Scribd
Upload
17 views

BA unit 2 notes (1)

Uploaded by

Santhu N Gowda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
17 views

BA unit 2 notes (1)

Uploaded by

Santhu N Gowda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Here are some notes on Trendiness and Regression Analysis:

Trendiness
- Definition: Trendiness refers to the tendency of a time series to move in a specific direction over time.
- Types of Trends:
- Upward trend: Increase in value over time
- Downward trend: Decrease in value over time
- Stationary trend: No change in value over time
- Methods to detect trendiness:
- Visual inspection of time series plots
- Trend tests (e.g. Mann-Kendall test)
- Regression analysis

Regression Analysis

- Definition: Regression analysis is a statistical method to establish a relationship between two or more
variables.

- Types of Regression:
- Simple Linear Regression (SLR): One independent variable
- Multiple Linear Regression (MLR): More than one independent variable
- Non-Linear Regression: Non-linear relationship between variables

- Steps in Regression Analysis:


1. Model specification
2. Estimation of parameters
3. Hypothesis testing
4. Model evaluation

- Assumptions of Regression Analysis:


- Linearity
- Independence
- Homoscedasticity
- Normality
- No multicollinearity
Regression Coefficients
- Slope coefficient (β1): Change in dependent variable for one-unit change in independent variable
- Intercept coefficient (β0): Value of dependent variable when independent variable is zero
- Coefficient of Determination (R-squared): Measures goodness of fit

Common Regression Models


- Linear Regression: Y = β0 + β1X + ε
- Logistic Regression: Y = 1 / (1 + e^(-β0 - β1X))
- Exponential Regression: Y = e^(β0 + β1X)
These notes cover the basics of trendiness and regression analysis, including types of trends, methods to
detect trendiness, types of regression, steps in regression analysis, assumptions, regression coefficients,
and common regression models.
Here are some notes on Modeling Relationships and Trends in Data using Simple Linear Regression:

Modeling Relationships
- Goal: To understand the relationship between two continuous variables
- Simple Linear Regression: A linear model that predicts the value of a continuous outcome variable
based on a single predictor variable
- Assumptions:
- Linearity: Relationship between variables is linear
- Independence: Observations are independent
- Homoscedasticity: Constant variance of residuals
- Normality: Residuals are normally distributed
- No multicollinearity: Predictor variable is not highly correlated with other variables

Simple Linear Regression Equation


- Y = β0 + β1X + ε
- Y: Outcome variable
- X: Predictor variable
- β0: Intercept coefficient
- β1: Slope coefficient
- ε: Residual error
Interpretation of Coefficients
- β0 (Intercept): Value of Y when X is 0
- β1 (Slope): Change in Y for a one-unit change in X

Model Evaluation
- Coefficient of Determination (R-squared): Measures goodness of fit (0-1)
- Residual Plots: Check for linearity, homoscedasticity, and normality
- Hypothesis Testing: Test for significance of coefficients (t-tests, F-tests)

Common Applications
- Predicting continuous outcomes (e.g., stock prices, temperatures)
- Identifying relationships between variables (e.g., correlation between age and income)
- Making informed decisions based on data-driven insights

These notes cover the basics of simple linear regression, including the assumptions, equation,
interpretation of coefficients, model evaluation, and common applications.
Here are some common types of data models:
1. Conceptual Data Model: A high-level, abstract model that describes the overall structure and
relationships of data.

2. Logical Data Model: A detailed, formal model that describes the relationships and constraints of data.

3. Physical Data Model: A low-level, detailed model that describes how data is stored and managed in a
specific database management system.

4. Relational Data Model: A model that organizes data into tables with well-defined relationships
between them.

5. Entity-Relationship Data Model: A model that describes data in terms of entities and relationships
between them.

6. Dimensional Data Model: A model that organizes data into facts and dimensions for analytical
querying.
7. Object-Oriented Data Model: A model that represents data as objects with properties and
relationships.

8. Hierarchical Data Model: A model that organizes data in a tree-like structure.

9. Network Data Model: A model that represents data as a network of interconnected records.

10. NoSQL Data Model: A model that stores data in a variety of formats such as key-value, document,
graph, and column-family stores.

Each type of data model has its strengths and weaknesses, and the choice of which one to use depends on
the specific needs of the application or organization.

Problem:
A company wants to understand the relationship between the amount spent on advertising (in thousands
of dollars) and the sales revenue (in thousands of dollars) for their product. They have collected data for
10 months, with the following values:
| Month | Advertising Spend (X) | Sales Revenue (Y) |
| --- | --- | --- |
| 1 | 10 | 50 |
| 2 | 15 | 60 |
| 3 | 20 | 70 |
| 4 | 25 | 80 |
| 5 | 30 | 90 |
| 6 | 35 | 100 |
| 7 | 40 | 110 |
| 8 | 45 | 120 |
| 9 | 50 | 130 |
| 10 | 55 | 140 |

Task:
1. Develop a linear regression model to predict sales revenue (Y) based on advertising spend (X).
2. Interpret the coefficients of the model.
3. Evaluate the performance of the model using appropriate metrics (e.g. R-squared, residual plots).
4. Use the model to predict sales revenue for a new month with an advertising spend of $60,000.
Solution:

1. Linear Regression Model:

Y = β0 + β1X + ε

Using the data, we estimate the coefficients:

β0 = 20.5
β1 = 2.3

So, the model is:

Y = 20.5 + 2.3X

1. Interpretation of Coefficients:

β0 (Intercept): The sales revenue when advertising spend is zero is $20,500.


β1 (Slope): For every additional $1,000 spent on advertising, sales revenue increases by $2,300.

1. Model Evaluation:

R-squared = 0.95 (high goodness of fit)


Residual plots show no obvious patterns or outliers.

1. Prediction:

For an advertising spend of $60,000, the predicted sales revenue is:

Y = 20.5 + 2.3(60) = 143.5

So, the predicted sales revenue is $143,500.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy