead(s) of various orders of a variable in SAS ?
Ans  : We can't ... No function available for this, sorry !

Are you sure ??? Don't be. Here comes one of the most versatile SAS procedures that would make you a super hero.

Correcting the negative intercept in Linear Regression

Regression not speaking business well !

Often during Linear Regression modeling, we come across a negative intercept and it becomes quite difficult for us to explain the business sense of the same.

Suppose equation comes like :  Y = -100 + 23 (Media spend) + 13 (Discount)  ; in this case, client argues that the equation means that Sales would be  negative if there is no media spend and also discount is nil.

Doesn't make any sense, right ? How can we deal with such situation/equation ? Let me give you a tablet that can treat the model.

How multicollinearity can be hazardous to your model ?

All about Multicollinearity

In almost all popular techniques e.g. Linear Regression, Logistic Regression, Cluster Analysis, it is advised to check and remove the traces of multicollinearity. Why ??? Is it important at all, or can we skip it. How does it affect the model ?

Let's try to explore answers of all these questions ... Secret of multicollinearity revealed !

Linear Regression - Ready Reckoner

                                              Linear Regression - Connecting Dots

Linear regression analysis analyzes the linear relationship that exists between a Dependent Variable and Independent Variables. The Least squares criterion is used for determining a regression line that minimizes the sum of squared Residuals. For more watch this video tutorial. The video tutorial covers basic theory of Linear Regression.

Linear Regression - Part 2 - Video Tutorial

Linear Regression - Connecting Dots

Linear regression analysis analyzes the linear relationship that exists between a Dependent Variable and Independent Variables. The Least squares criterion is used for determining a regression line that minimizes the sum of squared Residuals. For more watch this video tutorial. The video tutorial covers preparatory work required to be done before Linear Regression modeling.

Linear Regression - Part 1 - Video Tutorial

Linear Regression - Connecting Dots

Linear regression analysis analyzes the linear relationship that exists between a Dependent Variable and Independent Variables. The Least squares criterion is used for determining a regression line that minimizes the sum of squared Residuals. For more watch this video tutorial. The video tutorial covers basic theory of Linear Regression.