Question

Difference between box plot and histogram.

Difference between lasso ridge and introduce dimension reduction techniques

Answer 1

Difference between box plot and histogram.

1) box plot is graphical represenation of 5 number summary.

histogram. is barchart of frequencies.

2) histogram. is useful when very high or very low variance in observed frequencies.But to understand underline distribution boxplotb is useful.

=============================================================

Difference between lasso ridge

• Lasso does a sparse selection, while Ridge does not.
• For correlated variables, Ridge regression shrinks the two coefficients towards one another. but Lasso generally picks one over the other. we dont not know which variable gets picked.
• Ridge estimators are indifferent to multiplicative scaling of the data. That is, if both X and Y variables are multiplied by constants, the coefficients of the fit do not change, for a given λλ parameter. However, for Lasso, fit is dependent of the scaling.
• Ridge penalizes the largest ββ's more than the smaller ones (because they are squared in the penalty term). Lasso penalizes them more uniformly. the predictor's effectiveness is shrunk by the Ridge as compared to the Lasso.

===========================================================

introduce dimension reduction techniques

1) Remove variable with high % of missing value

2)Remove variable with low variance since do not contain much information or contains redundent information

3) Remove High correlated variable if multicollinearity present in data we use Principle component analysis fo this

4) stepwise regression

5) factor analysis

6) random forest for important variable selection

===========================================================

   If you have any doubt please let me know through comment
     Please give positive vote if you find this solution helpful. Thank you!