MAKE MOST OF THE KNOWLEDGE NETWORK, JOIN ACADEMIC RESEARCH FOUNDATION

Journal of Agriculture, Biology and Applied Statistics

Journal of Agriculture, Biology and Applied Statistics

Frequency :Bi-Annual

ISSN :2583-4185

Peer Reviewed Journal

Journal Home

Table of Content :-Journal of Agriculture, Biology and Applied Statistics, Vol:1, Issue:1 , Year:2022

State of the Art in COVID-19 in the SAARC Countries and China using BATS,TBATS, Holt's Linear and ARIMA Model

BY :   Pradeep Mishra, Mostafa Abotaleb, Kadir Karakaya, Amr Mostafa, Harun Yonar, Hazhar Talaat Abubaer Blbas, Umme Habibah Rahman and S S Das
Journal of Agriculture, Biology and Applied Statistics, Year:2022, Vol.1 (1 ), PP.1-24
Received:05 January 2022 | Revised:25 January 2022 | Accepted :19 February 2022 | Publication:30 June 2022
Doi No.:doi.org/10.46791/jabas.2022.v01i01.01

Corona Virus is the biggest global health disease and it is an epidemic according to the World Health Organization (WHO). The purpose of this paper is to identify the best fitted model among BATS, TBATS, Holt's linear trend and ARIMA based on the minimum value of AIC and MAE and forecasting data about corona virus from SAARC and China countries. Cumulative daily data about covid19 has been collected from 3 January, 2020 to 10 March, 2021in the world health organization (WHO) in both infection and death cases. BATS, TBATS, Holt's linear trend and ARIMA models with some selection criteria are used to forecast the next Covid-19 situation in SAARC and China usin  R Language Program. According to Akaike Information Criterion (AIC), Holt's linear trend model is the best model and better than both BATS and TBATS models in both infection and death cases. Depending on MAE criteria, ARIMA is the best fitted model for Nepal, Pakistan, Sri Lanka, and Bangladesh countries for both death and infection cases while Holt is the best fitted model for both India and Myanmar countries in both cases. On the other hand, BATS is the best fitted model for both death and infection cases in China.


Keywords: ARIMA,BATS, BATS, Holts Linear, MAE, AIC, COVID-19, Forecasting.

Pradeep Mishra, Mostafa Abotaleb, Kadir Karakaya, Amr Mostafa, Hynur Yonar, Hazhar Talaat Abubaer Blbas, Umme Habibah Rahman and S S Das. (2022). State of the Art in COVID-19 in the SAARC Counties and China using BATS,TBATS, Holt's Linear and ARIMA Model. Journal of Agriculture, Biology and Applied Statistics. Vol. 1, No. 1, pp. 1-24.

A Comparative Study between (ARIMA - ETS) Models to Forecast Wheat Production and its Importance's in Nutritional Security

BY :   Shweta Shrivastri, Khder Mohammed Alakkari, Priyanka Lal, Aynur Yonar, and Shikha Yadav
Journal of Agriculture, Biology and Applied Statistics, Year:2022, Vol.1 (1 ), PP.25-37
Received:15 January 2022 | Revised:09 February 2022 | Accepted :19 March 2022 | Publication:30 June 2022
Doi No.:/doi.org/10.46791/jabas.2022.v01i01.02

Wheat, which has been one of the most important food sources for humans for centuries, has a special place in the economy of India and its states due to its substantiality in food security, trade, and industry. Thus, the forecasting of wheat production is of great importance because it allows them to cope with food problems they may encounter in the future. This study aims to set up models and forecasts for wheat production in India and its five states: Uttar Pradesh (UP) - Punjab (PB) - Madhya Pradesh (MP) - Haryana - Rajasthan (RJ) by using annual time series data from 1956 to 2020. The ARIMA and ETS models were conducted and the best-fitted models to forecast wheat production were selected with respect to performance indicators of Akaike information criterion (AIC) and root mean square error (RMSE) for each state and India. The most appropriate models were determined as ARIMA (1,1,0) for UP, ARIMA (0,1,1) for PB, ETS (M, M, N) for MP, ETS (M, MD, N) for Haryana, ETS (M, N, N) for JR, and ETS (A, A, N) for India for forecasting wheat production from 2021 to 2030.

Keywords: ARIMA; ETS; Time series;Production; Forecasting.

Shweta Shrivastri, Khder Mohammed Alakkari, Priyanka Lal, Aynur Yonar & Shikha Yadav. (2022). A Comparative Study between (ARIMA-ETS) Models to Forecast Wheat Production and its Importance’s in Nutritional Security. Journal of Agriculture, Biology and Applied Statistics. Vol. 1, No. 1, pp. 25-37

Modeling and Forecasting of Producer Price Index (PPI) of Cheese Manufacturing Industries

BY :   Shikha Yadav, Ammar Kadi, Soumik Ray, Deepa Rawat, Tufleuddin Biswas, Pankaj Kumar Singh and Mostafa Abotaleb
Journal of Agriculture, Biology and Applied Statistics, Year:2022, Vol.1 (1 ), PP.39-49
Received:09 February 2022 | Revised:06 March 2022 | Accepted :19 April 2022 | Publication:30 June 2022
Doi No.:doi.org/10.46791/jabas.2022.v01i01.03

Modeling and forecasting of complex time series data has grown as an attractive field thanks to machine learning. The PPI (Producer Price Index) of cheese manufacturing businesses was examined in this study utilizing a machine learning technique. Training and testing data sets were created for the goal of creating and validating a model. After that, we built deep learning models such as LSTM, BILSTM, and GRU and tested them on a training data set using metrics such as ME, RMSE, MAE, MPE, MAPE, and ACF1. These deep learning models were compared on the basis of RMSE for the testing data set. On this set of data, the LSTM model outperforms the BILSTM and GRU models in terms of machine learning performance. These three models’ forecasting abilities are nearly identical. Policymakers and academics may find this study useful in building a body of knowledge about PPI in the cheese manufacturing industry. As a result, we feel that this work can be used as a textbook on how to apply machine learning techniques to complex time series.

Keywords: Producer Price Index (PPI); LSTM ;BILSTM; Forecasting.

Shikha Yadav, Ammar Kadi, Soumik Ray, Deepa Rawat, Tufleuddin Biswas, Pankaj Kumar Singh & Mostafa Abotaleb (2022). Modeling and Forecasting of Producer Price Index (PPI) of Cheese Manufacturing Industries. Journal of Agriculture, Biology and Applied Statistics. Vol. 1, No. 1, pp. 39-49.

Role of Probability Models for Enhancing the Information of Temperature and Relative Humidity in Hoshangbad

BY :   Kadir Karakaya and Vikas Jain
Journal of Agriculture, Biology and Applied Statistics, Year:2022, Vol.1 (1 ), PP.51-61
Received:22 February 2022 | Revised:30 March 2022 | Accepted :21 April 2022 | Publication:30 June 2022
Doi No.:doi.org/10.46791/jabas.2022.v01i01.04

In this paper, temperature and relative humidity are modeled using some well-known statistical distributions such as normal, logistic, Weibull, and gamma and lognormal. The mean minimum temperature, maximum temperature, morning relative humidity, and evening relative humidity were obtained monthly between 1996 and 2018. Parameter estimations are obtained by the maximum likelihood principle. The unknown parameter estimates of the distributions mentioned above are obtained by the principle of maximum likelihood. Data was combined on a monthly basis and modeled monthly. The minimum temperature, maximum temperature, morning relative humidity, and evening relative humidity are modeled and the best-fitted model is reported. For the best model, some information criterion and the Kolmogorov Smirnov statistic are reported.The best model for each month is given separately. With these models, modeling and desired probabilities can be calculated using the modeling results for any month.This weather infrormation helps farmers for makig plannning for farming of crops in the field.

Keywords: Humidity, Temperature, Statistical distribution, Kolmogorov-Smirnov test

Kadir Karakaya & Vikas Jain. (2022). Role of Probability Models for Enhancing the Information of Temperature and Relative Humidity in Hoshangbad. Journal of Agriculture, Biology and Applied Statistics. Vol. 1, No. 1, pp. 51-61.

A DEA Analysis of Farm Efficiency of KVK Adopted and Non- Adopted Farms in Khargone District of Madhya Pradesh

BY :   Sachin Yadav and Gourav Kumar Vani
Journal of Agriculture, Biology and Applied Statistics, Year:2022, Vol.1 (1 ), PP.63-67
Received:03 April 2022 | Revised:25 April 2022 | Accepted :19 May 2022 | Publication:30 June 2022
Doi No.:doi.org/10.46791/jabas.2022.v01i01.05

The study was conducted in Khargone district of Madhya Pradesh state in India. Primary data was collected from farms on various aspects pertaining to farm operations. Farms were divided into two groups, adopted and non-adopted by KVK. The study examined the technical, allocative, and economic and scale efficiency of the adopted and non-adopted farms estimated using data envelopment analysis. This study measured the average level of technical efficiency (vrs), scale efficiency and economic efficiency in kharif season were 0.597, 3.194 and 0.801 for adopted farms and 0.576, 2.268 and 0.737 for non-adopted farms, respectively. The average level of technical efficiency(vrs), scale efficiency and economic efficiency in rabi season were 0.67, 5.22 and 1.40 for adopted farms and 0.73, 2.60 and 1.29 for non-adopted farms, respectively. No significant difference was found in the mean efficiency score of adopted non-adopted famers except for technical and scale efficiency in rabi season. The major policy implication includes increasing farm mechanisation to sustain scale efficiency and rationalization of input use in kharif season.

Sachin Yadav & Gourav Kumar Vani. (2022). A DEA Analysis of Farm Efficiency of KVK Adopted and Non- Adopted Farms in Khargone District of Madhya Pradesh. Journal of Agriculture, Biology and Applied Statistics. Vol. 1, No. 1, pp. 63-67.

Displaying articles 1-5