Submit or Track your Manuscript LOG-IN

A Statistical Study of the Determinants of Rice Crop Production in Pakistan

A Statistical Study of the Determinants of Rice Crop Production in Pakistan

Muhammad Akbar Ali Shah1, Gamze Özel2, Christophe Chesneau3, Muhammad Mohsin4, Farrukh Jamal5* and Muhammad Faheem Bhatti6 

1Department of Statistics, The Islamia University of Bahawalpur, Pakistan; 2Department of Statistics, Hacettepe University, Turkey; 3Department of Mathematics, LMNO, University of Caen, Caen, France; 4Department of Geography, Govt. Degree College (Boys), Choti Zareen, D.G. Khan, Pakistan; 5Department of Statistics, Govt. S.A. Postgraduate College, Dera Nawab Sahib, Bahawalpur, Pakistan; 6Department of Statistics, The Islamia University of Bahawalpur, Pakistan.

drfarrukh1982@gmail.com  

ABSTRACT

Rice is the third major and second main staple crop of Pakistan. The main objective of the current research is to discover the determinants of the rice production of Pakistan to improve the production and fulfill the increasing demand. The study conducted in district Lodhran (Punjab province) and 31 villages selected as samples randomly. Time series data collected from Crop Reporting Service (CRS) for the period of last 10 years (2005-2014) containing 516 cases and 14,964 observations. Two different multiple linear regression (MLR) models are applied to study the relationship between the yield of rice (dependent variable) and the various factors (independent variables) which are affecting the rice crop production. The Model I is based on monthly average temperature and humidity during crop period and Model II is based on average temperature and humidity during crop period. The factors affecting rice crop production are also tested. Durbin-Watson test is applied to measure the serial correlation in the residuals and variation inflation factor (VIF) is also applied to test the multicollinearity. The VIF values of independent variables in Model I indicate the presence of multicollinearity and Durbin-Watson test shows autocorrelation in Model I whereas Model II is recommended due to the better value of R² with Durbin-Watson test and found no pattern of multicollinearity. The three most important factors that affect the yield per acre in mounds (1 mound= 40 kg) are DAP and Urea Fertilizer and Disease attack respectively. Thus, Model II is acceptable for the estimation of rice yield not only for district Lodhran but also for the case of Pakistan. 

 

To share on other social networks, click on P-share. What are these?

Pakistan Journal of Agricultural Research

June

Vol. 33, Iss. 2, Pages 192-421

Featuring

Click here for more

Subscribe Today

Receive free updates on new articles, opportunities and benefits


Subscribe Unsubscribe