Two of the five signs (coefficients), X 4 and X 5 , are positive and contrary to ex-
pectations since, for this model, negative scores indicate a healthy situation and pos-
itive scores indicate a failure classification. His model was based on observations
over five reporting periods prior to failure and is not based on one-year intervals. His
results were only mildly impressive, with accuracies ranging from 70% to 80% for
one year prior and remaining surprisingly stable over a five-year period prior to fail-
ure. He explains in his book (1979) that the stability is due to the facts that there are
no liquidity variables and the stable role of the value-added measure. Subsequent
tests of Bilderbeek’s model have been quite accurate (80% over five years). Appar-
ently, several institutions are now using his model for practical purposes.
(b) Van Frederikslust (1978). Van Frederikslust’s (1978) model included tests on a
sample of 20 failed and a matched nonfailed sample of observations for 1954 through
- All firms were quoted on The Netherlands Stock Exchange. In addition to the
now traditional research structure, that is, linear discriminant analysis, single year ra-
tios, and equal a prioriprobability of group membership assumptions, the author per-
formed several other tests. Those included (1) looking at the development of ratios
over time (temporal model) as well as analyzing ratio levels, (2) varying the a priori
assumption of group membership likelihood to conform with a specific user of the
model (e.g., lending officer), and (3) varying the expected costs of the models, tak-
ing into consideration the specific user’s utility for losses.
Van Frederikslust attempts to provide a theoretical discussion for his choice of
variables. He concludes that traditional measures of firm performance, that is, liq-
uidity, profitability, solvency, and variability of several of these categories, are the
correct indicators. Industry affiliation and general economic variables are also
thought to be important but are not included in his model. In fact, the primary model
only contained two variables representing liquidity and profitability.
Van Frederikslust’s primary model analyzed the level of ratios. His definition of
failure included many different types but essentially involved the failure to pay fixed
obligations. His sample included textile, metal processing, machinery, construction,
retailing, and miscellaneous firms. The nonfailed group (20) were randomly selected
from the same industries, size categories (assets), and time periods as was the failed
group. His first model was:
where
The author distinguishes between the internal coverageratio (cash balance + re-
sources earned in the period/short-term debt) and the external coverageratio (short-
term debt in period tplus available short-term debt [t– 1]). The external coverage
measures what can be expected from the renewal of existing debt and additional debt.
“Failure at moment (t) is completely determined by the values of internal and exter-
nal coverage at that moment” (p. 35). Van Frederikslust uses only the external cov-
erage measure in his “simple” model.
X 2 profitability ratio 1 rate of return on equity 2
X 1 liquidity ratio 1 external coverage 2
ZNFZ-score 1 Netherlands, Van Frederikslust 2
ZNF0.52930.4488X 1 0.2863X 2
10 • 18 BUSINESS FAILURE CLASSIFICATION MODELS