You are here

Comparative regression analysis of the number livestock and poultry in Ukraine and Belarus for the period of 1990-2016

The paper analyzes possible curvilinear regressions, which correspond to the reduction of the number of animals during the crisis period and increase their number when one exit the crisis. From the obtained differential equations, it is shown that during the crisis period, when there is not enough resources in agricultural enterprises for the extended reproduction of the dynamics of the population, the exponential, logistic regression and their modifications may correspond. Exit from a crisis situation is possible with significant increase of investments. During this period, the dynamics of the stock may correspond to logistic regression or modification.
An analysis of the dynamics of the number of cows, pigs, sheep, goats and poultry in Ukraine and Belarus during the period of 1990-2016 was made. It has been shown that in Ukraine, starting in 1991, when a change of ownership took place in the course of the collapse of the Soviet Union, there was a crisis in animal husbandry. This crisis continues at present, with the exception of poultry farming. The number of poultry has started to increase since 1998, which is explained by significant volumes of state financing of this branch of livestock, especially large poultry farms.
It was found that the dynamics of the number of cows and pigs corresponded to the modified exponential regression. The dynamics of sheep and goats corresponded to the logistic regression of Pearl-Reed. From 1991 to 1997, the number of birds decreased by exponential law, and since 1998, increased in accordance with the logistic regression of Pearl-Reed. According to the received regressions, it is forecasted that in 2020 in Ukraine there will be 1.823 million head of cows, 1.407 million head of sheep and goats, and 322.17 million head of cattle.
In Belarus there was another trend. From 1991 to 2003, the number of pigs decreased, and since 2004 increased. Similarly, the number of cows, together with sheep and goats, declined in line with 2009 and 2005, then increased. Beginning in 1995, the number of birds has increased steadily. The dynamics of the reduction and increase in the number of cows, pigs, sheep, goats, and poultry in Belarus corresponded to the modified logistic regressions of Pearl-Reed.
The Belarusian experience confirms that in order to start the outbreak of the livestock sector from a crisis, it is necessary to increase the volume of investments in the fixed capital of the industry at least – 6 times. This output will be gradual, since the resulting increasing regressions are symmetric decreasing. At the same time, in Ukraine, it is necessary to raise the level of procurement prices for milk and meat, increase the volume of state subsidies to agricultural producers. This will restore the volume of agricultural production, will create favorable conditions for the launch of the modernization process on a modern basis, which in turn will contribute to increasing the efficiency of production and competitiveness of national agrarian commodity producers both in the domestic and world markets.
Key words: logistic regression, curvilinear regression, forecasting, livestock, dynamics of livestock.
 1. Linnik Ju.V. (1962). Metod naimen'shih kvadratov i osnovy matematiko-statisticheskoj teorii obrabotki nabljudenij [The method of least squares and the foundations of the mathematical and statistical theory ofobservation processing]. L., Fizmatgiz, 352 p.
2. Guorfi L., Kohler M., Krzyzak A. and Walk H. A. (2002). Distribution-Free Theory of Nonparametric Regression. Springer, New York, 647 p.
3. Clements M.P., Hendry D.F. Forecasting economic processes. International Journal of Forecasting, 1998, vol. 14, pp. 111-131.
4. Holt C.C. Forecasting trends and seasonal by exponentially weighted averages. International Journal of Forecasting, 2004, vol. 20, pp. 5-13.
5. Semenychev V.K. Nelinejnye po parametram modeli trendov [ Nonlinear parameters of the trend model] Available at: http://  serey.svetunkov.ru/study/forecasting/files/25.pdf
6. Ramos R.A. Logistic function as a forecasting model: it's application to business and economics. International Journal of Engineering and Applied Sciences, 2013, vol. 2, pp. 29-36.
7. Modis T. Strengths and weaknesses of S-curves. Technological Forecasting and Social Shange, 2007, vol. 74, no.6, pp. 866–872.
8. Semenychev E.V. Metody identifikacii logisticheskoj dinamiki i zhiznennogo produk-ta model'ju Verhusta [Identification methods for logical dynamic and product lifecycle by the Verhulst model.] [Economics and Mathematical Methods]. RAN. M. 2012, no.1, pp. 108-115.
9. Jukic D., Kralik G., Scitovski R. Least-squares fitting Gompers curve. Journal of Computational and Applied Mathematics, 2004, vol. 169, no. 2, pp. 359-375.
10. Korn G., Korn T. (1974). Spravochnik po matematike dlja nauchnyh rabotnikov i inzhene-rov. [Handbook of Mathematics for Scientists and Engineers]. M., Nauka, 832 p.
11. Cіl's'ke gospodarstvo Ukraуіni, statistichnij zb. za 2004, 2016 rr.[Agriculture of Ukraine, statistical collection. for 2004, 2016]. K., Derzhkomstat[State Statistics Service of Ukraine]. Available at: http:// www.ukrstat.gov.ua
12. Sel'skoe hozjajstvo respubliki Belarus', statisticheskij sb. za 2004, 2016 gg.[ Agriculture of the Republic of Belarus, statistical collection. for 2004, 2016]. Minsk, Belstat. Available at: http:// www.belstat.gov.by