Award Date


Degree Type


Degree Name

Master of Science (MS)


Hotel Administration

First Committee Member

Zheng Gu

Number of Pages



This study makes an attempt to develop business failure prediction models for lodging firms located in South Korea using multi-variate analyses. These multi-variate analyses include Multiple Discriminant Analysis (MDA) and logit analysis. This study looked at the financial statements from a total of 154 firms to develop the prediction models, and used 11 different financial ratios from liquidity, solvency, leverage, and efficiency categories as classifying variables. The descriptive statistics of the 11 ratios for the failed and non-failed groups indicated that non-failed hospitality firms were significantly better than failed hospitality firms in terms of liquidity, leverage, and solvency, demonstrating the potential classifying ability of the financial ratios between failed and non-failed groups; A MDA model and a logit model were then developed based on sample firms' financial ratios one year prior to failure. For MDA, stepwise procedure was used and a model with three ratios was established. These three ratios were debt ratio, interest coverage ratio, and total assets turnover ratio; For the logit analysis, maximization of the log-likelihood function was used to derive a logit model also with three variables. (Abstract shortened by UMI.).


Analysis; Business; Discriminant; Failure; Firms; Korean; Lodging; Logit; Multiple; Prediction

Controlled Subject


File Format


File Size

1986.56 KB

Degree Grantor

University of Nevada, Las Vegas




If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to and include clear identification of the work, preferably with URL.


IN COPYRIGHT. For more information about this rights statement, please visit