Scribd Logo
Upload

Welcome to Scribd!

  • 23 views

    GLM Assignment

    Uploaded by

    Talha Farooq
    Linear models can be used to predict the relationship between a dependent variable and one or more independent variables. A simple linear model relates one dependent variable (Y) to a single independent variable (X) using the equation Y = β0 + β1X + ε, where β0 is the intercept, β1 is the slope, and ε is random error. Multiple linear models extend this to include more than one independent variable. The coefficients in a linear model are estimated using the least squares method to minimize the squared differences between observed and predicted dependent variable values. Linear models have applications in fields like predicting vaccine production levels based on factors like government funding and partnerships with biotech companies.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    GLM Assignment

    Uploaded by

    Talha Farooq
    23 views4 pages
    Linear models can be used to predict the relationship between a dependent variable and one or more independent variables. A simple linear model relates one dependent variable (Y) to a single independent variable (X) using the equation Y = β0 + β1X + ε, where β0 is the intercept, β1 is the slope, and ε is random error. Multiple linear models extend this to include more than one independent variable. The coefficients in a linear model are estimated using the least squares method to minimize the squared differences between observed and predicted dependent variable values. Linear models have applications in fields like predicting vaccine production levels based on factors like government funding and partnerships with biotech companies.

    Original Description:

    Generalised linear models with applications

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Linear models can be used to predict the relationship between a dependent variable and one or more independent variables. A simple linear model relates one dependent variable (Y) to a single independent variable (X) using the equation Y = β0 + β1X + ε, where β0 is the intercept, β1 is the slope, and ε is random error. Multiple linear models extend this to include more than one independent variable. The coefficients in a linear model are estimated using the least squares method to minimize the squared differences between observed and predicted dependent variable values. Linear models have applications in fields like predicting vaccine production levels based on factors like government funding and partnerships with biotech companies.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    23 views4 pages

    GLM Assignment

    Uploaded by

    Talha Farooq
    Linear models can be used to predict the relationship between a dependent variable and one or more independent variables. A simple linear model relates one dependent variable (Y) to a single independent variable (X) using the equation Y = β0 + β1X + ε, where β0 is the intercept, β1 is the slope, and ε is random error. Multiple linear models extend this to include more than one independent variable. The coefficients in a linear model are estimated using the least squares method to minimize the squared differences between observed and predicted dependent variable values. Linear models have applications in fields like predicting vaccine production levels based on factors like government funding and partnerships with biotech companies.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 4

    Linear Models

    Talha Farooq
    School of Natural Sciences
    MS Statistics

    National University of Sciences & Technology


    Pakistan
    Introduction
    The term Model is a representation of some phenomenon by us-
    ing data or information. We create a representation as a mathe-
    matically. This representation is a Model and by using this model,
    we can predict the future results of given data.
    The term Phenomenon could be Earthquake or height.
    Linear Models are used for a wide variety of statistical analysis.
    The basic concept is that a dependent variable can be predicted
    from a set of independent variables that are related in a linear
    fashion.
    Linear Models
    A linear model relating a random response Y to a set of indepen-
    dent variables x1 , x2 , ..., xk is of the form
    Yi = β0 + β1 x1 + β2 x2 + ... + βi xi + i
    where β0 , β1 , ..., βk are unknown parameters,  is a random variable
    and the variables x1 , x2 , ..., xk assume known values.
    Yi 's is dependent (response) variable.
    i 's are error components.
    βi is population slope.
    β0 is population Y-intercept.
    Xi 's are Independent (explanatory) variables.
    When we have only one explanatory variable then it becomes
    simple linear model and if has two or more Independent variables
    then it is multiple linear model.

    1
    We draw an estimated line and we get expected value.
    E(Y ) = βˆ0 + βˆ1 X1

    Estimated line can be drawn by using Least Square method.


    The principle of Least Square Method is to draw a line in such a
    way that the dierence between the observed points and the
    tted line must be minimized.
    We postulate that Y = βˆ0 + βˆ1 X + , where  possesses some
    probability distribution with E() = 0.
    The dierence between actual Y and predicted Y values is
    minimum but positive dierence o-set negative ones. So, square
    errors n n
    X X
    (Yi − Ŷ )2 = ˆi 2
    i=1 i=1

    We put the value of Yi and nd values of unknown parameters.


    We will get,
    Sxy
    βˆ1 =
    Sxx
    Where
    n
    X
    Sxy = (xi − x̄)(yi − ȳ)
    i=1
    n
    X
    Sxx = (xi − x̄)2
    i=1

    And
    βˆ0 = Ȳ − βˆ1 x̄

    Applications
    Linear Models are used to predict the relationship between two
    variables. The variable that is being predicted is dependent
    variable.
    Industrial sciences
    The Pzer-BioNTech COVID-19 vaccine is approved by six
    countries. U.S announced an agreement with U.S.-based Pizer
    Inc. for large scale production and nationwide delivery of 100
    million doses of a COVID-19 in the United States following the

    2
    vaccine's successful manufacture and approval.The agreement
    also allows the U.S government to acquire an additional 500
    million doses. Our dependent variable is the production amount
    of COVID-19 vaccine by the of this year. They have target to
    manufacture 300 million doses. The independent variables could
    be licensed by the U.S. food and Drug Administration. Pzer is
    collaborating with BioNTech, a German biotechnology company,
    to develop COVID-19 investigational vaccines without U.S.
    government nancial support. If we add nancial support from
    WHO and U.S. and add more biotechnology companies then we
    can get our results with much less time.
    n
    X
    Y = β0 + β1 Xi
    i=1

    Where, Y is our outcome and Xi 's are independent factors and β1


    is slope. By using this model, we can forecast the production of
    corona doses. If we have more money and more production tools,
    then we will be able to produce as much corona doses as we
    need.
    Medical sciences
    Like we discuss the production of COVID-19 vaccine and if we
    manufacture as much doses as we need in the emergency areas by
    the end of this year, then we will see an increase in people's
    recovery and reduction in new corona cases. By using these
    scenario, we can predict when the virus will be controlled and
    people will return to a prosperous life.

    You might also like