Statistical Modeling for Data science

• Interest in Learning Statistical Modelling

• Just a basic knowledge of high school maths

• People working in any numerate field which requires data analysis

• People carrying out observational or experimental studies

• Any one who want to make career in Data Science

• Understand what a Normal Distribution is

• Apply Hypothesis Testing for Means

• Understand standard deviations

• Apply the Central Limit Theorem

• Difference between continuous and discrete variables

• Use the Z-Score and Z-Tables

• what a sampling distribution is

What is Statistical Modeling?

Data science refers to the process of applying statistical analysis to datasets. It is a mathematical relationship between one or more random variables and other non-random variables. With the use of statistical modeling on raw data, data scientists are able to handle data analysis in a strategic manner, providing intuitive visualizations that aid in determining relationships between variables and making predictions.

In addition to the Internet of Things (IoT) sensors, census data, public health data, social media data, imagery data, and other public sector data that benefit from real-time prediction, statistical analysis is performed on a wide range of data sets.

Techniques for Statistical Modeling

Gathering data, which may come from spreadsheets, databases, data lakes, or the cloud, is the first step in developing a statistical model. Statistical modeling methods for analyzing this data fall into two categories: supervised learning and unsupervised learning. Examples of popular statistical models include logistic regression, time series, clustering, and decision trees. 

Techniques for supervised learning include regression models and classification models:

1) A regression model is a type of statistical model that analyzes the relationship between a dependent and an independent variable. Regression models include logistic, polynomial, and linear models. Forecasting, time series modeling, and causal effect relationships between variables are examples of applications.

2) A classification model is a type of machine learning in which an algorithm examines a set of known data points in order to better understand and classify the data; commonly used models include decision trees, Naive Bayes, nearest neighbors, random forests, and neural network models, which are typically used in Artificial Intelligence algorithms.

Clustering algorithms and association rules are examples of unsupervised learning techniques:

1) A K-means clustering method aggregates a set of data points into a set of groups based on certain similarities.

2) An area of deep learning that involves iterating over many attempts, rewarding steps that produce desired outcomes, and penalizing steps that produce unwanted outcomes, so that the algorithm learns the optimal process.

The three types of statistical models are parametric, nonparametric, and semiparametric:

1) A parametric distribution is a family of probability distributions with a finite number of parameters.

2) N‍onparametric models have parameters that are flexible and not fixed in advance.

3) A semiparametric parameter has both a finite-dimensional and an infinite-dimensional component.