Care with older and younger age groups may require

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ethod of Graduation Methods of graduation Graphical graduation Comparison of different graduation methods I Graduation by parametric formula used when large amounts of data available (the method does not work well when data are scanty over a wide age range). produces extremely precise results produces smooth results for a small enough no of parameters can optimize the fitting statistically and therefore eliminates any subjectivity form the fitting process. it is very well-suited for use in constructing standard tables (asymptotic) standard errors of fitted parameters available when maximum likelihood used 64/72 Actuarial Statistics – Module 8: Method of Graduation Methods of graduation Graphical graduation Comparison of different graduation methods II hard to find a suitable curve that fits an experience well at all ages. care with older and younger age groups - may require different formulae for different ages problems with heterogeneity (differences in diet, smoking habits, levels of exercise etc.) Graduation by reference to a standard table Relatively simple to apply Only a few parameters usually need to be fitted and therefore can fit small data sets Usually produces smooth rates, as it is a simple function of the standard table, which is smooth Easier to fit the high and low ages Not suitable for producing standard tables with large amounts of data, as it does not fully represent the data. 65/72 Actuarial Statistics – Module 8: Method of Graduation Methods of graduation Graphical graduation Comparison of different graduation methods III It heavily depends on the form of the standard table chosen. Care with choice of standard table. Graphical graduation useful where accuracy is not the main consideration inappropriate for the production of standard tables can be used where data are relatively scarce requires a good deal of experience to do properly it is subjective great deal of flexibility in shape 66/72 Actuarial Statistics – Module 8: Method of Graduation Methods of graduation Statistical Tests 1 Introduction 2 Testing smoothness 3 Statistical tests Preliminaries Chi-square (χ2 ) test Standardised Deviations Test Signs test Cumulative Deviations Test Grouping of Signs Test Serial Correlations Test 4 Methods of graduation Preliminaries Graduation by Parametric Formula Graduation by Reference to a Standard Table Graphical graduation...
View Full Document

This document was uploaded on 04/03/2014.

Ask a homework question - tutors are online