Models | Formula | Variables | Descriptions |
---|---|---|---|
Altman (1968) Multiple Discriminant Analysis | Z = β I X Where Z is the MDA score and X represent the variables listed. Cutoff value: Z ≥ 2.675, classified as non-bankrupt Z < 2.675, classified as bankrupt | WCTA RETA EBITA MVEBVD SLTA | = Net Working Capital/Total Assets = Retained earnings/Total Assets = Earnings before interest and taxes/Total assets = Market value of equity/Book value of total liabilities = Sales/Total Assets |
Ohlson (1980) Logit Model | P = (1 + exp {-β I X})−1 Where P is the probability of bankruptcy and X represents the variables listed. The logit function maps the value of β I X to a probability bounded between 0 and 1. Cutoff value: Y > 0.5, classified as defaulted otherwise non-defaulted. | SIZE TLTA WCTA CLCA OENEG NITA FUTL INTWO CHIN | = Log (Total assets/GNP price-level index). Index with a base 100 for 1968. = Total liabilities/Total Assets = Working capital/Total Assets= Current Liabilities/Current Assets = 1 If total liabilities exceed total assets, 0 otherwise. = Net income/Total assets = Funds provided by operations (income from operation after depreciation) divided by total liabilities. = 1 If net income was negative for the last 2 years, 0 otherwise. = (NI t  − NI t − 1)/(|NI t | + |NI t − 1|) where, NI t is net income for the most recent period. The denominator acts as a level indicator. The variable is thus intended to measure the relative change in net income. |
Zmijewski (1984) Probit model | P = ɸ (β I X) Where, P is the probability of bankruptcy and X represents the variables listed, and ɸ (.) represents the cumulative normal distribution function. The probit function maps the value β IX to a probability bounded between 0 and 1. Cutoff value: X > 0.5, classified as bankrupt, otherwise non-bankrupt. | NITL TLTA CACL | = Net income divided by total liabilities. = Total liabilities divided by total assets. = Current assets divided by current liabilities. |