Difficulties in Data Science
Unknown
02:41
Data Science Problems according to Difficulties
Descriptive Analysis: The main goal of this is to describe the Data.You are not going to make any prediction or any decision or performing any kind of analysis.This is the first kind of Data analysis performed, however, it is not generalized without adding statistical modeling.Commonly applied to the Census Data.
Exploratory Analysis: Exploratory analysis on data will show you different relationships between data which you don't know earlier.It is very much useful in defining future studies and defining new connections.Although it is not the final stage and prediction and decision making can't be done with this alone.
Inferential Analysis: Inferential Analysis uses a very small data, which is sample data and predicts something on larger Data that is predicting or making a decision on bigger population.It is the goal of statistical models and heavily depends on the sample or population.
Predictive Analysis: This Analysis refers to using the data on some objects for predicting the values of other objects.Doing correct prediction is very tough and heavily depends on measuring the right values.There are many models for prediction but if the Data size is more than with the simple model prediction really works well.
Casual Analysis: By this, you will find out that, what happens with one variable when you make a change to other variables.Casual Analysis is considered to be the "Gold Standard" for Data Analysis and is usually identified as average effects but may not apply to every individual.
You should have lots of practice with all the above approaches in order to have good command over the Data Science.The biggest thing is to keep yourself in practice and keep learning.
