Asymptotic Mean Square Prediction Error for an Autoregressive Model with Estimated Coefficients

1976 ◽  
Vol 25 (2) ◽  
pp. 123 ◽  
Author(s):  
Taku Yamamoto
Keyword(s):  
Autoregressive Model ◽  
Prediction Error ◽  
Mean Square ◽  
Mean Square Prediction Error

scholarly journals SCALING THRESHOLD CHARACTERS

Genetics ◽  
1981 ◽  
Vol 99 (2) ◽  
pp. 357-364 ◽  
Author(s):  
Daniel Gianola ◽  
H W Norton
Keyword(s):  
Prediction Error ◽  
Joint Distribution ◽  
Mean Square ◽  
Scaling Method ◽  
Simple Method ◽  
Normal Variable ◽  
Mean Square Prediction Error ◽  
Genetic Value ◽  
Ordered Categorical ◽  
Threshold Characters

ABSTRACT A simple method of scaling ordered categorical responses having a joint distribution with an underlying normal variable is presented. Scores are developed that maximize heritability of the observed variate and that in the class of scores based on polychotomies: (1) maximize the correlation between score and the underlying genetic value to be predicted, and (2) minimize mean-square prediction error. Several examples suggest little is lost, in terms of heritability, by using equally spaced scores. The proposed scaling method discriminates among candidates for selection that would be tied if equally spaced scores are used and sometimes yields different rankings of candidates.

scholarly journals Body weight prediction using body size measurements in Fleckvieh, Holstein, and Brown Swiss dairy cows in lactation and dry periods

2018 ◽  
Vol 61 (4) ◽  
pp. 413-424
Author(s):  
Leonhard Gruber ◽  
Maria Ledinek ◽  
Franz Steininger ◽  
Birgit Fuerst-Waltl ◽  
Karl Zottl ◽  
...  
Keyword(s):  
Body Weight ◽  
Body Size ◽  
Root Mean Square ◽  
Prediction Error ◽  
Prediction Accuracy ◽  
Body Measurements ◽  
Mean Square ◽  
Validation Data ◽  
Brown Swiss ◽  
Mean Square Prediction Error

Abstract. The objective of this study was to predict cows' body weight from body size measurements and other animal data in the lactation and dry periods. During the whole year 2014, 6306 cows (on 167 commercial Austrian dairy farms) were weighed at each routine performance recording and body size measurements like heart girth (HG), belly girth (BG), and body condition score (BCS) were recorded. Data on linear traits like hip width (HW), stature, and body depth were collected three times a year. Cows belonged to the genotypes Fleckvieh (and Red Holstein crosses), Holstein, and Brown Swiss. Body measurements were tested as single predictors and in multiple regressions according to their prediction accuracy and their correlations with body weight. For validation, data sets were split randomly into independent subsets for estimation and validation. Within the prediction models with a single body measurement, heart girth influenced relationship with body weight most, with a lowest root mean square error (RMSE) of 39.0 kg, followed by belly girth (39.3 kg) and hip width (49.9 kg). All other body measurements and BCS resulted in a RMSE of higher than 50.0 kg. The model with heart and belly girth (ModelHG BG) reduced RMSE to 32.5 kg, and adding HW reduced it further to 30.4 kg (ModelHG BG HW). As RMSE and the coefficient of determination improved, genotype-specific regression coefficients for body measurements were introduced in addition to the pooled ones. The most accurate equations, ModelHG BG and ModelHG BG HW, were validated separately for the lactation and dry periods. Root mean square prediction error (RMSPE) ranged between 36.5 and 37.0 kg (ModelHG BG HW, ModelHG BG, lactation) and 39.9 and 41.3 kg (ModelHG BG HW, ModelHG BG, dry period). Accuracy of the predictions was evaluated by decomposing the mean square prediction error (MSPE) into error due to central tendency, error due to regression, and error due to disturbance. On average, 99.6 % of the variance between estimated and observed values was caused by disturbance, meaning that predictions were valid and without systematic estimation error. On the one hand, this indicates that the chosen traits sufficiently depicted factors influencing body weight. On the other hand, the data set was very heterogeneous and large. To ensure high prediction accuracy, it was necessary to include body girth traits for body weight estimation.

scholarly journals Fiscal Marksmanship in Pakistan

2010 ◽  
Vol 15 (2) ◽  
pp. 113-133 ◽  
Author(s):  
Muhammad Zakaria ◽  
Shujat Ali
Keyword(s):  
Prediction Error ◽  
Rational Expectations ◽  
Central Government ◽  
Mean Square ◽  
Government Budget ◽  
Exogenous Variables ◽  
Random Components ◽  
The Mean ◽  
Source Of Error ◽  
Over Time

Using Theil’s inequality coefficient based on the mean square prediction error, this paper evaluates the forecasting efficiency of the central government budget and revised budget estimates in Pakistan for the period 1987/88 to 2007/08 and decomposes the errors into biasedness, unequal variation and random components to analyze the source of error. The results reveal that budgetary forecasting is inefficient in Pakistan and the error is due mainly to exogenous variables (random factors). We also find that neither the budget nor revised budget estimates of revenue and expenditure satisfy the criteria of rational expectations of forecasting. Further, there is very little evidence of improvement in the efficiency of budgetary forecasts over time.

Prediction for Sound Radiated Power from Submerged Double Cylindrical Shells Based on Measuring Vibration of Inner Shell

2013 ◽  
Vol 779-780 ◽  
pp. 602-606 ◽  
Author(s):  
Chao Zhang ◽  
De Jiang Shang ◽  
Qi Li
Keyword(s):  
Prediction Error ◽  
Cylindrical Shells ◽  
Prediction Method ◽  
Superposition Method ◽  
Power Curve ◽  
Mean Square ◽  
Average Prediction Error ◽  
Radiated Power ◽  
Modal Superposition Method ◽  
Good Agreement

A prediction method for the sound radiated power from submerged double cylindrical shells based on measuring vibration of inner shell is presented. The prediction model of submerged double cylindrical shells is established by using modal superposition method. Applied the ratio of the measuring value and theoretical value of the acceleration in one point or mean square velocity of inner shell, and combined with the theoretical value of the sound radiated power, the predicted value of the sound radiated power is derived. The corresponding experiment is carried out in lake. And then the measuring power curve is compared with the predicted power curve based on this method. The result shows that they have good agreement and the average prediction error is less than 2dB.

Sign in / Sign up

Export Citation Format

Share Document