Agricultural Research Management Information System

Home
Research Summary
Search
About Us
- ARMIS
- Brochure
Contact Us
Report
User Request
Data Input
Help
- Operation Manual
  - PDF
  - Video
- Program Area & Commodity
We have reached 37600 number of research entries at this moment.

- Logout

Research Detail

Home
Research
Detail

Measurement of Growth Rate, Instability and Forecasting of Aus Rice Production in Bangladesh

M.F. Imam
Department of Agricultural Statistics Bangladesh Agricultural University Mymensingh-2202 Bangladesh

M.A. Awal
Agricultural Economics, Regional Agricultural Research Station, Bangladesh Agricultural Research Institute, Rahmatpur, Barisal, Bangladesh

M.K.J. Bhuiyan
Department of Agricultural Statistics Bangladesh Agricultural University Mymensingh-2202 Bangladesh

Abstract/ Executive Summary:

The present study was under taken to measure the best growth rate, instability and forecast the Aus rice production in Bangladesh. The study based on secondary time series Aus rice production data during the period of 1969-70 to 2004-05 in Bangladesh. Nine- deterministic time series models are considered for the growth analysis. The estimate of the magnitude of instability in Aus rice production was attempted by computing the coefficient of variation (Cv) and the percentage deviation from three-years moving average values. The study revealed that the Aus local production was observed to be relatively stable (CV being 61 percent) compared to the total production (CV being 69 percent) and production from modern variety (CV being 95 percent). It was found that for total Aus and modern rice production, the cubic model is the most appropriate whereas quadratic model is appropriate for local variety. Five-years forecasting results showed that the total Aus rice production in the year of 2005/06 was 1834 million metric ton w.th a 95 percent confidence interval of (1203, 1834). In case of modern and local varieties Aus rice production in the year of 2005/06 were 1172 million and 561 metric tons respectively. If the present growth rates continued then the total Aus rice production in Bangladesh was 2287 million metric tons in the year of 2009/10 with approximately ±1908 million metric tons.

Keywords: Growth model, Instability, Fluctuation, Forecasting

Location: Bangladesh Agricultural University Mymensingh

Start Date:

End Date:

Program Area: Socio-economic and Policy

Commodity: Rice

Objectives:

To illustrate production instability and to formulated forecast of Aus rice production in different varieties overall in Bangladesh by using the best fitted models.

Methodology:

The present study was conducted using secondary time series Aus rice production data from Bangladesh during the period of 1969-70 to 2004-05. The data were collected from the various publication of Bangladesh Bureau of Statistics. The models those are used to describe the behavior of variables that vary with respect to time are termed as growth models. This type of model is needed in a specific area and in a specific problem that depends on the type of growth that occurs in the time series data. In general, growth models are mechanism rather than empirical ones. A mechanical growth model usually arises as a result of making assumptions about the type of growth. On the other hand, an empirical model is chosen empirically to approximate an unknown mechanistic model. Typically the empirical model is a polynomial of some suitable order. However, in this study, Linear, Logarithmic Inverse, Quadratic, Cubic, Power, S-Shape, Exponential and Compound growth models were considered. Model selection criteria: To identify the best model for a particular time series data the latest available diagnostic tools are R², Adjusted R², RMSE, AIC, SIC, (BIC), MAE, MSE and MAPPE. Measures of instability in export: The measurement of instability in time series data requires an explicit assumption of what constitute the acceptable and unacceptable components. A systematic component, which can be predicted, does not constitute instability and hence, it should be eliminated from data. The remaining unpredictable component represents the instability. Two methods, viz., moving average and trend fitting have been used to capture the predictable component. Here the preference is for three-year moving average since this form may more adequately keep in touch with influences on trend earnings, such as Changing comparative advantage and policy changes. The estimate of the magnitude of instability in the time series data on exports had been attempted by computing the coefficient of variation (CV) and the percentage deviation from three-years moving average values.

Source of Information: Bangladesh J. Agril. Sci. 33(1): 85-92, January, 2006; ISSN 0379-4296

Article Link (Online Journal):

Funding Source:

Total Budget (Tk.) :

Achievement/Findings:

The study revealed that the Aus local production was observed to be relatively stable (eV being 61 percent) compared to the total production (CV being 69 percent) and production from modern variety (CV being 95 percent). It was found that for total Aus and modern rice production, the cubic model is the most appropriate whereas quadratic model is appropriate for local variety. Five-years forecasting results showed that the total Aus rice production in the year of 2005/06 was 1834 million metric ton w.th a 95 percent confidence interval of (1203, 1834). In case of modern and local varities Aus rice production in the year of 2005/06 were 1172 million and 561 metric tons respectively. If the present growth rates continue then the total Aus rice production in Bangladesh will be 2287 million metric tons in the year of 2009/10 with approximately ±1908 million metric tons.

Knowledge Management: Journal