SEASONALITY AND THE ORDER OF INTEGRATION FOR CONSUMPTION<sup>*</sup>

Osborn, Denise R.; Chui, Alice P.L.; Smith, Jeremy; Birchenhall, Chris

doi:10.1111/j.1468-0084.1988.mp50004002.x

Cited by 251 publications

(74 citation statements)

References 19 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The tests were performed using the log transformation of the data and their results can be found on the website cited in the introduction. We applied the Osborn et al (1988) tests, hereafter OCSB, and Hylleberg et al (1990) test as extended in Beaulieu and Miron (1993), hereafter HEGY. Using the terminology employed in the first paper, I(r,s) -where r and s can take values one or zero-means that the data needs r regular differences and s annual differences in order to be stationary.…”

Section: Trend and Seasonal Factorsmentioning

confidence: 99%

Forecasting aggregates and disaggregates with common features

Espasa

Mayo-Burgos

2013

International Journal of Forecasting

View full text Add to dashboard Cite

This paper focuses on providing consistent forecasts for an aggregate economic indicator, such as a consumer price index, and all its components. The procedure developed is a disaggregated approach based on single components, which take into account the stable features as common trend and common serial correlation that some components share. Our procedure starts by classifying a large number of components based on restrictions from common features. The result of this classification is a disaggregation map, which may also be useful in applying dynamic factors, defining intermediate aggregates or formulating models with unobserved components. We apply the procedure to forecast inflation in the Euro Area, the UK and the US. Our forecasts of the aggregate and other indirect forecasts. This paper focuses on providing consistent forecasts for an aggregate economic indicator, such as a consumer price index, and all its components. The procedure developed is a disaggregated approach based on single-equation models for the take into account the stable features as common trend and common serial correlation that some components share. Our procedure starts by classifying a large number of components based on restrictions from common features. The result of s a disaggregation map, which may also be useful in applying dynamic factors, defining intermediate aggregates or formulating models with unobserved components. We apply the procedure to forecast inflation in the Euro Area, the UK and the US. Our forecasts are significantly more accurate than a direct forecast of the aggregate and other indirect forecasts. Forecasting aggregates and disaggregates with common featuresThis paper focuses on providing consistent forecasts for an aggregate economic indicator, such as a consumer price index, and all its components. The procedure equation models for the take into account the stable features as common trend and common serial correlation that some components share. Our procedure starts by classifying a large number of components based on restrictions from common features. The result of s a disaggregation map, which may also be useful in applying dynamic factors, defining intermediate aggregates or formulating models with unobserved components. We apply the procedure to forecast inflation in the Euro Area, are significantly more accurate than a direct forecast

show abstract

Section: Trend and Seasonal Factorsmentioning

confidence: 99%

Forecasting aggregates and disaggregates with common features

Espasa

Mayo-Burgos

2013

International Journal of Forecasting

View full text Add to dashboard Cite

show abstract

“…17 The AR terms represent dependence on past time-series values and the MA terms represent dependence on past errors (e.g., noise); detailed explanations of this statistical technique are found elsewhere. 18 The order of seasonal and nonseasonal differencing needed to achieve stationarity of the series was determined using the OCSB test 19 and KPSS test, 20 respectively, and validated by visual inspection of the autocorrelation function (ACF) and partial autocorrelation (PACF) plots. A SARIMA model was then obtained by finding the parameters that yielded the smallest Akaike Information Criterion 21 (AIC) among all possible models.…”

Section: Discussionmentioning

confidence: 99%

Presentations to Alberta Emergency Departments for Asthma: A Time Series Analysis

2015

View full text Add to dashboard Cite

Objectives: Asthma is a common chronic respiratory condition, and exacerbations may cause individuals to seek care in emergency departments (EDs). This study examines the monthly patterns of asthma presentations to EDs in Alberta, Canada.Methods: All presentations to the ED for asthma from April 1999 to March 2011 were extracted from provincial administrative health databases. Data included age, sex, and health zone of residence. Crude rates per 100,000 population were calculated. Seasonal autoregressive integrated moving average (SARIMA) time-series models were developed.Results: There were a total of 362,430 ED presentations for asthma, and the monthly rate of presentation declined from 115.5 to 41.6 per 100,000 during the study period. Males made 50.1% of ED presentations, and adults made 52.8%. The absolute number of ED presentations for asthma declined in each of the five administrative health zones in the province, with smaller percentage decreases seen in the most urbanized zones (32.1%) than the other zones (46.9%). One SARIMA model closely predicted overall presentation rates as well as the rates of ED presentations for age and zone subgroups. These models showed strong seasonal components, with the strongest estimates occurring for the pediatric subgroup and the southernmost provincial zone. Conclusions:Rates of ED presentations for asthma have been declining in this province during the past decade. The reasons for this decline warrant further exploration. The SARIMA models quantified the temporal patterns and may be helpful for planning research and health care service needs. 3 Conversely, the prevalence of asthma in adults has remained stable, with a declining sex-adjusted emergency department (ED) presentation rate first detected in the mid-2000s.

show abstract

“…Additionally, both the trend and seasonal differencing parameters are taken care of by performing unit root tests beforehand [49], i.e. the Augmented Dickey-Fuller test [15] and the Osborn-Chui-Smith-Birchenhall test [51]. The following steps form the procedure of the hybrid model, which is adjusted for a holdout sample test process.…”

Section: The Profarima Proceduresmentioning

confidence: 99%

“…Firstly, the two differencing terms need to be considered, as the correct identification of the other terms can only be achieved for a stationary time series. The addition of both trend and seasonal differencing is typically decided on by performing unit root tests, such as the Augmented Dickey-Fuller test [15] and the Osborn-Chui-Smith-Birchenhall test [51] respectively. Further model identification can then be done by utilizing expert knowledge or by comparing models using several evaluation criteria.…”

Section: Arima Modelingmentioning

confidence: 99%

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

Calster

Baesens

Lemahieu

2017

Applied Soft Computing

View full text Add to dashboard Cite

In forecasting, evolutionary algorithms are often linked to existing forecasting methods to optimize their input parameters. Traditionally, the fitness function of these search heuristics is based on an accuracy measure. In this paper, however, we combine forecasting accuracy with business expertise by defining a flexible and easily interpretable profit function for sales forecasting, which is based on the profit margin of a given product, the volume of its sales and the accuracy of the forecast. ProfARIMA is a new procedure that selects the lags of a Seasonal ARIMA model according to the profit of a model's forecasts by taking advantage of search heuristics. This procedure is tested on both publicly available datasets and a real-life application with datasets of The Coca-Cola Company in order to assess its performance, both in profit and accuracy. Three different evolutionary algorithms were implemented during this testing process, i.e. Genetic Algorithms, Particle Swarm Optimization and Simulated Annealing. The results indicate that ProfARIMA always performs at least equally to the Box-Jenkins methodology and often outperforms this traditional procedure. For The Coca-Cola Company, our new algorithm in combination with Genetic Algorithms even leads to a significantly larger profit for out-of-sample forecasts.

show abstract

SEASONALITY AND THE ORDER OF INTEGRATION FOR CONSUMPTION^*

Cited by 251 publications

References 19 publications

Forecasting aggregates and disaggregates with common features

Forecasting aggregates and disaggregates with common features

Presentations to Alberta Emergency Departments for Asthma: A Time Series Analysis

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

Contact Info

Product

Resources

About

SEASONALITY AND THE ORDER OF INTEGRATION FOR CONSUMPTION*

Cited by 251 publications

References 19 publications

Forecasting aggregates and disaggregates with common features

Forecasting aggregates and disaggregates with common features

Presentations to Alberta Emergency Departments for Asthma: A Time Series Analysis

ProfARIMA: A profit-driven order identification algorithm for ARIMA models in sales forecasting

Contact Info

Product

Resources

About

SEASONALITY AND THE ORDER OF INTEGRATION FOR CONSUMPTION^*