In this study, an Econometric analysis has been conducted to identify the important factors that affect the food grain productions inBangladesh. Here, we have considered time series data for the years from 1989- 1990 to 2019-2020. Vector Autoregressive (VAR)Model and Autoregressive Integrated Moving Average (ARIMA) model have been considered in this study. Both these modelshave been considered to forecast the productions of food grains in Bangladesh. The forecasting performances of these two modelshave been compared by using RMSE, MAE, and MAPE. It has been found that the VAR model is better than the ARIMA model toforecast the food grain production. On the other hand, it has been come out from the analysis that there is no significant impact ofchemical fertilizer on the food grain production, but irrigation area has significant impact on the food grain production. Among thethree variables: food grain production, irrigation area and chemical fertilizer, there exists short run relationship. Dhaka Univ. J. Sci. 70(1): 8-13, 2022 (January)

Forecasting behavior of Econometric and Machine Learning models has recently attracted much attention in the research sector. In this study an attempt has been made to compare the forecasting behavior of Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) using univariate time series data of annual rice production (1972 to 2013) of Bangladesh. Here, suitable ARIMA has been chosen from several selected ARIMA models with the help of AIC and BIC values. A simple ANN model using backpropagation algorithm with appropriate number of nodes or neurons in a single hidden layer, adjustable threshold value and learning rate, has been constructed. Based on the RMSE, MAE and MAPE values, the results showed that the estimated error of ANN is much higher than the estimated error of chosen ARIMA. So, according to this study, it can be said that the ARIMA model is better than ANN model for forecasting the rice production in Bangladesh. Dhaka Univ. J. Sci. 68(2): 143-147, 2020 (July)

Critical flicker frequency (CFF) of 40 men, 20 mentally retarded whose mean age was 22.0 yr. and 20 normal whose mean age was 21.5 yr., was measured under binocular viewing using the Lafayette Visual Perception Control with a display unit. Subjects had been previously tested for visual acuity and color blindness. Analysis showed a significant difference in CFF between mentally retarded persons and normal individuals, the former having lower CFF than the latter. This finding suggests lower perceptual sensitivity of the mentally retarded persons. Further research with provision for EEG recordings is suggested.

An attempt has been made to study various models regarding watermelon production in Bangladesh and to identify the best model that may be used for forecasting purposes. Here, supply, log linear, ARIMA, MARMA models have been used to do a statistical analysis and forecasting behavior of production of watermelon in Bangladesh by using time series data covering whole Bangladesh. It has been found that, between the supply and log linear models; log linear is the best model. Comparing ARIMA and MARMA models it has been concluded that ARIMA model is the best for forecasting purposes.

In this study we used Autoregrressive Intigrated Moving Average (ARIMA) and Vector Autoregrressive (VAR) model to analyze and forecast the price of total Jute Goods with four of its types, where data has been collected from Bangladesh Jute Mills Corporation (BJMC) from the year 1980-81 to 2013-2014. In this study, a comparison has been made regarding ARIMA model and VAR model to investigate which model is the best to forecast. The methodology employed in this study is the co-integration and Granger Causality under VECM. The Augmented Dickey Fuller (ADF) Test has been performed to test the stationarity of the data set. The findings of this study suggested that in forecasting the price of jute goods of Bangladesh, the ARIMA model is more efficient than VAR model. Dhaka Univ. J. Sci. 66(2): 91-94, 2018 (July)