Traditional linear model, Advanced Statistics

What is a Generalized Linear Model? A traditional linear model is of the form

691_Traditional linear model.png

where Yi is the response variable for the ith observation, xi is a column vector of explanatory variables for the ith response. Note that the p-dimensional vector xi is usually considered to be ?xed, or nonrandom. The p-dimensional vector β of unknown coe?cients is to be estimated on the basis of n observations. The errors i are assumed to be independent normally distributed zero-mean random variables with a constant variance. Hence, 1925_Traditional linear model1.png holds, that is, the expected value of the output random variable is a linear transformation of the input. All these assumptions are limitations and may not hold in some cases. In particular:

  • We may have non-normally distributed errors;
  • The mean µi may be restricted by the nature of the problem (for example, if it has a meaning of probability, it would be in (0,1)) but the linear predictor x0iβ of this mean is not restricted to this range;
  • It may be unrealistic to assume that the variance of the data is constant for all observations. (For example, the variance of Poisson data increases with the mean.)

These limitations are dealt with in the setting of the generalized linear model (GLM) or their generalization, the generalized additive model (GAM). GLM have been introduced in Statistics by Nelder and Wedderburn (1972).

Posted Date: 2/27/2013 12:33:56 AM | Location : United States







Related Discussions:- Traditional linear model, Assignment Help, Ask Question on Traditional linear model, Get Answer, Expert's Help, Traditional linear model Discussions

Write discussion on Traditional linear model
Your posts are moderated
Related Questions
The Null Hypothesis - H0: There is no autocorrelation The Alternative Hypothesis - H1: There is at least first order autocorrelation Rejection Criteria: Reject H0 if LBQ1 >

Cause specific death rate : A death rate calculated for the people dying from the specific disease. For instance, the below given are the rates per 1000 people for three disease cl

This graph for Cross Correlation Function for RES1, RES1 shows that there is possibly negative autocorrelation as there are alternating spikes; also the first spike is negative whi

Canonical correlation analysis : A process of analysis for investigating the relationship between the two groups of variables, by ?nding the linear functions of one of the sets of

In the time series plot and scatter graphs there were many outliers that were clearly visible. These have been removed to identify if they were influential or had high leverage and

Time series : The values of a variable recorded, generally at a regular interval, over the long period of time. The observed movement and fluctuations of several such series are

Remedian: The robust estimator of location which is computed by an iterative process. By assuming that the sample size n can be written as bk where b and k are the integers, the s

It is the technique used in the clinical trials when it is possible to make an acceptable place before an active treatment but not to make the two active treatments identical. In t

Response feature analysis is the approach to the analysis of longitudinal data including the calculation of the suitable summary measures from the set of repeated measures on each

Cohort study : An investigation in which the group of individuals (or the cohort) is identi?ed and followed prospectively, possibly for many years, and their subsequent medical his