Exploring the application of latent class cluster analysis for investigating pedestrian crash injury severities in Switzerland

Lekshmi Sasidharan, Kun Feng Wu, Monica Menendez

    Research output: Contribution to journalArticle

    Abstract

    One of the major challenges in traffic safety analyses is the heterogeneous nature of safety data, due to the sundry factors involved in it. This heterogeneity often leads to difficulties in interpreting results and conclusions due to unrevealed relationships. Understanding the underlying relationship between injury severities and influential factors is critical for the selection of appropriate safety countermeasures. A method commonly employed to address systematic heterogeneity is to focus on any subgroup of data based on the research purpose. However, this need not ensure homogeneity in the data. In this paper, latent class cluster analysis is applied to identify homogenous subgroups for a specific crash type-pedestrian crashes. The manuscript employs data from police reported pedestrian (2009-2012) crashes in Switzerland. The analyses demonstrate that dividing pedestrian severity data into seven clusters helps in reducing the systematic heterogeneity of the data and to understand the hidden relationships between crash severity levels and socio-demographic, environmental, vehicle, temporal, traffic factors, and main reason for the crash. The pedestrian crash injury severity models were developed for the whole data and individual clusters, and were compared using receiver operating characteristics curve, for which results favored clustering. Overall, the study suggests that latent class clustered regression approach is suitable for reducing heterogeneity and revealing important hidden relationships in traffic safety analyses.

    Original languageEnglish (US)
    Pages (from-to)219-228
    Number of pages10
    JournalAccident Analysis and Prevention
    Volume85
    DOIs
    StatePublished - Dec 1 2015

    Fingerprint

    Cluster analysis
    Switzerland
    cluster analysis
    pedestrian
    Cluster Analysis
    Safety
    Wounds and Injuries
    traffic safety
    Manuscripts
    Police
    Law enforcement
    ROC Curve
    Demography
    Pedestrians
    Research
    police
    recipient
    traffic
    regression

    Keywords

    • Binary logit
    • Cluster analysis
    • Latent class
    • Pedestrian
    • Receiver operating characteristic (ROC) curve
    • Severity
    • Switzerland

    ASJC Scopus subject areas

    • Human Factors and Ergonomics
    • Safety, Risk, Reliability and Quality
    • Public Health, Environmental and Occupational Health
    • Law

    Cite this

    Exploring the application of latent class cluster analysis for investigating pedestrian crash injury severities in Switzerland. / Sasidharan, Lekshmi; Wu, Kun Feng; Menendez, Monica.

    In: Accident Analysis and Prevention, Vol. 85, 01.12.2015, p. 219-228.

    Research output: Contribution to journalArticle

    @article{7750e91222f748dd983ef76ddc5563a6,
    title = "Exploring the application of latent class cluster analysis for investigating pedestrian crash injury severities in Switzerland",
    abstract = "One of the major challenges in traffic safety analyses is the heterogeneous nature of safety data, due to the sundry factors involved in it. This heterogeneity often leads to difficulties in interpreting results and conclusions due to unrevealed relationships. Understanding the underlying relationship between injury severities and influential factors is critical for the selection of appropriate safety countermeasures. A method commonly employed to address systematic heterogeneity is to focus on any subgroup of data based on the research purpose. However, this need not ensure homogeneity in the data. In this paper, latent class cluster analysis is applied to identify homogenous subgroups for a specific crash type-pedestrian crashes. The manuscript employs data from police reported pedestrian (2009-2012) crashes in Switzerland. The analyses demonstrate that dividing pedestrian severity data into seven clusters helps in reducing the systematic heterogeneity of the data and to understand the hidden relationships between crash severity levels and socio-demographic, environmental, vehicle, temporal, traffic factors, and main reason for the crash. The pedestrian crash injury severity models were developed for the whole data and individual clusters, and were compared using receiver operating characteristics curve, for which results favored clustering. Overall, the study suggests that latent class clustered regression approach is suitable for reducing heterogeneity and revealing important hidden relationships in traffic safety analyses.",
    keywords = "Binary logit, Cluster analysis, Latent class, Pedestrian, Receiver operating characteristic (ROC) curve, Severity, Switzerland",
    author = "Lekshmi Sasidharan and Wu, {Kun Feng} and Monica Menendez",
    year = "2015",
    month = "12",
    day = "1",
    doi = "10.1016/j.aap.2015.09.020",
    language = "English (US)",
    volume = "85",
    pages = "219--228",
    journal = "Accident Analysis and Prevention",
    issn = "0001-4575",
    publisher = "Elsevier Limited",

    }

    TY - JOUR

    T1 - Exploring the application of latent class cluster analysis for investigating pedestrian crash injury severities in Switzerland

    AU - Sasidharan, Lekshmi

    AU - Wu, Kun Feng

    AU - Menendez, Monica

    PY - 2015/12/1

    Y1 - 2015/12/1

    N2 - One of the major challenges in traffic safety analyses is the heterogeneous nature of safety data, due to the sundry factors involved in it. This heterogeneity often leads to difficulties in interpreting results and conclusions due to unrevealed relationships. Understanding the underlying relationship between injury severities and influential factors is critical for the selection of appropriate safety countermeasures. A method commonly employed to address systematic heterogeneity is to focus on any subgroup of data based on the research purpose. However, this need not ensure homogeneity in the data. In this paper, latent class cluster analysis is applied to identify homogenous subgroups for a specific crash type-pedestrian crashes. The manuscript employs data from police reported pedestrian (2009-2012) crashes in Switzerland. The analyses demonstrate that dividing pedestrian severity data into seven clusters helps in reducing the systematic heterogeneity of the data and to understand the hidden relationships between crash severity levels and socio-demographic, environmental, vehicle, temporal, traffic factors, and main reason for the crash. The pedestrian crash injury severity models were developed for the whole data and individual clusters, and were compared using receiver operating characteristics curve, for which results favored clustering. Overall, the study suggests that latent class clustered regression approach is suitable for reducing heterogeneity and revealing important hidden relationships in traffic safety analyses.

    AB - One of the major challenges in traffic safety analyses is the heterogeneous nature of safety data, due to the sundry factors involved in it. This heterogeneity often leads to difficulties in interpreting results and conclusions due to unrevealed relationships. Understanding the underlying relationship between injury severities and influential factors is critical for the selection of appropriate safety countermeasures. A method commonly employed to address systematic heterogeneity is to focus on any subgroup of data based on the research purpose. However, this need not ensure homogeneity in the data. In this paper, latent class cluster analysis is applied to identify homogenous subgroups for a specific crash type-pedestrian crashes. The manuscript employs data from police reported pedestrian (2009-2012) crashes in Switzerland. The analyses demonstrate that dividing pedestrian severity data into seven clusters helps in reducing the systematic heterogeneity of the data and to understand the hidden relationships between crash severity levels and socio-demographic, environmental, vehicle, temporal, traffic factors, and main reason for the crash. The pedestrian crash injury severity models were developed for the whole data and individual clusters, and were compared using receiver operating characteristics curve, for which results favored clustering. Overall, the study suggests that latent class clustered regression approach is suitable for reducing heterogeneity and revealing important hidden relationships in traffic safety analyses.

    KW - Binary logit

    KW - Cluster analysis

    KW - Latent class

    KW - Pedestrian

    KW - Receiver operating characteristic (ROC) curve

    KW - Severity

    KW - Switzerland

    UR - http://www.scopus.com/inward/record.url?scp=84944062678&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84944062678&partnerID=8YFLogxK

    U2 - 10.1016/j.aap.2015.09.020

    DO - 10.1016/j.aap.2015.09.020

    M3 - Article

    VL - 85

    SP - 219

    EP - 228

    JO - Accident Analysis and Prevention

    JF - Accident Analysis and Prevention

    SN - 0001-4575

    ER -