# Empirical Results From The Modeling Of Claim Inflation

735 Words3 Pages
4.2 ARIMA MODEL This chapter displays the empirical results from the modeling of claim inflation using ARIMA model. Data Description Series=claim inflation Sample 1984-2014 Observations=30 Mean=2.748 Median=2.415 Minimum=1.25 Maximum=7.15 Standard deviation=1.43012 Kurtosis=1.679 Skewness=1.354 4.2.1 Descriptive Statistics for the claim inflation series The data is not stationary since it does not exhibit a certain state of statistical equilibrium showing that the variance changes with time. Performing a log transformation still produces a non-stationary process in which case we should difference the series before continuing. ACF and PACF 4.2.2 Unit Root Test for CPI Series Test for unity we use the ADF test for unit test hypothesis; Ho: the CPI has unit root (non-stationary) Vs H1: CPI data has no unit root (stationary). Augmented Dickey fuller test Data: log.claiminf Dickey-fuller = -9.6336 lag order=12 p-value=0.01 Alternative hypothesis stationary warning message: 4.2.3 Model Identification, Estimation and Interpretation ARIMA models are univariate models that consist of an autoregressive polynomial, an order of integration (d), and a moving average polynomial. Since Claim inflation became stationary after first order difference (ADF test) the model that we are looking at is ARIMA (p, 1, q). We have to identify the model, estimate suitable parameters, perform diagnostics for residuals and finally forecast the inflation series.