Various Simulations and Time series analysis of various Data Sets
The objective is to fit an auto-regressive process to the recruitment data, which is number of new fish for a period of 453 months, ranging over 1950s till 1987, and we'll be using Yule-Walker equations in matrix form to estimate the parameters of the fitted model.
The objectives is, to fit an AR(p) model to Quarterly earnings in dollars per Johnson & Johnson share from 1960-1980.
Fit an ARIMA model into a real life dataset
Examine Ljung-Box Q-statistics for testing if there's an autocorrelation in a time series.
Look if there's a trend in the data
Look if there's a difference in the variation
Look at ACF, PACF. Akaike Information Criterion, sum of squared errors, and also Ljung-Box Q-statistics
Performing Difference operations to bring in stationarity
Trying various models and selecting the best on the basis pf simplicity and AIC
Fit sarima model to quaterly earnings of JOhnson and johnson share
Residual analysis
Forecast future values of the examined time series.
look at the time plot; if they need transformation, we're going to transform the data.
If we need differencing - seasonal or non-seasonal, we're going to do differencing.
look at ACF and PACF to determine our orders.
Once we have some idea of a lot about our orders PQ, we're going to look at a few different models
use the parsimony principle and choose the smallest AIC value.
residual analysis
Fit SARIMA model to Milk Production Data from TSDL(Time series data library)
Residual analysis
Forecast future values of examined time series.
fit SARIMA models to the dataset
forecast the future values of the same time series.
Analysed the temperature time series and Developed Holt-Winter Forecasting Method, ARIMA Seasonal Model in JMP.
Engineered a transfer function model for Temperature-Electricity consumption in JMP
Forecasted Electricity consumption for given next 6 months of temperatures.
Achieved forecasting accuracy of 97.9% using Seasonal ARIMA model in temperature forecasting.