This document discusses statistical concepts including white noise, moving averages, and MA(1) models. It presents an MA(1) model where the variable yt is equal to a constant mu plus the error term ut plus a coefficient teta1 multiplied by the lagged error term ut-1. The error term ut is described as following an approximate normal distribution with mean 0 and variance sigma squared.
This document discusses statistical concepts including white noise, moving averages, and MA(1) models. It presents an MA(1) model where the variable yt is equal to a constant mu plus the error term ut plus a coefficient teta1 multiplied by the lagged error term ut-1. The error term ut is described as following an approximate normal distribution with mean 0 and variance sigma squared.
This document discusses statistical concepts including white noise, moving averages, and MA(1) models. It presents an MA(1) model where the variable yt is equal to a constant mu plus the error term ut plus a coefficient teta1 multiplied by the lagged error term ut-1. The error term ut is described as following an approximate normal distribution with mean 0 and variance sigma squared.
Moving average MA(1) : yt = mu + ut + teta1 x ut-1 With ut following approximately a normal law of mean 0 and variance sigma square u Yt-1 = mu + ut-1 + teta1 x ut-2