Agriculture
Research Paper
E-ISSN No : 2454-9916 | Volume : 8 | Issue : 11 | Nov 2022
A STOCHASTIC PROCESS IN MODELING AND FORECASTING OF ONION PRODUCTION IN INDIA 1
1
Dr. Sameerabanu P , Dr. C. Sekhar 1
Nalanda College of Agriculture, M.R.Palayam, Tiruchirappalli, India.
ABSTRACT This work focuses on modeling and analysis of crop yield over space and time. Specifically, the onion yield data set was used. This study on estimating the future yield of onions in major producing states in India. To achieve this, we applied time series on onion yield data recorded from 1978 to 2020, as per availability from the website of Ministry of Agriculture, Government of India. By using SPSS software, The data are analyzed using the autoregressive integrated moving average (ARIMA) model to best fit the model. Selected best models were used to estimate onion yield. The selection of a suitable model requires determining the efficiency of different models in predicting future outcomes and selecting the most suitable model for the prediction work. To develop a suitable forecast ARIMA model for agricultural data. To study the predictive ability of the univariate ARIMA model to suggest an optimal model, the best predictive model was selected. KEYWORDS: ARIMA, ACF, PACF, Onion forecast. INTRODUCTION: Farming sector faces several challenges from land preparation to harvesting and marketing of farm produce. The consumers of farm output though are healthy and wealthy; they are able to bargain to the lowest price for the output realized. The traders are having collusion and their association is strong enough to bargain from the farmers. But the farmers and the farmer organizations are weak in their association and cannot be unified to establish an organization to the fullest spirit to command price for their produce. Though there were few farmer organizations in our country, they cannot raise to the expected level in achieving or distributing the farm produce. During the time of harvest, supply will be excess and the demand will be less and hence proper storage and distribution is a must. State Governments took effort to procure the principal crop outputs particularly in respect of cereals like rice and cannot procure other farm produce timely and hence balancing the area under crop and its output production becomes much more important. For that, information on price availability, demand for that produce and expected price for the output by the farmers are to be provided in advance prior to the crop season. In this respect, forecasting is the tool that will help to predict the yield and price in advance. Forecasting refers to the practice of predicting what will happen in the future by taking into consideration events in the past and present. Basically, it is a decision-making tool that helps businesses cope with the impact of the future’s uncertainty by examining historical data and trends. It is a planning tool that enables businesses to chart their next moves and create budgets that will hopefully cover whatever uncertainties may occur (CFI, 2022). This study is the one that aimed at forecasting the yield of onion in India.
Ÿ
Forecasts are based on opinions, intuition, guesses, as well as on facts, figures, and other relevant data. All of the factors that go into creating a forecast reflect to some extent what happened with the business in the past and what is considered likely to occur in the future.
Ÿ
Most businesses use the quantitative method, particularly in planning and budgeting activities
Collection of Data: The secondary data was collected from the website of Ministry of Agriculture, Government of India. Onion production over a period of time was gathered from the above website and is analyzed using ARIMA models. By using SPSS software, the data was analyzed to fit the best model using an autoregressive integrated moving average (ARIMA) model. The selected best models were used to forecast the onion yield. ARIMA Modeling: In general, an ARIMA model is characterized by the notation ARIMA (p,d,q) where, p, d and q denote orders of autoregression integration (differencing) and moving average respectively. Time series is a linear function of past actual values and random shocks. For instance, given a time series process {Yi}, a first order auto-regressive process is denoted by ARIMA (1,0,0) or simply AR(1) and is given by Y i = μ + φ 1Y i-1 + ε t
METHODOLOGY: This study aimed at forecasting the yield of Onion in India. For that the basis of forecasting is to be discussed to develop an overall idea. The first step in the process is developing the basis of the investigation and identifying where the business is currently positioned in the market. Forecasting Methods: Businesses choose between two basic methods when they want to predict what can possibly happen in the future, namely, qualitative and quantitative methods. 1.
Qualitative Method: Otherwise known as the judgmental method, qualitative forecasting offers subjective results, as it is comprised of personal judgments by experts or forecasters. Forecasts are often biased because they are based on the expert's knowledge, intuition, and experience, and rarely on data, making the process non-mathematical. One example is when a person forecasts the outcome of a finals game in the NBA, which, of course, is based more on personal motivation and interest. The weakness of such a method is that it can be inaccurate.
2.
Stationary: A stationary time series does not depend on the time when a particular point is observed. Each point in time has a value that is not dependant on another point in time, such as white noise. The plots below are some examples of stationary time series. Other examples may include cyclic data with non-consistent periods. Differencing: Differencing is a time series transformation that attempts to eliminate timedependent factors from the time series such as trend and seasonality. There are different orders of differencing; the equation below shows the first-order difference. It is simply the difference between the current and previous observation:
After the first-order difference, if the time series is still not stationary, differencing once more will give you the second-order differencing.
Quantitative Method: The quantitative method of forecasting is a mathematical process, making it consistent and objective. It steers away from basing the results on opinion and intuition, instead utilizing large amounts of data and figures that are interpreted.
Features of Forecasting: Here are some of the features of making a forecast: Ÿ Forecasts are created to predict the future, making them important for planning.
The order of the differencing can be defined in the d parameter of the model. Autoregressive Models: An autoregressive (AR) model, defined as being the regression of it, is simply a
Copyright© 2022, IERJ. This open-access article is published under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License which permits Share (copy and redistribute the material in any medium or format) and Adapt (remix, transform, and build upon the material) under the Attribution-NonCommercial terms.
International Education & Research Journal [IERJ]
56