Statistical-Inference-course

Welcome to the Statistical Inference course repository offered at the University of Tehran. This repository contains code for assignments and projects completed during the course. The course by:

• Dr. Behnam Bahrak

Course Description

This course provides an overview of fundamental concepts in statistics and probability. It begins with Probability Theory, which delves into the foundations of probability and its significance in statistical inference. Next, Sampling Techniques are explored, with a focus on various sampling methods and their implications in data analysis. Estimation techniques follow, covering how to estimate population parameters using sample data, including point and interval estimates. The concept of Hypothesis Testing is then introduced, detailing procedures for making decisions based on sample data. Regression Analysis comes next, highlighting the use of linear regression models to predict outcomes. Analysis of Variance (ANOVA) is discussed as a means of comparing means across multiple groups. Additionally, Non-parametric Methods are introduced, offering alternatives to traditional statistical techniques for data analysis. Finally, Bayesian Inference is presented as an introduction to Bayesian statistics and its differences from classical (frequentist) approaches. Overall, this summary provides a comprehensive glimpse into key statistical concepts and their applications.

Table of Contents

Please find below a brief overview of the contents of this repository:

1. HW1/: This directory contains code and asnwers for Assignment 1, which focuses on confounding variables, sampling strategies, calculating data statistics, and different methods of data visualization.
2. HW2/: This directory contains code and answers for Assignment 2, which focused on conditional probability, binomial probability, geometric random variables, Poisson random variables, and using ggplot2 for data visualization.
3. HW3/: This directory contains code and answers for Assignment 3, which focuses on Hypothesis testing, Confidence Intervals, error types I and II, calculating power, and calculating confidence intervals for the Galton dataset.
4. HW4/: This directory contains code and answers for Assignment 4, which focuses on ANOVA, t-distribution, comparing two means, Multiple Comparisons, and Bootstrapping.
5. HW5/: This directory contains code and answers for Assignment 5, which focuses on Inference for Proportion, Independence Tests(chi-square test), and Inference for Proportion.
6. HW6/: This directory contains code and answers for Assignment 6, which focuses on regression and goodness of fit.
7. Final Project/: Here, you can find code related to the projects completed as part of the course requirements.

Final Project

In this project, we aim to study and analyze Airbnb datasets to gain valuable insights into the preferences of both guests and property owners. Airbnb is a platform that facilitates the rental of properties by homeowners to people in need of temporary accommodation. The platform operates on a commission-based model for each booking and does not own any of the listed properties.

Project Objectives

The primary objectives of this project are to answer the following questions:

1. Factors Influencing House Selection

   • What features are most significant for guests when choosing their preferred accommodation?
   • Does the neighborhood play a crucial role in the decision-making process?
   • Are certain neighborhoods more affordable than others?
   • Is proximity to tourist attractions a determining factor for the popularity of certain neighborhoods?
   • Do houses located in specific neighborhoods receive more visitors, and which neighborhoods are more popular overall?

2. Price Acceptability and Impact

   • What price range is more acceptable to potential guests?
   • Do guests prioritize cheaper prices, or does the rating of the property carry more weight?
   • Do service fees significantly impact guests' decisions, and can they act as deal breakers?

3. Effect of House Ratings

   • How does the rating of a property influence guests' decisions?
   • Is there a correlation between higher prices and better ratings?
   • Does the number of previous visitors and their ratings impact the popularity of a property?

4. Preferred House Characteristics

   • What type of houses do guests prefer to stay in?
   • Does the construction year of the property matter to guests?
   • Which room types are more popular among renters? Do guests prefer more expensive houses for increased privacy?
   • What property policies tend to drive guests away?

5. Impact of Instant Booking, Availability 365, and Cancellation Policies

   • Does the availability of instant booking influence guests' decisions?
   • Is the "availability 365" metric significant for guests when choosing a property?
   • Are guests comfortable with strict cancellation policies?

6. Property Owner Preferences

   • What kind of services do property owners prefer to provide?
   • Do property owners tend to enforce strict policies?
   • How does property owner identification verification affect visitor engagement?
   • Do property owners in economically disadvantaged neighborhoods tend to rent only part of their homes?
   • What is the preferred price range for property owners in each area?

7. Recommendations

Based on the insights gained from the analysis of Airbnb datasets, we can leverage this information in combination with user data to provide personalized house recommendations to guests. By understanding the factors that influence guests' decisions and property owners' preferences, we aim to enhance the overall experience and satisfaction of both parties on the Airbnb platform.

---

Disclaimer

This repository is for archival and reference purposes only. The code here might not be updated or maintained. Use it at your own discretion.