Predicting dry matter intake of steers and heifers in the feedlot by using categorical and continuous variables

Monday, July 21, 2014
Exhibit Hall AB (Kansas City Convention Center)
Ozgur Koskan , Suleyman Demirel University, Isparta, Turkey
Hayati Koknaroglu , Suleyman Demirel University, Isparta, Turkey
Daniel D. Loy , Iowa State University, Ames, IA
M. Peter Hoffman , Iowa State University, Ames, IA
Abstract Text: Close-out information, submitted by Iowa cattle producers to the Iowa State University Feedlot Performance and Cost Monitoring Program, was used to develop dry matter intake prediction model for steers and heifers by considering categorical and continuous variables. Close-out information consisting of 1651 pens of steers and 601 pens of heifers included information on start and end dates, cattle per pen, sex, housing type, days on feed, initial and sale weight, feed conversion (FC), proportion of concentrate, average daily gain (ADG), percent death loss, feed cost and total cost per 45.35 kg gain, breakeven sale price, non-feed variable cost, non-feed fixed cost and corn price. Dry matter intake (DMI) was not provided but was calculated as DMI = ADG x FC.  In predicting DMI, categorical regression analysis (optimal scaling) was applied for steers and heifers separately.  Independent variables used were starting date on feed (season) (1= Winter: December through February; 2=Spring: March through May; 3=Summer: June through August and 4=Fall: September through November), number of cattle per pen (head), housing type (housing) (1= confinement, 2= partially open lot, 3= open lot), days on feed (dof), initial weight (iw), proportion of concentrate (concentrate). When the model was applied separately for steers and heifers, DMI prediction for steers was found as DMI = 0.540*iw + 0.017*season +0.143*housing -0.062*head – 0.096*concentrate – 0.186*dof (R2=0.433), whereas DMI prediction for heifers was found as DMI = 0.706*iw + 0.086*season + 0.085*housing + 0.186*dof - 0.099*head - 0.084*concentrate (R2=0.468).  With this model, categorical variables such as housing type and season are included in the regression model and this may help professionals predict the DMI of their steers and heifers in the feedlot.

Keywords: dry matter intake prediction, categorical regression, feedlot