dc.description.abstract | Logistic regression combines independent variables to estimate the probability that a
particular event will occur, i.e. a subject will be a member of one of the groups defined
by the dichotomous dependent variable. If the probability for group membership in the
modeled category is above some cutoff point, the subject is predicted to be a member of
the modeled group. ]f the probability is below the cutoff point, the subject is predicted to
be a member of the other group.
This study assesses the probability of firm failure, a year before failure, using logistic
regression model that was developed by Ohlson (1980). The study utilized secondary
data collected from Capital Markets Authority and Nairobi Securities Exchange. The
required data was collected from financial statements of a sample of sixteen companies;
ten of which were in good financial health and six of which were financially distressed.
The study covered a range of 14 years from 1997 to 2011.
The results of this study show that logistic regression analysis is applicable in 9 out of 10
firms analyzed which indicates a 90% successful application of the Ohlson (1980) model
used in the study. The model is found to be successful in predicting business failure one
year before it occurs. The study concludes that the logistic regression analysis model
developed by Ohlson (1980) is applicable in predicting financial failure of companies and
is a useful tool for investors in the Kenyan market.
This study contributes to the literature by expanding the application of Ohlson (1980)
logit model to Kenya publicly listed companies. It provides applicable measures for
predicting firm delisting events in Kenya's stock markets. The study recommends that the
assessment be extended is to test bankruptcy prediction models to the non-listed,
relatively smaller turnover sized firms where the incidence of business failure is greater
than larger corporations. | en_US |