The Z-score formula for predicting bankruptcy was published in 1968 by Edward I.

Altman, who was, at the time, an Assistant Professor of Finance at New York University. The formula may be used to predict the probability that a firm will go into bankruptcy within two years. Z-scores are used to predict corporate defaults and an easy-to-calculate control measure for the financial distress status of companies in academic studies. The Z-score uses multiple corporate income and balance sheet values to measure the financial health of a company. Estimation of the formula The Z-score is a linear combination of four or five common business ratios, weighted by coefficients. The coefficients were estimated by identifying a set of firms which had declared bankruptcy and then collecting a matched sample of firms which had survived, with matching by industry and approximate size (assets). Altman applied the statistical method of discriminant analysis to a dataset of publicly held manufacturers. The estimation was originally based on data from publicly held manufacturers, but has since been re-estimated based on other datasets for private manufacturing, non-manufacturing and service companies. The original data sample consisted of 66 firms, half of which had filed for bankruptcy under Chapter 7. All businesses in the database were manufacturers, and small firms with assets of < $1 million were eliminated. The original Z-score formula was as follows: Z = 0.012T1 + 0.014T2 + 0.033T3 + 0.006T4 + 0.009T5. T1 = Working Capital / Total Assets. Measures liquid assets in relation to the size of the company. T2 = Retained Earnings / Total Assets. Measures profitability that reflects the company's age and earning power. T3 = Earnings Before Interest and Taxes / Total Assets. Measures operating efficiency apart from tax and leveraging factors. It recognizes operating earnings as being important to long-term viability. T4 = Market Value of Equity / Book Value of Total Liabilities. Adds market dimension that can show up security price fluctuation as a possible red flag. T5 = Sales/ Total Assets. Standard measure for total asset turnover (varies greatly from industry to industry). Altman found that the ratio profile for the bankrupt group fell at -0.25 avg, and for the non-bankrupt group at +4.48 avg. Precedents

Altman's work built upon research by accounting researcher William Beaver and others. In the 1930s and on, Mervyn and others had collected matched samples and assessed that various accounting ratios appeared to be valuable in predicting bankruptcy. Altman's Z-score is a customized version of the discriminant analysis technique of R. A. Fisher (1936). William Beaver's work, published in 1966 and 1968, was the first to apply a statistical method, t-tests to predict bankruptcy for a pair-matched sample of firms. Beaver applied this method to evaluate the importance of each of several accounting ratios based on univariate analysis, using each accounting ratio one at a time. Altman's primary improvement was to apply a statistical method, discriminant analysis, which could take into account multiple variables simultaneously. Accuracy and effectiveness In its initial test, the Altman Z-Score was found to be 72% accurate in predicting bankruptcy two years prior to the event, with a Type II error (false positives) of 6% (Altman, 1968). In a series of subsequent tests covering three different time periods over the next 31 years (up until 1999), the model was found to be approximately 8090% accurate in predicting bankruptcy one year prior to the event, with a Type II error (classifying the firm as bankrupt when it does not go bankrupt) of approximately 1520% (Altman, 2000).[1] From about 1985 onwards, the Z-scores gained wide acceptance by auditors, management accountants, courts, and database systems used for loan evaluation (Eidleman). The formula's approach has been used in a variety of contexts and countries, although it was designed originally for publicly held manufacturing companies with assets of more than $1 million. Later variations by Altman were designed to be applicable to privately held companies (the Altman Z'-Score) and non-manufacturing companies (the Altman Z"-Score). Neither the Altman models nor other balance sheet-based models are recommended for use with financial companies. This is because of the opacity of financial companies' balance sheets, and their frequent use of off-balance sheet items. There are market-based formulas used to predict the default of financial firms (such as the Merton Model), but these have limited predictive value because they rely on market data (fluctuations of share and options prices to imply fluctuations in asset values) to predict a market event (default, i.e., the decline in asset values below the value of a firm's liabilities).[2] Original z-score component definitions variable definition weighting factor T1 = Working Capital / Total Assets T2 = Retained Earnings / Total Assets T3 = Earnings Before Interest and Taxes / Total Assets T4 = Market Value of Equity / Total Liabilities

T5 = Sales/ Total Assets Z score bankruptcy model: Z = 1.2T1 + 1.4T2 + 3.3T3 + 0.6T4 + .999T5 Zones of Discrimination: Z > 2.99 -Safe Zones 1.81 < Z < 2.99 -Grey Zones Z < 1.81 -Distress Zones Z-score estimated for private firms T1 = (Current Assets Current Liabilities) / Total Assets T2 = Retained Earnings / Total Assets T3 = Earnings Before Interest and Taxes / Total Assets T4 = Book Value of Equity / Total Liabilities T5 = Sales/ Total Assets Z' Score Bankruptcy Model: Z' = 0.717T1 + 0.847T2 + 3.107T3 + 0.420T4 + 0.998T5 Zones of Discrimination: Z' > 2.9 -Safe Zone 1.23 < Z' < 2. 9 -Grey Zone Z' < 1.23 -Distress Zone [edit]Z-score estimated for non-manufacturer industrials & emerging market credits T1 = (Current Assets Current Liabilities) / Total Assets T2 = Retained Earnings / Total Assets T3 = Earnings Before Interest and Taxes / Total Assets T4 = Book Value of Equity / Total Liabilities Z-Score bankruptcy model: Z = 6.56T1 + 3.26T2 + 6.72T3 + 1.05T4 Zones of discrimination: Z > 2.6 -Safe Zone

1.1 < Z < 2. 6 -Grey Zone Z < 1.1 -Distress Zone The Z-score is a combination of five weighted business ratios and can also be used to predict bankruptcy. In a series of tests covering three different time periods over 31 years (up until 1999), the model was found to be 80-90% accurate in predicting bankruptcy one year prior to the event, with a error rate of 1520%.

The z-score is calculated as follows: Z-score = 1.2T1 + 1.4T2 + 3.3T3 + .6T4 + .999T5. T1 = Working Capital / Total Assets. T2 = Retained Earnings / Total Assets. T3 = Earnings Before Interest and Taxes / Total Assets. T4 = Market Value of Equity / Book Value of Total Liabilities. T5 = Sales/ Total Assets.

And is interpreted as follows: Z-score > 2.99 = Safe 1.8 < Z-score < 2.99 = Middle or grey Z-score < 1.80 = Distress

The Altman Z-Score was developed by New York University professor Edward I. Altman. It is intended to determine the risk of a company going bankrupt. The original Z-score formula was as follows:

Z = 0.012X1 + 0.014X2 + 0.033X3 + 0.006X4 + 0.999X5</math>

Where:

X1 = Working Capital / Total Assets X2 = Retained Earnings / Total Assets X3 = Earnings Before Interest and Taxes / Total Assets X4 = Market Value of Equity / Book Value of Total Liabilities X5 = Sales / Total Assets

Altman found that the score had an 84% accuracy rate of predicting bankruptcy within two years for companies with a score below 1.81.

Altman challenges the quality of the univariate ratio analysis as an analytical technique.He applies multivariate discriminant analysis to derive a linear combination of the ratioswhich best discriminate between financially distressed and nondistressed groups.Altman uses a sample of 33 bankruptcies filed between 1946 and 1965 and matchesthem with 33 nondistressed firms from the same industry and of similar size. All com- panies are operating in the manufacturing industry; small firms with assets less than $ 1million are deleted from the sample. Similarly to Beaver, he selects 22 financial ratios 284 Cybinski (2003, 12). 285 Keasey and Watson (1991). 286 Cybinski (2003, 13). 287 Altman (2002, 9).

Financial Distress and Risk: State of the Art in Theory and Empirical Research 91 based on their popularity in the literature and potential relevance to the study and groupsthem into five categories: profitability, liquidity, leverage, solvency, and activity. After numerous statistical tests of the interrelations among variables, tests of statistical sig-nificance and predictive accuracy, Altman is able to specify five ratios which are themost significant indicators of distress risk. An overall score, known as Altmans Z-Score, can be computed from the following discriminant function: 1 2 3 4 5 0 . 0 1 2 0 . 0 1 4 0 . 0 3 3 0 . 0 0 6 0 . 9 9 9 Z X X X X X = + + + + (3)where X 1 = working capital to total assets, X 2 = retained earnings to total assets,

X 3 =earnings before interest and taxes to total assets, X 4 = market value of equity to book value of total liabilities, X 5 = sales to total assets, and Z = overall index or score. Com- panies with a Z-Score lower than the cutoff score are financially distressed; firms havinga Z-Score higher than the cutoff score are financially sound. The lower a firms Z-Score,the higher its probability of default.Altmans model is more accurate than Beavers univariate technique. In the originalsample the Type I error is only 6% and the Type II error is 3% respectively, with overallaccuracy of the score of 95%. 288 After the technique was established, several researchers directly tested the classificationaccuracy of Altmans Z-Score. Scott (1981) highlights that Altmans variable selectionapproach may cause a search bias if a chosen set of predictive variables is applied tofirms in time periods different from those used in the initial model. Begley et al. (1996)doubt the performance of the model in periods representing a different economic envi-ronment. For instance, changes in bankruptcy laws or buyout activities in the 1980schanged the likelihood of bankruptcy. Therefore, the use of the model developed prior to the changes may increase the number of classification errors. Finally, Grice and In-gram (2001) show that the accuracy of the initial model is significantly lower in recent periods and suggest re-estimating the coefficients of the discriminant function using es-timation samples close to the testing periods.Altman (2002) has documented changes in the accuracy and the relevance of original Z-Score in recent decades. While Type I error accuracy continues to be greater than 80%one year prior to default, Type II error increases substantially. The main reason for changes in accuracy is that the U.S. firms, in general, become more risky. This deterio-rates the meaning of a number of original financial distress indicators in the Z-Scoremodel. He reestimates the model for later periods and for different predictive samples. 288 The test is undertaken for the ratios obtained from financial statements one year prior to default.

Financial Distress and Risk: State of the Art in Theory and Empirical Research92 Most of the misclassified firms in the updated sample have a Z-Score between 1.81 and2.675. Altman calls this range the zone of ignorance or gray area. He concludes thatthe use of a more conservative cutoff of 1.81 has 84% accuracy rate, whereas accuracyof the cutoff equal 2.675 is comparable to the original sample and is 94%.To summarize, Altmans Z-Score substantially improves accounting-based techniquesof the identification of financial distress risk. The Z-Score represents a weighted combi-nation of ratios which best separates the two groups of firms. Many statistical packagesincorporate the multivariate discriminant analysis and allow estimation of coefficients of the Z-Score function for different geographical markets. This spares the time and work of calculating traditional ratios for drawing conclusions. The accuracy of Altmansmodel one year prior to default is substantially higher than that of Beavers univariatemodel. However, the multivariate discriminant technique also has limitations. The set of the relevant ratios varies from industry to industry. The technique is sensitive to thesample size and number of explanatory variables. It also depends on a number of restric-tive assumptions, such as linearity, normality, independence among predictors, whoseviolation affects robustness of the estimated results. 28

z-score pros: - easy to compute - easy to assign weights - standard method z-score cons: - risk losing information - risk unintended weights - risk confusing candidates Why Calculate z-Scores? To compare scores on two unlike scales - Conscientiousness - Physical performance test To combine scores on two unlike scales - Compute weighted average How to Calculate a z-Score Step 1. Compute the mean Step 2. Compute the standard deviation Step 3. Compute the z-score Z=X-X bar / SDx X=raw score Xbar=Mean SDx= standard deviation