Estimations of means and variances in a Markov linear model

Description

Multivariate regression models and ANOVA are probably the most frequently applied methods
of all statistical analyses. In the second chapter of this thesis, we propose an alternative
to the classic approaches that do not assume homoscedasticity or normality of the error term
but assumes that a Markov chain can describe the covariates’ correlations. This approach
transforms the dependent covariate using a change of measure to independent covariates. The
transformed estimates allow a pairwise comparison of the mean and variance of the contribution
of different values of the covariates. We show that under standard moment conditions,
the estimators are asymptotically normally distributed. Additionally, we test our method with
simulated data and apply it to several classic data sets.

Period	10 Sept 2020
Event title	8th Austrian Stochastics Days
Event type	Conference
Location	Graz, AustriaShow on map
Degree of Recognition	National