English version of this page

Lu Zhang

Stipendiat - CREATE Senter for forskning på likhet i utdanning

E-post lu.zhang@create.uio.no

Rom 3526

Brukernavn

Besøksadresse Blindernveien 31 Kristine Bonnevies Hus (entrance from Moltke Moes vei by Bikuben) 0371 Oslo

Postadresse Postboks 1161 Blindern 0318 Oslo

Andre tilknytninger Det utdanningsvitenskapelige fakultet (Student)

Pressebilde Last ned visittkort

Faglige interesser

Jeg forsker på å utvikle estimeringsmetoder for generaliserte lineære latente variabelmodeller. Målet er å forbedre analyser og tolkning av resultater, slik at vi kan få mer robuste og nøyaktige konklusjoner innen utdanningsmåling.

Metodologiske interesser

Computerized adaptive testing

Item response theory

Estimation methods

Bakgrunn

M.Sc. in Assessment, Measurement and Evaluation, University of Oslo

M.Sc. i økonomi, University of Macau

Zhang, Lu & Andersson, Björn (2026). Likelihood ratio tests with marginal maximum likelihood using Laplace approximations and adaptive quadrature. Journal of Statistical Computation and Simulation. ISSN 0094-9655. s. 1–26. doi: 10.1080/00949655.2026.2616410. Fulltekst i vitenarkiv Vis sammendrag
Estimation of generalized linear latent variable models is typically done with marginal maximum likelihood (MML) estimation which requires approximation methods to compute integrals without a closed form solution. In applied settings, likelihood ratio tests are often used to test hypotheses regarding parameter restrictions. This study examines the properties of likelihood ratio tests when using approximate MML estimation. We consider first- and second-order Laplace approximations, along with adaptive Gauss-Hermite quadrature with varying numbers of quadrature points. In two simulation studies we perform likelihood ratio tests, varying data types (binary, ordinal, and count data), sample sizes, and the number of observed variables. The first simulation examines slope parameter equivalence, while the second focuses on group restrictions in multiple group models. Results indicate adaptive quadrature and second-order Laplace approximations provide reliable inference across most settings. Meanwhile, the first-order Laplace approximation generally works well except in some binary data cases.

Se alle arbeider i NVA

Zhang, Lu; Skov, Henrik; Massling, Andreas; Dall’Osto, Manuel; Evangeliou, Nikolaos & Che, Haochi [Vis alle 8 forfattere av denne artikkelen] (2026). Evolving Anthropogenic and Natural Aerosol Sources in the High Arctic. Fulltekst i vitenarkiv
Boogerd, Cathal; Moonen, Leon & Zhang, Lu (2008). On the Use of Data Flow Analysis in Static Profiling. Fulltekst i vitenarkiv Vis sammendrag
Static profiling is a technique that produces estimates of execution likelihoods or frequencies based on source code analysis only. It is frequently used in determining cost/benefit ratios for certain compiler optimizations. In previous work,we introduced a simple algorithm to compute execution likelihoods,based on a control flow graph and heuristic branch prediction. In this paper we examine the benefits of using more involved analysis techniques in such a static profiler. In particular, we explore the use of value range propagation to improve the accuracy of the estimates, and we investigate the differences in estimating execution likelihoods and frequencies.