Forecasting medical cost inflation rates: A model comparison approach

Due to healthcare costs rising faster than overall cost of living, decision makers (i.e., households, businesses, and governments) must cut back on healthcare utilization or spending elsewhere to be fiscally responsible. Accurate forecasts of future medical costs are critical for efficient planning, budgeting and operating decisions at all levels. This research compares the accuracy of the linear autoregressive moving average (ARMA) model and the nonlinear neural network model in producing forecasts of medical cost inflation rates. The analysis focuses on twelve monthly measures of medical costs including the overall medical care price index and eleven (disaggregated) subsectors of medical costs. In addition to standard symmetric measures of forecast accuracy, we utilize two asymmetric error measures designed to capture and penalize preferences for under- and overprediction in model selection. The findings indicate that the neural network model outperforms the univariate ARMA in both 1-step and 12-step ahead forecasts. A number of important practical implications are discussed, such as the use of accurate forecasts in contract negotiations, budgeting and planning. Highlights? It compares ARMA model with neural network model in medical cost inflation rates forecasting. ? We find that the neural network model outperforms the univariate ARMA in both 1-step and 12-step ahead forecasts. ? A number of important practical implications are discussed.

[1]  Daniel E. Sichel.  Business cycle asymmetry: a deeper look , 1993 .

[2]  W. Enders.  Applied Econometric Time Series , 1994 .

[3]  Luis G. Vargas,et al.  Choosing Data-Mining Methods for Multiple Classification: Representational and Performance Measurement Implications for Decision Support , 1999, J. Manag. Inf. Syst..

[4]  Chih-Ping Wei,et al.  Predicting the length of hospital stay of burn patients: Comparisons of prediction accuracy among different clinical stages , 2010, Decis. Support Syst..

[5]  Emi Nakamura,et al.  Inflation forecasting using a neural network , 2005 .

[6]  Qing Cao,et al.  Neural network earnings per share forecasting models: A comparison of backward propagation and the genetic algorithm , 2009, Decis. Support Syst..

[7]  M. A. Thompson,et al.  A State‐Level Analysis of Business Cycle Asymmetry , 2012 .

[8]  Haralambos Sarimveis,et al.  A combined model predictive control and time series forecasting framework for production-inventory systems , 2008 .

[9]  Philip Rothman,et al.  Time Irreversibility and Business Cycle Asymmetry , 1996 .

[10]  P L Grimaldi.  New healthcare price indexes aid financial analysis. , 1994, Healthcare financial management : journal of the Healthcare Financial Management Association.

[11]  Nirup M. Menon,et al.  Cost control and production performance enhancement by IT investment and regulation changes: evidence from the healthcare industry , 2000, Decis. Support Syst..

[12]  Frank Slesnick,et al.  Forecasting Medical Costs in Tort Cases: The Role of the Economist , 1990 .

[13]  Wooju Kim,et al.  Combination of multiple classifiers for the customer's purchase behavior prediction , 2003, Decis. Support Syst..

[14]  W. J. Conover,et al.  Practical Nonparametric Statistics , 1972 .

[15]  Xiaoning Zhang,et al.  Data Mining for Network Intrusion Detection: A Comparison of Alternative Methods , 2001, Decis. Sci..

[16]  Bradley T. Ewing,et al.  Forecasting Medical Net Discount Rates , 2003 .

[17]  Wei Zhang,et al.  Neural Network Earnings per Share Forecasting Models: A Comparative Analysis of Alternative Methods , 2004, Decis. Sci..

[18]  A. Harvey.  Time series models , 1983 .

[19]  Siddhartha Bhattacharyya,et al.  Inductive, Evolutionary, and Neural Computing Techniques for Discrimination: A Comparative Study* , 1998 .

[20]  Vijay S. Desai,et al.  The Efficacy of Neural Networks in Predicting Returns on Stock and Bond Indices , 1998 .

[21]  Steven Walczak,et al.  Reducing surgical patient costs through use of an artificial neural network to predict transfusion requirements , 2000, Decis. Support Syst..

[22]  Gary Klein,et al.  Marketing Category Forecasting: An Alternative of BVAR-Artificial Neural Networks , 2000, Decis. Sci..

[23]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[24]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[25]  Min Qi,et al.  Nonlinear Predictability of Stock Returns Using Financial and Economic Variables , 1999 .

[26]  Saeed Moshiri,et al.  Neural Network versus Econometric Models in Forecasting Inflation , 1999 .

[27]  Joseph P. Newhouse,et al.  Price Indexes for Medical Care Goods and Services: An Overview of Measurement Issues , 1998 .

[28]  Roger J. Calantone,et al.  Artificial Neural Network Decision Support Systems for New Product Development Project Selection , 2000 .

[29]  Norman R. Swanson,et al.  A Model Selection Approach to Real-Time Macroeconomic Forecasting Using Linear Models and Artificial Neural Networks , 1997, Review of Economics and Statistics.

[30]  Tai-Hsi Wu,et al.  Using data mining techniques to predict hospitalization of hemodialysis patients , 2011, Decis. Support Syst..

[31]  M. Qi.  Predicting US recessions with leading indicators via neural network models , 2001 .

[32]  T. Brailsford,et al.  An evaluation of volatility forecasting techniques , 1996 .

[33]  R. E. Abdel-Aal,et al.  Univariate modeling and forecasting of monthly energy demand time series using abductive and neural networks , 2008, Comput. Ind. Eng..

[34]  Dahlia K Remler,et al.  How much more cost sharing will health savings accounts bring? , 2006, Health affairs.