Logistic regression modelling for first and second language perception data

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Logistic regression analysis has, for some time, been successfully applied to L1 speech perception data, but has not been widely applied in L2 speech perception research. This chapter is a tutorial which makes use of simple data sets to introduce logistic regression analysis as applied to categorical response data from L1 and L2 speech perception experiments. Data are taken from an experiment on L1 Spanish vowel perception by Álvarez González, and experiments on L1 and L2 English vowel perception by Escudero & Boersma, and Morrison. Model fitting is demonstrated as a technique to determine which acoustic cues are attended to by listeners. Logistic regression coefficients are used to quantify how listeners use those acoustic cues, to produce graphical representations of their use of acoustic cues, and as statistics in secondary analyses used to determine whether there are significant differences in the perception of stimuli by L1 versus L2 groups of listeners.
Original languageEnglish
Title of host publicationSegmental and prosodic issues in Romance phonology
EditorsPilar Prieto, Joan Mascaro, Maria-Josep Sole
PublisherJohn Benjamins
Pages219-236
ISBN (Print)9789027247971
DOIs
Publication statusPublished - 6 Apr 2007

Publication series

NameSegmental and prosodic issues in Romance phonology
Volume282
ISSN (Print)0304-0763

Fingerprint

logistics
regression
language
listener
acoustics
experiment
regression analysis
stimulus
statistics
Group

Cite this

Morrison, G. (2007). Logistic regression modelling for first and second language perception data. In P. Prieto, J. Mascaro, & M-J. Sole (Eds.), Segmental and prosodic issues in Romance phonology (pp. 219-236). (Segmental and prosodic issues in Romance phonology; Vol. 282). John Benjamins. https://doi.org/10.1075/cilt.282.15mor
Morrison, Geoffrey-stewart. / Logistic regression modelling for first and second language perception data. Segmental and prosodic issues in Romance phonology. editor / Pilar Prieto ; Joan Mascaro ; Maria-Josep Sole. John Benjamins, 2007. pp. 219-236 (Segmental and prosodic issues in Romance phonology).
@inbook{f0a152796e694943b4c6192ed6e8bb37,
title = "Logistic regression modelling for first and second language perception data",
abstract = "Logistic regression analysis has, for some time, been successfully applied to L1 speech perception data, but has not been widely applied in L2 speech perception research. This chapter is a tutorial which makes use of simple data sets to introduce logistic regression analysis as applied to categorical response data from L1 and L2 speech perception experiments. Data are taken from an experiment on L1 Spanish vowel perception by {\'A}lvarez Gonz{\'a}lez, and experiments on L1 and L2 English vowel perception by Escudero & Boersma, and Morrison. Model fitting is demonstrated as a technique to determine which acoustic cues are attended to by listeners. Logistic regression coefficients are used to quantify how listeners use those acoustic cues, to produce graphical representations of their use of acoustic cues, and as statistics in secondary analyses used to determine whether there are significant differences in the perception of stimuli by L1 versus L2 groups of listeners.",
author = "Geoffrey-stewart Morrison",
year = "2007",
month = "4",
day = "6",
doi = "10.1075/cilt.282.15mor",
language = "English",
isbn = "9789027247971",
series = "Segmental and prosodic issues in Romance phonology",
publisher = "John Benjamins",
pages = "219--236",
editor = "Pilar Prieto and Joan Mascaro and Maria-Josep Sole",
booktitle = "Segmental and prosodic issues in Romance phonology",
address = "Netherlands",

}

Morrison, G 2007, Logistic regression modelling for first and second language perception data. in P Prieto, J Mascaro & M-J Sole (eds), Segmental and prosodic issues in Romance phonology. Segmental and prosodic issues in Romance phonology, vol. 282, John Benjamins, pp. 219-236. https://doi.org/10.1075/cilt.282.15mor

Logistic regression modelling for first and second language perception data. / Morrison, Geoffrey-stewart.

Segmental and prosodic issues in Romance phonology. ed. / Pilar Prieto; Joan Mascaro; Maria-Josep Sole. John Benjamins, 2007. p. 219-236 (Segmental and prosodic issues in Romance phonology; Vol. 282).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Logistic regression modelling for first and second language perception data

AU - Morrison, Geoffrey-stewart

PY - 2007/4/6

Y1 - 2007/4/6

N2 - Logistic regression analysis has, for some time, been successfully applied to L1 speech perception data, but has not been widely applied in L2 speech perception research. This chapter is a tutorial which makes use of simple data sets to introduce logistic regression analysis as applied to categorical response data from L1 and L2 speech perception experiments. Data are taken from an experiment on L1 Spanish vowel perception by Álvarez González, and experiments on L1 and L2 English vowel perception by Escudero & Boersma, and Morrison. Model fitting is demonstrated as a technique to determine which acoustic cues are attended to by listeners. Logistic regression coefficients are used to quantify how listeners use those acoustic cues, to produce graphical representations of their use of acoustic cues, and as statistics in secondary analyses used to determine whether there are significant differences in the perception of stimuli by L1 versus L2 groups of listeners.

AB - Logistic regression analysis has, for some time, been successfully applied to L1 speech perception data, but has not been widely applied in L2 speech perception research. This chapter is a tutorial which makes use of simple data sets to introduce logistic regression analysis as applied to categorical response data from L1 and L2 speech perception experiments. Data are taken from an experiment on L1 Spanish vowel perception by Álvarez González, and experiments on L1 and L2 English vowel perception by Escudero & Boersma, and Morrison. Model fitting is demonstrated as a technique to determine which acoustic cues are attended to by listeners. Logistic regression coefficients are used to quantify how listeners use those acoustic cues, to produce graphical representations of their use of acoustic cues, and as statistics in secondary analyses used to determine whether there are significant differences in the perception of stimuli by L1 versus L2 groups of listeners.

UR - https://benjamins.com/catalog/cilt.282.15mor

U2 - 10.1075/cilt.282.15mor

DO - 10.1075/cilt.282.15mor

M3 - Chapter

SN - 9789027247971

T3 - Segmental and prosodic issues in Romance phonology

SP - 219

EP - 236

BT - Segmental and prosodic issues in Romance phonology

A2 - Prieto, Pilar

A2 - Mascaro, Joan

A2 - Sole, Maria-Josep

PB - John Benjamins

ER -

Morrison G. Logistic regression modelling for first and second language perception data. In Prieto P, Mascaro J, Sole M-J, editors, Segmental and prosodic issues in Romance phonology. John Benjamins. 2007. p. 219-236. (Segmental and prosodic issues in Romance phonology). https://doi.org/10.1075/cilt.282.15mor