Question
Ls4202_endsem_2016
please answer only question no.2. (5 marks)
203, hn LS4203 Biod a Biostatistics)Biostatistics: Presentation Presentation. ts4201 Struc file meuse Soura %20Roy/Documents Ls4202 Bio stat%20p%20n 20 op downloaded%20from %20drive obert%2Dsi 201 apdr Section 1: Answer all questions. Marks: 5x6 30 1. The regression function is the conditional expectation of Y for any given values of x1.x2 Xi denoted as E(Yln, 12, 1.) =+ 3,F1 + + Alk-State the assumptions of the linear regression model regarding the Y, and X, . Then, for k = l and for n o!servations y, Ya-...), show how you can derive the least squares line Yi-+ 8 . Under what conditions or properties of a response variable y is a Generalized Linear Model (GLM) needal over a simple linear regression model? Given the need for a CLAM to model your data, whist ate the basic compouents of a GLM that you would need? 33 In the context of testing GLMs, what is residual deriance and nuil deance? Hon can sou use this in hypothesis tests pertaining to the eflect of a predictor arialk X? 4. Write dlown the expression for the Akike Idormation Citerion (AJ) anid esplam its compouenits What is the basis of its use in model selerction? The l".qustion : tnales ier×ns fet" les ittnonu, st,,, ttiit1,2th lunut s ichnitt inui
Explanation / Answer
Q 2. Ans: The generalized linear model is an extension of the general linear model that allows the specification of models whose response variable follows different distributions other than a normal distribution. For example, logistic regression where the dependent variable is categorical) or Poisson regression (where the dependent variable is a count variable) are both generalized linear models. For the generalized linear model different link functions can be used that would denote a different relationship between the independent variables and the response variable such as log function for the Poisson.
