REGRESSION

REGRESSION
• Regression analysis is a form of predictive modelling technique which

investigates the relationship between a dependent (target) and
independent variable(s) (predictor). This techniques is used for forecasting,
time series modelling, and finding the causal effect relationship between
the variables.
• In statistical modeling, regression analysis is used to estimate the
relationships between two or more variables:
• Dependent variable (criterion variable) is the main factor you are trying to
understand and predict.
• Independent variables ( explanatory variables, or predictors) are the factors
that might influence the dependent variable.
Regression analysis helps you understand how the dependent variable changes
when one of the independent variables varies and allows to mathematically
determine which of those variables really has an impact.
• A regression analysis model is based on the sum of squares, which is a
mathematical way to find the dispersion of data points. The goal of a model
is to get the smallest possible sum of squares and draw a line that comes
closest to the data.
• Simple linear regression models the relationship between a dependent
variable and one independent variables using a linear function. If you use
two or more explanatory variables to predict the dependent variable, you
deal with multiple linear regression.
• Linear regression equation
Mathematically, a linear regression is defined by this equation:
y = bx + a + ε
Where:
x is an independent variable.
y is a dependent variable.
a is the Y-intercept, which is the expected mean value of y when all x variables
are equal to 0. On a regression graph, it's the point where the line crosses the Y
axis.
b is the slope of a regression line, which is the rate of change
for y as x changes.
ε is the random error term, which is the difference between the actual value of
a dependent variable and its predicted value. The linear regression equation
always has an error term because, in real life, predictors are never perfectly
precise.
In Excel, y = bx + a
Multiple R. It is the Correlation Coefficient that measures the strength of a
linear relationship between two variables. The correlation coefficient can be
any value between -1 and 1, and its absolute value indicates the relationship
strength. The larger the absolute value, the stronger the relationship:
• 1 means a strong positive relationship
• -1 means a strong negative relationship
• 0 means no relationship at all
R Square. It is the Coefficient of Determination, which is used as an indicator of
the goodness of fit. It shows how many points fall on the regression line. The
R2 value is calculated from the total sum of squares, more precisely, it is the
sum of the squared deviations of the original data from the mean.
In our example, R2 is 0.91 (rounded to 2 digits), which is fairy good. It means
that 91% of our values fit the regression analysis model. In other words, 91% of
the dependent variables (y-values) are explained by the independent variables
(x-values). Generally, R Squared of 95% or more is considered a good fit.
Adjusted R Square. It is the R square adjusted for the number of independent
variable in the model. You will want to use this value instead of R square for
multiple regression analysis.
Standard Error. It is another goodness-of-fit measure that shows the precision
of your regression analysis - the smaller the number, the more certain you can
be about your regression equation. While R2 represents the percentage of the
dependent variables variance that is explained by the model, Standard Error is
an absolute measure that shows the average distance that the data points fall
from the regression line.
Observations. It is simply the number of observations in your model.
Regression analysis output: ANOVA
The second part of the output is Analysis of Variance (ANOVA):
Basically, it splits the sum of squares into individual components that give
information about the levels of variability within your regression model:
• df is the number of the degrees of freedom associated with the sources of
variance.
• SS is the sum of squares. The smaller the Residual SS compared with the
Total SS, the better your model fits the data.
• MS is the mean square.
• F is the F statistic, or F-test for the null hypothesis. It is used to test the
overall significance of the model.
• Significance F is the P-value of F.
The ANOVA part is rarely used for a simple linear regression analysis in Excel,
but you should definitely have a close look at the last component.
The Significance F value gives an idea of how reliable (statistically significant)
your results are. If Significance F is less than 0.05 (5%), your model is OK. If it is
greater than 0.05, you'd probably better choose another independent variable.
Regression analysis output: coefficients
This section provides specific information about the components of your
analysis:
The most useful component in this section is Coefficients. It enables you to
build a linear regression equation in excel:
y = bx + a
For our data set, where y is the number of umbrellas sold and x is an average
monthly rainfall, our linear regression formula goes as follows:
Y = Rainfall Coefficient * x + Intercept
Y=0.45*x-19.074
For example, with the average monthly rainfall equal to 82 mm, the umbrella
sales would be approximately 17.8:
0.45*82-19.074=17.8
In a similar manner, you can find out how many umbrellas are going to be sold
with any other monthly rainfall (x variable) you specify.

REGRESSION

Uploaded by

Copyright:

Available Formats

REGRESSION

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

REGRESSION

Uploaded by

Copyright:

Available Formats

REGRESSION

• Regression analysis is a form of predictive modelling technique which

You might also like