Colloquium, Trainings, and Events


  • Image for Public Forum for the Selection of New UPSS Dean

    Public Forum for the Selection of New UPSS Dean

    Last updated: Aug. 14, 2019, 10:21 a.m.

    Date: Aug. 15, 2019, 9 a.m.

    Venue: Lecture Hall 1, School of Statistics

    Abstract: There will be a presentation of accomplishments of outgoing Dean and a presentation of the vision and plans of the nominees.

    Files :
    Call for Nominations, UPSS Deanship
    Schedule of activities in connection with the selection of the new Dean

  • Image for Some Recent Developments in the Item Response Theory Modeling of Forced-Choice Data

    Some Recent Developments in the Item Response Theory Modeling of Forced-Choice Data

    Last updated: March 12, 2019, 2:02 p.m.

    Speaker: Dr. Jimmy de la Torre. Faculty of Education, The University of Hong Kong

    Date: March 7, 2019, 2 p.m.

    Venue: UP Stat Lecture Hall 1

    Abstract: Likert format is the most popular item type for the measurement of non-cognitive constructs (e.g., attitude, personality). However, it is well known that responses to this format can be affected by response biases such as social desirability and faking. To address the bias-related issues in Likert format items, alternative item formats (i.e., forced-choice items) have been proposed. Traditional scoring of forced-choice items produces ipsative scores, which, some researchers claim, are appropriate for intra-individual, but not inter-individual comparisons. In this presentation, several item response theory models, which can be used in conjunction with different forced-choice formats, are presented to extract scores from ipsative instruments that can be used for inter-individual comparisons. In addition to the model formulation, model estimation and related issues are discussed. Simulation studies and a real data example are provided to examine the practical viability of the different models. The presentation concludes with a discussion of some unresolved issues and potential research directions pertaining to the analysis of forced-choice data.

    Kindly pre-register with Ms. Nancy Angala (npangala@up.edu.ph).

  • Image for The Impact of News Sentiment on Financial Risk: An Extreme Value Approach

    The Impact of News Sentiment on Financial Risk: An Extreme Value Approach

    Last updated: March 12, 2019, 2:06 p.m.

    Speaker: Prof. Peter Julian Cayton, Assistant Professor, UP School of Statistics

    Date: March 7, 2018, 4:30 p.m.

    Venue: Conference Room

    Abstract: Methods of estimating and analysing the impact of news sentiment on the behaviour of prices of financial instruments are proposed, based on the block maxima approach. The methods assume that news sentiment affects the maximum and minimum returns of an instrument through their generalised extreme value distributions. By applying these methods to the stock return data of the S&P500 firms, the predictive ability and accuracy of our methods are assessed from a risk-management perspective. To quantify the impact of news sentiment, we make use of the various sentiment measures from the comprehensive and unique RavenPack® database, which captures more than 1200 types of firm-specific and macroeconomic-specific events. The empirical results suggest that news sentiment has the potential of enhancing the predictive ability of our methods.

    Please pre-register with Ate Nancy

    Files :
    Publicity Material
    Publicity Material
    Publicity Material

  • Image for STAT SPEAKS: Seminar Series

    STAT SPEAKS: Seminar Series

    Last updated: March 12, 2019, 2:03 p.m.

    Speaker: Angelita P. Tobias

    Date: March 1, 2019, 5:15 p.m.

    Venue: UP Stat Lecture Hall 1

    Abstract: A nonparametric regression model to estimate multi-input transfer function model is proposed. Issues and limitations of the parametric transfer function such as linearity, correlated inputs, misspecification errors, short time series and presence of structural change are addressed by the nonparametric model. Three modelling approaches were compared - parametric transfer function(ARMAX), nonparametric regression generalized additive model (GAM), and forward search and nonparametric bootstrap (FSNB) method. Simulation results show that GAM performs best under short time series. Moreover, GAM is robust under the presence of misspecification error and structural change, on the number of inputs, correlated inputs, and length of time series. ARMAX on the other hand performed better on longer time series and exponentially decaying form. Forward search and nonparametric bootstrap method performed the least among the three approach but the mean absolute percent error (MAPE) is stable under different conditions of structural change such as location and length of structural change. Overall, the nonparametric approach is superior and most efficient in fitting different form of transfer function especially when there is misspecification error and correlated inputs.

  • Image for STAT SPEAKS: Seminar Series

    STAT SPEAKS: Seminar Series

    Last updated: March 12, 2019, 2:06 p.m.

    Speaker: Johann Sebastian B. Claveria, UP Diliman

    Date: March 1, 2019, 2:30 p.m.

    Venue: UP Stat Lecture Hall 1

    Abstract: In the analysis of count data, overdispersion happens when the response variance of the counts exceeds the response mean; and its presence in the count model often leads to underestimated standard errors and erroneous inferences. The existing method for detecting overdispersion is through the regression-based test, where the estimated response variance is modelled with a function of the mean, whose form is established prior to fitting the variance model; a score test statistic is then compared with the quantiles of a 𝑡_(𝑛−1) distribution. However, establishing the form of the variance a priori may lead to a misspecified variance, more so that it is not directly observed; consequently, the test statistic is also affected. This study explores the properties of the existing test under different scenarios of specifying the variance of an unknown form. Bootstrap simulations are carried out on different a priori models where the variance is modelled as a constant, a linear function, a quadratic function, and a polynomial function of the mean. Simulations show that while the parametric framework of the score test for overdispersion may seem to yield an improper statistical size yet high statistical power, its nonparametric counterpart yields a better statistical size yet low statistical power. This trend is observed as the assumed form of the variance model becomes more complicated. Moreover, simulations have shown that, as the framework does not consider restrictions in the estimation procedure of the variance model, negative estimates are observed, which may then yield to negative variances.

Highlights