ECON 174 Lecture Notes - Lecture 3: Null Hypothesis, Standard Deviation, Normal Distribution
Document Summary
Ex: autoplot(rwf(eggs, drift = true, lambda = 0. 4, biasadj = true) Reverse box-cox transformation with bias adjustment is where h is the h-step forecast variance - standardized variations over time. We will refer to one-step ahead forecasts y t|t 1 as fitted values. A residual is the difference between the observation and the fitted value. Ex: et = yt y t actual - predicted value = residual of error. Any good forecasting model should satisfy the following two properties: Autoplot(goog200, series = data ) + autolayer(fits, series= fitted ) + xlab( day ) + ylab( closing price (us$) ) + ggtitle( google stock (daily ending 6 december 2013) ) Otherwise it must be available information is left on the table and the forecast can be improved. Compute mean and standard deviation in the sample. Means usually can"t be exactly zero but close. Zscore < (mean(na. omit (res)) 0)/ (sd(na. omit (res))/sqrt(nrow(na. omit (res))))