Explore publications.

This study mainly aimed to investigate the impact of seasonal changes on media advertising revenues (AR) in R environment through a visual-print media company example. So, the study primarily aimed to examine whether visual, print and internet ARs were affected by seasonal change. The study also aimed to indicate the trends of visual/ print/ and internet ARs over time in the light of seasonality. Furthermore, it was also aimed to make AR estimates for the next year with the best performing methods covering ARIMA and ETS. Methodologically, R programming language and its libraries were used together with ARIMA and ETS time series models. The data set consisted of a monthly ARs series consisting of 180 rows covering the period between January/2007-December/2021 and having a sufficient number of observations for the application of the models. Data were analyzed with R and next year’s forecasts were done with ARIMA and ETS. The study revealed that all AR types were affected by seasonal changes in the specified period and included seasonality, i.e. specially in the summer months.  Additionally, it was observed that AR types have different trends despite containing seasonality. The study found that visual ARs denoted a slight downward trend including seasonality during the period. It was also indicated that print ARs reflected a very rapid and drastic downward trend covering seasonality. The study also revealed that internet ARs showed a very rapid and sharp upward trend compared to the other two AR types despite having seasonality. Furthermore, taking into account the calculated error metrics, it was found that the ARIMA model showed the best estimation performance in both i.e. visual and internet ARs. On the other hand, the ETS model indicated the best estimation performance in print ARs. Accordingly, estimations of the visual/print and internet ARs for the next year were made with the best performing methods. It was pointed out that estimated ARs included seasonality in the summer months and revealed similar results to the previous trends based on historical data.

This paper employs the R software in identifying the most suitable ARMA model for forecasting the growth rate of the exchange rate between the US dollar and a unit of the British pound. The data is systematically split into two distinct periods identified as the in-sample period and the out of sample period. The best model selected for the in-sample period is used to make forecasts for the out of sample period. Both traditional and rolling window forecasting methods are employed. This research uses the MSE, MAE, MAPE and correct sign prediction criterion to compare the forecasting performance of the rolling window forecasting method and the traditional forecasting method. The results obtained suggest that the traditional forecasting method performs better judging by MSE, MAE and MAPE. In other words, the traditional forecasting method is more suitable for predicting the magnitude (i.e., size) by which the US /UK exchange rate changes over time. However, the results also suggest that the rolling window forecasting method performs better based on the correct sign prediction criterion. In other words, the rolling window forecasting method is more appropriate for predicting the changes in the sign of the US /UK exchange rate.