| No. of records per page: 10 | 20 | 30 | 50 | 100 | Show all |
Record ID: 19 [ Page 8 of 8, No. 1 ]
Assessing Strength of Seasonality Through Sample Entropy: A Simulation Study
Authors: John Carlo P. Daquis; Maria Lizeth M. Laus; Nikki E. Supnet
Abstract:
This paper investigates the behaviour of sample entropy when used as a measure of seasonality of time series. Sample entropy decreases when the series becomes less complex or when regular patterns emerge. The more regular patterns in seasonal data compared to those of non-seasonal data is used in providing evidence that sample entropy is inversely related to the likelihood that seasonality exists in the data. A simulation study was conducted to assess the behaviour of the sample entropy in relation to seasonality. Sample entropy yields large values for time series without seasonality, and as the extent of seasonality becomes dominant, the value decreases. The sample entropy becomes a more reliable measure of seasonality as the length of the time series increases.
Keywords: entropy; sample entropy; seasonality; time series
Download this article:
Year: 2012 Vol.: 61 No.: 1
Record ID: 27 [ Page 8 of 8, No. 2 ]
Statistical Models for Extreme Values
Authors: Peter Julian A. Cayton
Abstract:
Keywords:
Download this article:
Year: 2012 Vol.: 61 No.: 1
Record ID: 18 [ Page 8 of 8, No. 3 ]
Sample Sizes to Compare Two Poisson Rates
Authors: Edsel A. Pena
Abstract:
In this note, procedures for determining the sample sizes needed to compare the rates of two Poisson populations to achieve a pre-specified power at a given ratio of the rates are proposed. The first method relies on a conditional uniformly most powerful test (CUMPT) which leads to sample sizes that will guarantee the desired power, but at the cost of using more units than necessary. The second method relies on a normal approximation and may not always guarantee that the desired power will be achieved, but generally yields a power close to the pre-specified value and prescribes smaller sample sizes than the CUMPT-based method. Properties of the procedures are examined using simulation studies. The particular applicability and motivating situations leading to these procedures are in colon cancer research. Illustrations of the applicability of the procedures in studies dealing with tumor counts in mice are presented.
Keywords: conditional uniformly most powerful test; normal approximation test; power function; test function.
Download this article:
Year: 2012 Vol.: 61 No.: 1
Record ID: 17 [ Page 8 of 8, No. 4 ]
Bootstrap Methods
Authors: Erniel B. Barrios
Abstract:
Keywords:
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 16 [ Page 8 of 8, No. 5 ]
A Dose of Business Intelligence: Data Mining
Authors: Joseph Ryan G. Lansangan,
Abstract:
Keywords:
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 15 [ Page 8 of 8, No. 6 ]
Copula-Based Vector Autoregressive Models for Bivariate Cointegrated Data
Authors: Hideaki Taima; Ana Maria L. Tabunda,
Abstract:
The copula method is well applied in finance and actuarial science but its application in economic studies is limited and its use in the cointegration framework virtually nil. This paper explores the use of copula method to analyze the remaining dependence after a cointegration relationship is modeled. Specifically, simulated data is used to characterize the behavior of the dependence parameter estimates of several copulas fitted to the distribution of the residuals after cointegrated Vector Autoregressive (VAR) and Vector Error-Correction Mechanism (VECM) models are fitted, as well as evaluate the forecasting ability of the copula-based models. The Clayton, Frank, Gaussian, Gumbel and Plackett copulas are used and are compared on the basis of bias, root mean square error (RMSE) and maximum likelihood. The density forecasting ability of the copula-based VAR and VECM is then compared with that of standard models via conditional Kullback-Leibler Information Criterion (KLIC) divergence measure using simulated and empirical data. The simulation results indicate that the copula-based models generally have better density forecasting ability than standard VAR and VECM models, a finding that is supported in the application of a copula-based VAR to empirical data.
Keywords: Copula; Cointegration; VAR; VECM
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 14 [ Page 8 of 8, No. 7 ]
Nearest-Integer Response from Normally-Distributed Opinion (NIRNDO) Model for Likert Scale
Authors: Jonny B. Pornel, Vicente T. Balinas, Giabelle A. Saldaa
Abstract:
This paper proposes that respondents’ opinions on Likert Scale items are normally distributed around their latent ability although their observable responses will be integers in the scale nearest to those opinions. This paper tested the appropriateness of the model on actual data gathered by a Likert scale developed to measure attitude of teachers towards research undertaking. The paper then proceeded to test the soundness of common research practice of using mean and standard deviation to estimate the respondents’ latent ability. The results show that the NIRNDO model could be used appropriately to model responses on Likert scale. Also, the results show that using the mean response to a Likert scale, the resulting 95% confidence interval (mean + 1.96 SEM) would be effective at least 90% of the time. This effectiveness is guaranteed for latent ability in the optimum range [u+0.8, v-0.8] where u and v is the lowest and highest points of the scale.
Keywords: Likert Scale; NIRNDO Model; latent ability
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 13 [ Page 8 of 8, No. 8 ]
Substance Use Among Serious Adolescent Offenders Following Different Patterns of Antisocial Activity
Authors: Michelle Besana; Edward P. Mulvey
Abstract:
The present study examines individual differences in the levels of substance use in a sample (n=1,067) of male serious adolescent offenders following distinct trajectories of criminal offending over a three (3) year period. The levels of substance use are compared for the different offender groups controlling the effects of age, ethnicity, and diagnosis of previous drug and alcohol abuse/dependence. The association between antisocial activity and the level of substance use was also examined and compared for the different groups after controlling the effect of institutional placement. The growth or decline in substance use was investigated and compared for the different groups above and beyond the effects of antisocial activity and institutional confinement. After fitting a series of hierarchical generalized linear models for repeated measurements data, results revealed that significant differences in the level of substance use exist among the different offender groups in the sample. Antisocial activity is associated with the level of substance use over time after controlling the effect of institutional placement in all offender groups. Above and beyond the effect of antisocial activity and institutional placement, substance use is increasing over the data collection period in all groups, but the rate of growth is highest in the lowest offending group.
Keywords: hierarchical generalized linear models; growth curve models; substance use; antisocial activity; delinquency; serious adolescent offenders
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 12 [ Page 8 of 8, No. 9 ]
Food Inflation, Underemployment and Hunger Incidence: A Vector Autoregressive (VAR) Analysis
Authors: Dennis S. Mapa; Fatima C. Han; Kristine Claire O. Estrada
Abstract:
The high level of hunger incidence in the country is perhaps one of the most pressing issues that need to be addressed by our policy makers. Official government statistics and data from self-rated hunger surveys show an increasing trend in hunger incidence among Filipino households. Data from National Statistical Coordination Board (NSCB) show that the percentage of Filipinos experiencing hunger almost remained the same, decreasing only slightly from 11.1 percent in 2003 to 10.8 percent in 2009. The Social Weather Stations (SWS) quarterly surveys on hunger incidence also show an increasing trend in the percentage of families that experienced hunger, reaching an alarming level of 24 percent in December 2009, representing about 4.4 million households. One probable cause of the increasing trend in hunger is the rising food prices akin to what the country experienced in 2008. This paper aims to determine the impact of food inflation and underemployment on hunger incidence in the Philippines, using the hunger incidence data from the SWS. A vector autoregressive (VAR) model is used to determine the effect of a shock or increase to food inflation and underemployment on total involuntary hunger. Results show that an increase in food prices at the current quarter will increase hunger incidence for five quarters. Shocks to underemployment will also increase hunger incidence but the effects last for only two quarters. The results of this study provide relevant information that will be useful in crafting policies related to the Hunger Mitigation Program of the government.
Keywords: hunger; food inflation; underemployment; vector autoregressive
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 11 [ Page 8 of 8, No. 10 ]
Length of a Time Series for Seasonal Adjustment: Some Empirical Experiments
Authors: Lisa Grace S. Bersales
Abstract:
Use of 5 to 15 years of quarterly or monthly data is suggested when doing seasonal adjustment using X11 and its variants. This is meant to address changes in the structure of the time series. Philippine time series are good candidates for this practice since they usually exhibit frequent changes in patterns. Empirical validation of the suggested length of series is done for seasonal ARMA processes. Different quarterly series were simulated for the following situations and seasonal adjustment was done for various lengths of time series: (1) processes without any structural change; (2) processes with abrupt permanent change in structure; (3) processes with gradual permanent change in structure. For all types of processes, both weak and strong seasonality were considered. Regression models were used in testing the effect of length of series used in seasonal adjustment to the error in estimating the seasonal factor. Results show that the length of series used does not have significant effect on the seasonal adjustment for processes without structural change and with abrupt permanent structural change. On the other hand, for processes with gradual permanent change, use of longer lengths of series for seasonal adjustment is better.
Keywords: seasonal adjustment, seasonal factor, X11-ARIMA, seasonal ARMA processes
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 10 [ Page 8 of 8, No. 11 ]
Investigating the Efficiency of Stratified Ranked Set Sampling Using Nonparametric Bootstrap Estimation
Authors: Kevin Carl P. Santos; Jenniebie Salagubang
Abstract:
This paper aims to compare stratified random sampling and stratified ranked set sampling. A simulation study is conducted to evaluate the performance of the parameter estimates on both sampling techniques. Population sizes, sampling rates, stratum sizes, and correlation of the target variable and concomitant variable were varied, nonparametric bootstrap was then used in estimating the mean and its standard error. The coefficient of variation (CV) and the bias of the bootstrap estimates were compared. Stratified ranked set sampling generally outperforms stratified random sampling in terms of bias most especially for small populations. The two sampling designs were used in estimating the average mango production per barangay in the country.
Keywords: ranked set sampling; nonparametric bootstrap estimation; stratification; simple random sampling
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 9 [ Page 8 of 8, No. 12 ]
Nonparametric Model-Based Predictive Estimation in Survey Sampling
Authors: April Anne H. Kwong
Abstract:
A nonparametric model-based estimator of the population total is proposed. The sample data along with the auxiliary information are used in fitting a generalized additive model that is then used in reconstructing the unknown population. The estimates of the population parameters are computed from the predicted population values (for the unsampled part of the population) and the sample values. A simulation study designed to account for different association patterns between the target variable and the auxiliary variable, population size, and sample size was conducted to evaluate the proposed procedure. The method is robust to data-generating model form, population size, and sampling rate, and is generally superior to design-unbiased estimators.
Keywords: model-based estimation; predictive estimation; nonparametric regression; additive model
Download this article:
Year: 2011 Vol.: 60 No.: 1
Record ID: 8 [ Page 8 of 8, No. 13 ]
Teaching of Statistical Consulting in the Philippines
Authors: Erniel B. Barrios
Abstract:
Teaching in a developing country is generally challenging due to the inadequate infrastructures in the development of teaching materials and the facilities in the delivery of such. The teacher has to be creative enough in developing cost-effective teaching materials, efficiently allocating the limited resources. Statistical consulting is generally taught using audio-visual infrastructure support. In the Philippines, it has to be taught through case studies, coaching and guided practice to complement the absence or inadequate audio-visual facilities. The methods are fairly adequate in imparting to the students the techniques and necessary skills in the practice of statistical consulting.
Keywords: statistical consulting; statistics education
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 7 [ Page 8 of 8, No. 14 ]
Teaching Experiments for a Course in Introductory Statistics
Authors: Josefina V. Almeda
Abstract:
Appreciation of college students on the statistical science relies to a large extent on how the introductory course is managed. Two groups of students (undergraduate statistics majors and non-statistics majors) were exposed to teaching an introductory course. Within each group, half is exposed to fun games intended as enrichment activities, the other half served as the control. Grades after one semester were analyzed and treatment effect is computed through Heckmans’ Selection Model. While the treatment (games) is beneficial for the non-statistics majors, it is disadvantageous for the statistics majors. For students with inherent interest in statistics, the introductory course will only require a clear presentation of concepts that will help them appreciate the discipline. However, the non-statistics majors or those with negative perception on statistics, fun activities like games can help conceal their dislike for statistical science and help improve the eventual outcomes in the course.
Keywords: fun games; Heckmans’ Selection Model; treatment effect
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 6 [ Page 8 of 8, No. 15 ]
The Random Component of the Levy Fractional Brownian Motion: A Rotation-Scale-Reflection-Invariant Random Field
Authors: Jeffry J. Tejada
Abstract:
This paper shows that the Levy fractional Brownian motion (LFBM) on the plane factors as a product of two components, one being a deterministic trend term and the other being a rotation-scale-reflection-invariant (RSRI) random field. An important consequence of this characterization is that one can study the LFBM by establishing the properties of the associated RSRI random field.
Keywords: Levy fractional Brownian motion; rotation-scale-reflection-invariant random field
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 5 [ Page 8 of 8, No. 16 ]
Backfitting Estimation of a Response Surface Model
Authors: Jhoanne Marsh C. Gatpatan
Abstract:
The backfitting algorithm is used in estimating a response surface model with covariates from a data generated through a central composite design. Backfitting takes advantage of the orthogonality generated by the central composite design on the design matrix. The simulation study shows that backfitting yield estimates and predictive ability of the model comparable to that from ordinary least squares when the response surface bias is minimal. Ordinary least squares estimates generally fails when the response surface bias is large, while backfitting exhibits robustness and still produces reasonable estimates and predictive ability of the fitted model. Orthogonality facilitates the viability of assumptions in an additive model where backfitting is an optimal estimation algorithm.
Keywords: backfitting; response surface model; second order model; central composite design
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 4 [ Page 8 of 8, No. 17 ]
Knowledge, Attitudes, and Practices of Filipino Households in Relation to Avian Influenza: A Pilot Study
Authors: Josefina V. Almeda; Jonathan G. Yabes
Abstract:
Avian influenza, commonly known as bird flu, once threatened the lives of birds as well as of human beings. Caused by a virus, it is considered endemic in many parts of Indonesia and Vietnam and in some parts of Cambodia, China, and Thailand. Outbreak of many similar diseases can easily reach epidemic level because households have minimal knowledge of precautionary measures. This study conducted a survey of Filipino households’ knowledge, attitudes, and practices related to avian influenza. Results of this assessment can help in the development of intervention strategies for the mitigation of the hazards such outbreaks may cause to humans. The results of the knowledge, attitudes, and practices study is beneficial to the country since it showed that there should be an improvement on the publics’ knowledge of transmission and preventive measure and that health professionals and other concerned agencies should provide effective information to prevent the disease.
Keywords: knowledge; attitudes; practices; avian influenza
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 3 [ Page 8 of 8, No. 18 ]
Loglinear and Classification Tree Models of the Decision Paradigm of the Tuberculosis Diagnostic Committee
Authors: Caryl Rose E. Alfonte
Abstract:
The TB Diagnostic Committees (TBDC) evaluate cases of pulmonary tuberculosis (PTB) symptomatics who are smear-negative, but whose chest x-rays show lesions suggestive of tuberculosis that may warrant anti-TB treatment. In a review of the 600 TBDC referral forms of new patients who consulted at Manila district health centers from 2006 to 2008, the demographic and clinical characteristics associated with a positive chest x-ray and eventually leading to a diagnosis of new active PTB are identified using loglinear models and classification trees.
Keywords: Classification tree, Loglinear model, Positive chest x-ray, Pulmonary tuberculosis, Sputum smear-negative, TB Diagnostic Committee
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 2 [ Page 8 of 8, No. 19 ]
Spatio-Temporal Modeling of Growth in Rice Production in the Philippines
Authors: Angela D. Nalica
Abstract:
When the strong El Nino episode in recent history happened in 1998, gross value added of the rice sector in the Philippines declined by as much as 24% while other crops were able to keep the decline to within single digit level. The convergence hypothesis was verified among the Philippine provinces with reference to rice production. Convergence could mean harmonized efforts among various stakeholders to increase production and hopefully aim for food sufficiency. Divergence on the other hand could imply the need for structural assessment of the sector including the goals of various stakeholders, so that an optimal strategy that can stimulate development will be identified. A spatial term is incorporated into the model, providing empirical evidence for the need to localize rice production policy programs across the country. The spatial term also accounts for the natural endowments of the producing provinces that complement those policies in realizing progress in the sector. Rice production among the Philippine provinces diverged in the period 1990-2002. The El Nino episode of 1998 pulled down rice yield by as much as 10% aggravating further the divergence among provinces.
Keywords: spatio-temporal model; backfitting; autoregression; convergence hypothesis; agricultural growth
Download this article:
Year: 2010 Vol.: 59 No.: 1
Record ID: 1 [ Page 8 of 8, No. 20 ]
What Drives the Dynamic Conditional Correlation of Foreign Exchange and Equity Returns?
Authors: Gregorio A. Vargas
Abstract:
This paper establishes the link of microstructure and macroeconomic factors with the time-varying conditional correlation of foreign exchange and excess equity returns. By using the proposed DCC model with exogenous variables, capital flows and interest rate differentials are shown to be significant determinants of this correlation which is inclusive of the short-run variation of both asset returns. The results also provide evidence of the dynamic behavior of global investors as they seek parity in equity returns between home and foreign markets to reduce exchange rate risks.
Keywords: uncovered equity parity; order flow; DCCX
Download this article:
Year: 2010 Vol.: 59 No.: 1