Michelle Liou

Prof. Dr. Michelle Liou

Institute of Statistical Science, Academia Sinica
orcid

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2001 in Applied Psychological Measurement
Verified
Journal Article
Closed access
MLMichelle Liou
Michelle Liou
PCPhilip E. Cheng
Philip E. Cheng
MLMing-Yen Li
Ming-Yen Li
The possibility of using surrogate variables (e.g., school grades, other test scores, examinee background information) as replacements for common items predicting sample-selection bias between groups was investigated. The problem was specified as an incomplete data problem of comparability studies and was addressed using nonequivalent groups. A general model for estimating complete data (fitted) distributions through covariates is proposed (including common-item scores and surrogate variables as special cases). Model parameters are estimated using the EM algorithm. Standard errors of comparable scores are derived under the proposed model. Data from an empirical example examined the use of surrogate variables for establishing score comparability.

1 October 2003 in Journal of Cognitive Neuroscience
Verified
Journal Article
Closed access
MLMichelle Liou
Michelle Liou
HSHong-Ren Su
Hong-Ren Su
JLJuin-Der Lee
Juin-Der Lee
PCPhilip E. Cheng
Philip E. Cheng
CHChien-Chih Huang
Chien-Chih Huang
CTChih-Hsin Tsai
Chih-Hsin Tsai
Historically, reproducibility has been the sine qua non of experimental findings that are considered to be scientifically useful. Typically, findings from functional magnetic resonance imaging (fMRI) studies are assessed with statistical parametric maps (SPMs) using a p value threshold. However, a smaller p value does not imply that the observed result will be reproducible. In this study, we suggest interpreting SPMs in conjunction with reproducibility evidence. Reproducibility is defined as the extent to which the active status of a voxel remains the same across replicates conducted under the same conditions. We propose a methodology for assessing reproducibility in functional MR images without conducting separate experiments. Our procedures include the empirical Bayes method for estimating effects due to experimental stimuli, the threshold optimization procedure for assigning voxels to the active status, and the construction of reproducibility maps. In an empirical example, we implemented the proposed methodology to construct reproducibility maps based on data from the study by Ishai et al. (2000). The original experiments involved 12 human subjects and investigated brain regions most responsive to visual presentation of 3 categories of objects: faces, houses, and chairs. The brain regions identified included occipital, temporal, and fusiform gyri. Using our reproducibility analysis, we found that subjects in one of the experiments exercised at least 2 mechanisms in responding to visual objects when performing alternately matching and passive tasks. One gave activation maps closer to those reported in Ishai et al., and the other had related regions in the precuneus and posterior cingulate. The patterns of activated regions are reproducible for at least 4 out of 6 subjects involved in the experiment. Empirical application of the proposed methodology suggests that human brains exhibit different strategies to accomplish experimental tasks when responding to stimuli. It is important to correlate activations to subjects' behavior such as reaction time and response accuracy. Also, the latency between the stimulus presentation and the peak of the hemodynamic response function varies considerably among individual subjects according to types of stimuli and experimental tasks. These variations per se also deserve scientific inquiries. We conclude by discussing research directions relevant to reproducibility evidence in fMRI.

1 August 2006 in NeuroImage
Verified
Journal Article
Closed access
ATArthur C. Tsai
Arthur C. Tsai
MLMichelle Liou
Michelle Liou
TJTzyy-Ping Jung
Tzyy-Ping Jung
JOJulie A. Onton
Julie A. Onton
PCPhilip E. Cheng
Philip E. Cheng
SMScott Makeig
Scott Makeig

1 September 2000 in Applied Psychological Measurement
Verified
Journal Article
Closed access
PDF file
PCPhilip E. Cheng
Philip E. Cheng
MLMichelle Liou
Michelle Liou
In computerized adaptive testing (CAT), an examinee’s trait level (Θ) must be estimated with reasonable accuracy based on a small number of item responses. A successful implementation of CAT depends on (1) the accuracy of statistical methods used for estimating and (2) the efficiency of the item-selection criterion. Methods of estimating suitable for CAT are reviewed, and the differences between Fisher and Kullback-Leibler information criteria for selecting items are discussed. The accuracy of different CAT algorithms was examined in an empirical study. The results showed that correcting estimates for bias was necessary at earlier stages of CAT, but most CAT algorithms performed equally well for tests of 10 or more items.

15 March 2016 in Journal of the International Phonetic Association
Verified
Journal Article
Closed access
PDF file
JEJonathan P. Evans
Jonathan P. Evans
JSJackson T.-S. Sun
Jackson T.-S. Sun
CCChenhao Chiu
Chenhao Chiu
MLMichelle Liou
Michelle Liou
This study explores the phenomenon of uvularization in the vowel systems of two Heishui County varieties of Qiang, a Sino-Tibetan language of Sichuan Province, China. Ultrasound imaging (one speaker) shows that uvularized vowels have two tongue gestures: a rearward gesture, followed by movement toward the place of articulation of the corresponding plain vowel. Time-aligned acoustic and articulatory data show how movement toward the uvula correlates with changes in the acoustic signal. Acoustic correlates of uvularization (taken from two speakers) are seen most consistently in raising of vowel F1, lowering of F2 and in raising of the difference F3-F2. Imaging data and the formant structure of [l] show that uvular approximation can begin during the initial consonant that precedes a uvularized vowel. Uvularization is reflected phonologically in the phonotactic properties of vowels, while vowel harmony aids in the identification of plain–uvularized vowel pairs. The data reported in this paper argue in favor of a revision of the catalog of secondary articulations recognized by the International Phonetic Alphabet, in order to include uvularization, which can be marked with the symbol [ʶ] in the case of approximation and [χ] for secondary uvular frication.

14 July 2022 in Sensors
Verified
Journal Article
Open access
PDF file
JLJiun-Wei Liou
Jiun-Wei Liou
PWPo-Shan Wang
Po-Shan Wang
YWYu-Te Wu
Yu-Te Wu
SLSheng-Kai Lee
Sheng-Kai Lee
SCShen-Da Chang
Shen-Da Chang
MLMichelle Liou
Michelle Liou
Approximate entropy (ApEn) is used as a nonlinear measure of heart-rate variability (HRV) in the analysis of ECG time-series recordings. Previous studies have reported that HRV can differentiate between frail and pre-frail people. In this study, EEGs and ECGs were recorded from 38 elderly adults while performing a three-stage cycling routine. Before and after cycling stages, 5-min resting-state EEGs (rs-EEGs) and ECGs were also recorded under the eyes-open condition. Applying the K-mean classifier to pre-exercise rs-ECG ApEn values and body weights revealed nine females with EEG power which was far higher than that of the other subjects in all cycling stages. The breathing of those females was more rapid than that of other subjects and their average heart rate was faster. Those females also presented higher degrees of asymmetry in the alpha and theta bands (stronger power levels in the right frontal electrode), indicating stressful responses during the experiment. It appears that EEG delta activity could be used in conjunction with a very low ECG frequency power as a predictor of bursts in the heart rate to facilitate the monitoring of elderly adults at risk of heart failure. A resting ECG ApEn index in conjunction with the subject’s weight or BMI is recommended for screening high-risk candidates prior to exercise interventions.