Colloquium on Statistical Sciences

Last updated: March 29, 2021, 7:07 p.m.

Speaker: Joemari Olea & Carla Intal

Date: April 8, 2021, 4 p.m.

Venue: via Zoom

Join us in our Colloquium on Statistical Sciences via Zoom! You may register here: bit.ly/Colloq0408.

The talks will also be livestreamed through Facebook Live at https://www.facebook.com/UPDStat/live.









ABSTRACT
Finite Mixture Modelling Application for Cognitive Diagnosis
by Joemari Olea, UP School of Statistics

Although the Generalized deterministic inputs, noisy “and” gate (G-DINA) model is a general cognitive diagnosis model (CDM), it does not account for the heterogeneity that is rooted from existing subgroups in the population of examinees. To address this, this study proposes the Mixture G-DINA model, a CDM that incorporates the G-DINA model within the finite mixture modeling framework. An Expectation-Maximization algorithm will be developed to estimate the Mixture G-DINA model. To determine the viability of the proposed model, an extensive simulation study will be conducted to examine the parameter recovery performance, model fit, and correct classification rates. Responses of examinees to a language assessment will be analyzed to further demonstrate the capability of the proposed model.


ABSTRACT
Can local electoral support for the President influence fiscal allocations to the municipality: Evidence from the 2016 Philippine Elections
by Carla Intal, Oxford Internet Institute

In settings where resources are limited as is the case in developing countries like the Philippines, local governments rely on national revenues to provide for the basic needs of its citizens. In many cases, the distribution of national income to local units is formulaic and mandated by law. However in recent years, there persists a growing body of literature—particularly in low and middle-income economies—suggesting the influence of politics in intergovernment resource allocation. This paper explores the idea that national governments use its resources as a “prize” to politically-aligned localities. Using data from the most recent Philippine election and a regression discontinuity research design, the results indicate that municipalities that supported the president-incumbent subsequently received a higher budgetary allocation from the national government.