Search

This article presents commentary from Lawrence Fisher about two papers in the current issue, "On the Pricing of Corporate Debt: The Risk Structure of Interest Rates" by Merton, and "The Economic Determinants of Systematic Risk," by Robichek and Cohn. He regards Merton's work as commendable, but wishes he would augment his model with a variable to represent transaction costs. In his view Robichek and Cohn address an important question, but their work is undermined by faulty statistical methods. The author describes six such flaws and proposes remedies for each.

Whenever a regression analysis is run, one of the key statistics which is reported is the coefficient of determination or, as it is more commonly known, R[sup 2]. This quantity represents the proportion of the variance of the dependent variable that is associated with ("explained by") the set of independent variables. However, this statistic is a biased estimate of the true coefficient of determination for the underlying population. Moreover, the bias in unadjusted R[sup 2] can be sizeable and may lead to serious misinterpretation of research results. The purpose of this note is to examine the magnitude of the bias in R[sup 2] and to discuss some of the properties of R[sup 2] adjusted for degrees of freedom, a statistic which is less biased than R[sup 2]. The properties of the unadjusted R[sup 2] are examined in the first part of this note. The second part describes the properties of adjusted R[sup 2] when adjustment is considered necessary. [ABSTRACT FROM AUTHOR]

In this paper, we present evidence that local trends do exist in the Standard and Poor's Index. We begin by assuming that the logarithm of the price at time t[sub 1], say log P(t[sub 1]), has an expected value which is a linear function of time. That is, E log P(t[sub 1]) = at[sub 1] + b where a and b are arbitrary but fixed constants. Then we use the techniques of the analysis of variance to test whether any constants in the expression above satisfy the data. The tests show that these data are not explained by such an expected value. We conclude that the mean is different (certainly more complicated than at[sub 1] + b) over different intervals of time. The changes in expected value over these intervals are referred to as local trends. Finally, by repetition of the tests for different interval sizes, we find that the tests are significant for interval sizes up to approximately one year but not longer. Thus the evidence suggests that the local trends, when they occur, do not last longer than this period of time. [ABSTRACT FROM AUTHOR]

This study analyzes the differential effects of management (management effects) and other selected variables on commercial bank profitability and the operating relationships through which these effects are transmitted and relative profitability determined. Management effects are the results of differences in bank management objectives, policies, decisions, and actions reflected in differences in bank operating relationships, including profitability. The operating relationships reflect (1) overall profitability and gross revenue; (2) funds-use measures (asset-management measures, including "returns" on the uses); (3) funds-source measures (deposit and capital measures, including "costs" of the sources); and (4) expense measures. [ABSTRACT FROM AUTHOR]

The author comments on the article "Credit Regulations and Consumer Buying," by Duncan McC. Holthausen. The author explains that he agrees with Holthausen on the importance of having adequate consumer credit statistics. In Holthausen's article he presents suggestions for improving the figures, which fall into four broad categories. The categories include the elimination of non-consumer credit items in the statistics, adding consumer credit items not covered, bringing benchmark figures up to date, and expand and improve the reporting samples used to project benchmark figures. The author critically analyzes these categories.

The article presents a critical evaluation of available consumer credit statistics. It is reported that there are three principal types of consumer credit statistics available on a regular or periodic basis as of May 1952. The first consumer credit statistics examined in the article are volume statistics, which are the regular monthly estimates of consumer credit outstanding published by the U.S. Federal Reserve Board. Volume statistics are also comprised of the individual trade reports on installment sales and collections, also published by the Federal Reserve Board, and many monthly and annual reports on credit granted and unpaid balances made available by trade associations and state and federal governments.

This article focuses on the development of operating and capacity variances with the intension to improve decision making in regard to capacity design. The authors distinguish between the decentalization of capacity decisions and operating decisions in order to offer an alternative conceptual framework for generating variances. This distinction makes it possible to treat capacity as a decision variable, making it apart of control through variances. This also shows the possible sources of suboptimal output due to the interaction between the operating and capacity decisions.

The article discusses the predictive power of first-quarter earnings reports in earnings per share (EPS) reports. First-quarter EPS interim models are compared to the annual models which do not use first-quarter EPS. The earnings reports of 46 New York Stock Exchange firms were sampled in 1965. It was found that there was no clear improvement in annual predictions when first-quarter interim reports were used over annual reports. Also, there is commentary on the papers by Welsch and Holton which relate to earnings reports and predictive power.

The article reports on quality control for accounts receivable and discusses the paper "Managerial Controls of Accounts Receivable: A Deterministic Approach," by H. Banishay. The control scheme designed by Banishay consists of a departure from existing credit policy and facilitates management by exception. However, the control statistics he proposes do not distinguish between changes in sales volume and changes in the collection pattern. The article presents a modified control scheme and illustrates its effectiveness in a simulation of an accounts receivable operation.

This article presents information on Bayesian statistics. The author looks at the way Bayesian statistical decision theory has been dealt with in literature, focusing on "Probability and Statistics for Business Decisions," by Robert Schlaifer. Bayesian statistical decision theory is distinguished from classical statistics by being problem solving oriented and relying on the use of subjective rather than objective measures of probability. Through Bayes' Theorem, data taken from personal probabilities can be used in conjunction with data taken from samples of the process being evaluated, resulting in probabilities which reflect the entirety of the decision-makers knowledge on the problem at hand. Bayesian approaches that lend themselves to auditing functions are discussed.

The article presents several charts and statistics concerning the manuscripts submitted to the journal for 1972 and compared with previous years.

The article presents commentary from Irwin E. Jones about an article written by Henry A. Latane and William E. Young (L&Y), "Test of Portfolio Building Rules," which appeared in the September, 1969 edition of the "Journal of Finance." In that paper L&Y concluded that diversification of a securities portfolio both reduces the portfolio's variance and increases its geometric mean return. Jones observes that this contradicts accepted portfolio theory and is in fact erroneous, owing to L&Y's misuse of statistics.

Replies to an objection to some statistical tests of the Keynesian demand function for money. Deflated values for the money stock and for income; Belief that a 17-year weighted moving average of current and past interest rates is a good measure. [ABSTRACT FROM AUTHOR]

The article presents statistics and reports regarding the journal's editorial operations in 1966.

The article looks at several dilemmas prevalent in modern accounting research as discussed in the "Journal of Accounting Research." The author notes that two separate volumes published within the "Journal of Accounting Research" hold different opinions on the state of accounting. The first volume dictates that accountancy is out with natural law, while the second informs that double-entry accountancy is both a natural law and a theory from which all necessary working principles may be deduced. The duties of the accountant are discussed. The author feels that accounting must not only address obsolescence, but one must learn to assess it and incorporate it in the Accounting Theory.

Soit une suite stationnaire {X [ABSTRACT FROM AUTHOR]

Nagambal et Tracy {1} ont donné des règles pour las multiplication da n'importe quel 'Polykay' par un autre 'Polykay' de 5 facteurs. Dans {2}, ils not proposé des reègles semblables pout la multiplication d'un 'Polykay' par des productis de 'Polykays' de 5 facteurs. Dans cet article, toutes ces rèqles sont présentées explicitement. [ABSTRACT FROM AUTHOR]

Cet article contient l'analyse et la contruction de quelques expériences confuses 'diallelle' comprenant des F [ABSTRACT FROM AUTHOR]

La puisance de l'analyse de variance paramétrique habituelle pour un modèle á deux factues avec intéractions possibles est comparée à la puissance d'un test basé sur l'analyse paramétrique habituelle partiquée sur les rangs, c.-à.-d. que l'on utilise une transformation donnant des rangs. Alors que las théorie mathématique n'a pas encore été élaborée pour une tell approche, cette étude indique que c'est probablement une méthode valide, et démontre qu'un démontre qu'un développement de la théorie aurait unecertaine valeur. Des résultats de simulations sont présenté pur trois populations sous-jacentes; normale, normale containée, et exponetielle. Ces résultats montrent que l'approache par les rangs mène, dans tous les cas étudiée à partir de données brutes. Une faible perte de puissance peut se produire lorsque l'on utilise cettle approache, mais un accroissement significatif est apparent quand la population sous-jacente est normale contaminée. [ABSTRACT FROM AUTHOR]

In this experiment an attempt was made to determine which of a number of neuroelectric variables best predict the amplitude of the average evoked potential (AEP). Several EEG parameters derived from period analysis and amplitude integration of the primary trace, as well as the amplitude and latencies of single sensory evoked potentials, were treated with a stepwise multiple regression procedure. The amplitudes of certain components of the AEP were tested against the battery of independent variables (predictors) as separate criteria. The results of these analyses revealed that the amplitude of the single EPs accounted for the greatest proportion of variance in the AEP (each component measured). These data suggest that the size of the AEP is not dependent on spontaneous EEG fluctuations. [ABSTRACT FROM AUTHOR]

The statistical distributions of heart rate (HR) and heart period (HP) measures were compared for 10 adults. Koimogorov-Smirnov indices of fit and specific indices of skewness and kurtosis were applied to a 40-min sample of baseline heart beats. Neither individual HR nor HP distributions were consistently normally distributed. Over the sample, HP distribution indices were not significantly different from normal although HR distribution indices were. The use of HP in measuring cardiac evoked responses is advocated. [ABSTRACT FROM AUTHOR]

Three long series of rainfall and wheat yield data in climatically different regions of Israel were analyzed by means of different statistical methods as well as by means of a simple soil moisture simulation technique. Both the statistical methods and the simulation model gave good results in the arid zone, accounting in all cases for more than 70 percent of the yield variations. In areas of higher rainfall the statistical methods that gave the best results explained about 30 percent of these variations that were accounted for by the simulation model.

Most futurologists seem to assume that the best way of coping with the future is to perfect methodologies of prediction, but the ability to forecast accurately may not be the crucial element in dealing effectively with the future. Rather, trying to create the future might be far more fruitful, a possibility this paper explores in some detail. [ABSTRACT FROM AUTHOR]

Although essential to a good understanding of human cutaneous infections, studies on long term carriage of skin bacteria are rare, perhaps because there are few adequate typing schemes with which to identify organisms accurately. A seven month qualitative study of two individuals showed that three groups of organisms-residents, "nomads" and transients-could be identified. Quantitative study of 12 individuals suggested that while the standard deviation of the mean count in a series of residents may reach 25 % of the mean count, in transients it may be far higher. Statistical methods might therefore be employed in determining the status of cutaneous bacteria. [ABSTRACT FROM AUTHOR]

This article comments on the study, The Ruin Problem in Multiple-Line Insurance--A Simplified Model, by A. E. Hofflander and R. M. Duvall, published in the June 1967 issue of the Journal of Financial and Quantitative Analysis. This study is one of the more significant efforts in applying statistical techniques to devise rules for testing the ratio of premiums written to policyholders' surplus. The authors state that their purpose is to make use of a generally accepted statistical tool to devise and explain a new rule for relating premiums written to policyholders' surplus, taking the loss reserve and stock portfolio into account. They concluded at the end of their paper that under the worst possible conditions a property and liability insurance company could write up to $9.10 of premiums for every dollar of policyholders' surplus with only the slightest probability of becoming insolvent. This was a rather astounding conclusion, given the emphasis on the traditional 2:1 rule which has been expounded in industry circles for years. The conclusion may have been so astounding as to turn practical insurance men and women off from considering their model. Unfortunately, Hofflander and Duvall may have unknowingly blunted the importance of their efforts by a rather elementary arithmetic error. Rather than a 9.1:1 premiums to policyholders' surplus ratio, it should have been .91:1. Apparently they misplaced the decimal by one place. A ratio of .91:1 is obviously much more realistic and certainly a more palatable result for practitioners in the industry.

This article deals with a study which restated the concept of insurer's risk using elementary statistical theorems. In its simplest form the insurer's risk model assumes that the company insures n identical exposure units. In the model the losses of the i-th exposure limit can be represented by the random variable x1 which can range in value from 0 to V where V is the total amount of insurance written on that exposure unit. The assertion that insurance is possible when the average covariances are equal to zero is supported by a law of large numbers. However, since there is no readily applicable central limit theorem, confidence limits cannot be established. Furthermore, negative correlation is unlikely to be very strong in any insurance situation and will almost certainly not offset a clear catastrophe hazard. Thus, although technically one could quarrel with the statement that independence is necessary for insurance, in fact that assertion is generally true both theoretically and practically. This article has utilized some elementary statistical theorems to restate the concept of insurer's risk and to elaborate upon and extend that concept in such a way as to expose some prevalent fallacies in that topic. It is hoped that this information will be useful to teachers of insurance in presenting material on insurer's risk.

This article presents views on the assertion made that different performance characteristics of stock and mutual life insurance companies are caused by the difference in the two ownership types. It is contended that the sample presented enables application of statistical inference to the population of stock and mutual life insurance companies operating under New York State regulations. One is inclined to argue that statistical inference cannot be applied here, because the companies investigated do not comprise a sample, but a census of all typical life insurance companies licensed in the New York State. The said sample: excludes new companies, namely, those which had less than fifteen years of operation prior to 1952; excludes atypical firms, namely, those limited to certain customer groups or certain products; and it includes all other companies licensed in New York. The omission of new companies may be critical. On the one hand, one of the main reasons for undertaking the study was the rapid increase in the market share of stock companies. On the other hand, it is suggested that some of the change in the relative position of stocks and mutuals may be attributed to the many new stock companies which began operations during the years covered.

This paper presents a comparison of three distributed lag estimators: OLS, the Almon procedure, and the Hannan "inefficient" method. Each method is compared for sample sizes of 50 and 100 for several alternative distributed lag shapes and residual process structures. The results not only reveal the relative performance of these estimators, but also provide evidence on each method's performance under misspecification with respect to lag length and the residual process. [ABSTRACT FROM AUTHOR]

The article examines the use of the Chow test to determine the consequence of violation of the variances of error terms between separate sample regimens. The test is well behaved when there are variations of variances, if at least one of the sample sizes is very large. If the samples are of small sizes, the moderate heteroscedasticity has considerable effect on the level of significance of the test. It is better not to use tests against heteroscedasticity which assume the equality of regression coefficients between separate sample regimes. The direct use of the Chow test should be avoided.

This paper describes an iterative procedure for obtaining maximum likelihood estimates of the parameters of a generalized regression model when direct maximization with respect to all parameters is difficult. A proof of convergence and some interesting applications are provided. [ABSTRACT FROM AUTHOR]

This paper sets out a general criterion for the identifiability of a statistical system, based on Kullback's information integral. It is shown that the general identification problem is equivalent to a maximisation problem, or where parameter restrictions are present, a problem in nonlinear programming. The relationship of this criterion to that based on the information matrix of the underlying distribution is also exhibited. [ABSTRACT FROM AUTHOR]

Examines the accuracy of the hog farrowings report of the United States Department of Agriculture. Survey techniques; Performance test; Amount of bias detected by mean-square error statistic.

Frequently, alternative theories are proposed as relevant models for an economic process. Which alternative is a relatively better representation is a question of fact, but empirical methods of resolving the issue have not been compelling. This study develops a technique for discrimination from Bayesian statistical theory. This technique can analyze an arbitrary number of alternatives simultaneously, and each alternative can be characterized by distribution theory appropriate to its structure. An example, the aggregate consumption function, is considered, and each alternative is characterized by the Normal regression process. The results may only be regarded as suggestive, as the parameterization of the structure may be incomplete on that assumption. [ABSTRACT FROM AUTHOR]

A model for measuring subjective evaluations of multiple component alternatives is developed and tested in the context of business students' evaluations of professorial candidates for tenured positions. The model is based on a type of ANOVA formulation in which the response variable need only be rank ordered. That is, arbitrary monotonic functions of subjective responses can be made that optimize a well-defined badness of fit measure. Application of the model indicates that metric analysis of the response data can exhibit a large number of configural (interaction) effects that may be a reflection of how subjects use rating scales rather than anything more basic in their combination of multiple component cues. Implications of these findings for the modeling of multiple component choices are discussed. [ABSTRACT FROM AUTHOR]

The article discusses the relationship between ridge regression (RR) and the minimum mean square error (MMSE) estimator of Chipman. It provides information on the method of ridge regression. The assumptions on MMSE and RR and the measures of multicollinearity of the normal matrix are presented. An illustration of the Chipman estimator is given. It has been shown that both ridge regression and Chipman's method of estimation have something to offer the econometrician when the data re highly collinear. It also shows the difficulties in using RR.

The article provides information on the integration of projects among industries and a sector analysis on inter-industry relationship. It also discusses the details of semi-input-output system and the direct benefit-cost ratio of an increase in output from an international sector. A discussion on the increase in value-added and factor incomes is presented. The article shows how the semi-input-output method may be modified to accommodate the Little-Mirrlees criterion. It is clear from the national income identity that the increase in value-added is also the increase in factor incomes.

Focuses on a study which examined the acquisition patterns of consumer durables. It discusses the purchasing behaviors of consumers and the estimation of a priority acquisition pattern. The article attempts to determine whether it is possible, by observing the outcome of past purchasing behavior by individual consumers, to establish that there is, within tolerable limits, a unique order in which a particular set of durables tends to be acquired by all members of the population or a particular sub-group.

The reliability of the quarterly national income and product (NIP) accounts of the United States is examined from several standpoints. First, possible sources of error in the quarterly NIP accounts are explored, the most important being the lack of appropriate data, seasonal adjustment errors, sampling errors and biases, and the nature of the U.S. statistical system. Next, four ways of assessing the reliability of the accounts are considered. The most weight is given to measures of revisions in early estimates of the quarterly NIP aggregates. Results of previous studies of revisions are reviewed, and a summary of a major study of revisions for the period 1947-71 is given. The other ways of assessing reliability which are examined are the effect of errors on economic policy making, analysis of the statistical discrepancy, and expert judgment on sources and methodology. The degree of accuracy is judged to be generally sufficient for the policy decisions for which the NIP estimates are used. The early estimates of a quarter's change in GNP almost always distinguish whether the ultimate estimate will be large or small and will usually distinguish whether the ultimate estimate will be larger or smaller than the preceding quarter. While the accuracy of the estimates has generally been sufficient, the accuracy for 1965 was judged insufficient by policymakers. There is some evidence that errors have been reduced over time. [ABSTRACT FROM AUTHOR]

Most developing countries have compiled national accounts on a regular basis only for the last few years. It has not yet been possible for them to collect many of the statistics necessary to obtain good coverage of their economic activities by methods which would generally be accepted as reliable. Consequently the checks on reliability imposed by the framework of the national accounts are often absent, and the accounts prepared contain many estimates of doubtful quality. These doubts can usually only be removed as statistics collected by better methods become available. This is proving to be a slow process, partly because of the shortage of trained statistical staff and the competing demands of social and demographic statistics and partly because of the inherent difficulties in collecting good statistics from small business and traditional households. The need to define traditional households as producers as well as consumers leads to our demanding extra information from this difficult sector. In addition it is often difficult for the national accounts statistician, and even more so for the user, to find out in the time available exactly how some of the statistics with which he is presented were obtained. When this cannot be done it is impossible to assess their reliability. Thus assessing the overall reliability of national accounts in developing countries for even a limited range of uses is at present largely a matter of personal judgment. The information necessary to make more objective assessments rarely exists and because the problems which developed countries face in using such information are not yet which the experience of most developing countries. [ABSTRACT FROM AUTHOR]

The article presents that several statistics are available to test the impact of public policy when the research is cast in the quasi-experimental, interrupted time-series context. Each of these statistical tests is appropriate for a specifically formulated hypothesis. That is, some tests focus upon intercept differences and some upon differences of slope. For all tests, it is assumed that the change point is established independent of the data. However, if a researcher has sound theoretical reasons for expecting the treatment, innovation, or intervention to have a delayed impact, a number of post-intervention observations may be included as pre-change data points.

A Note on the. Treatment of Serial Correlation. There are essentially two courses of action open to the researcher who finds that the Durbin-Watson statistic is significant: (a) to re-estimate the original equation using a technique designed to take account of autoregressive errors; (b) to re-specify the equation until the Durbin-Watson statistic becomes insignificant. The purpose of this paper is to suggest a large sample test procedure to test the hypothesis that the first course of action is valid. The test only uses results from simple least squares estimation and so no complicated computation is required. The test is illustrated using data previously published in a paper by Durbin and Watson. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to construct an index of industrial morale that incorporates information on several indicators of industrial morale simultaneously and then to test certain conjectures concerning the causes and consequences of morale by statistical techniques that effectively hold other relevant variables constant. [ABSTRACT FROM AUTHOR]

THIS article is concerned with some of the evidence for one of the most widely held and frequently expressed theories of industrial unrest--the 'state subsidy' theory of strikes. Holders of all forms of this theory assume a positive relationship between payments to strikers and their families (in the form of tax rebates, family allowances and supplementary social security benefits), and the extent and duration of stoppages of work. In its general form the theory implies that recent increases in the volume and level of state payments to some extent 'explain' general changes in the British strike pattern--i.e. increases in the frequency, size and duration of strikes. [ABSTRACT FROM AUTHOR]

The article examines labor statistics on absence, overtime, and the structure of employees' compensation package. Several shortcomings of the various government bodies' approaches to labor statistics are discussed, primarily the use of macro-level statistics (such as a national income policy) to address micro-level issues (such as earnings or training). Two different statistical approaches are described, and the role of overtime and other incentive elements in the pay packet. The effects of incentive earnings and inflation on employees' effort-reward relationship are also considered.

Copyright of European Journal of Social Psychology is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years there has been a considerable, although inconclusive, debate concerning the relationship between the degree of unionization and union power. Craft unions tend to recruit by occupation across several industries, whilst the general unions recruit members from a wide variety of trades. Any industrial division is bound to be arbitrary to some extent in the absence of detailed classification by individual unions. The purpose of this article is to undertake a process of estimation for the post-war years. The nature of the available sources is slightly different, however, so that the method of calculation must again be outlined. The article supplements the previously published estimates from 1924 to 1938 by providing comparable data for the post-war years. This detailed description of the research methods is justified by the intricate process of calculation required due to the non-industrial structure of British trade union organization. It is hoped that the series provided, will prove useful to future investigators in this field, although the imperfections of the data and the assumptions and approximations of our method of estimation must be remembered.

Unemployment may be broadly classified as that caused by the inadequacy of aggregate demand and that arising out of the imperfect functioning of the labour market. The former is referred to as demand-deficient unemployment the latter as non demand-deficient unemployment. It is assumed that demand-deficient unemployment is the composite of frictional and structural unemployment. Researchers define it as that amount of unemployment existing at the Beveridge full employment level; that it is the amount of unemployment existing when aggregate unemployment is just equal to aggregate unfilled vacancies. Any unemployment in excess of this amount is defined as demand-deficient unemployment. If it is assumed - that all workers attached to a particular occupation are able to fill any job vacancy that arises in that occupation then any vacancies that do arise will be purely frictional, provided that unemployment exceeds vacancies for that occupation. Thus in 1965, when male unemployment was lower on average than in any other year--and the ratio of male unemployment to vacancies was at its minimum--28 per cent of total male unemployment was structural.

The article analyzes the utility of maximizing firms in economics. The dichotomy between ownership and control of the firm has led to increasing criticism of the profit maximizing assumption of the neoclassical model of the firm. The article discusses various approaches to prove superior to the maximization of monetary profit where vigorous competition is absent and barriers to entry are absent. The article also examines the implications, which can be deduced if the assumption is replaced. Numerous mathematical formulas have been used in the process of analyzing the utility. The article reveals that important differences emerge as between the profit maximizer and the utility maximizer. It also explains the positive correlation, which researchers have obtained between wage levels and the concentration ratio, a result, which is inconsistent with simple profit maximizing models. The article points out two implications of utility maximizing models of the firm, which offer additional explanation of propositions or empirical results obtained by other researchers.

The article discusses relations between the intraclass correlation and the Kuder-Richardson reliability formulas. The intraclass correlation coefficient based upon analysis of variance concepts is now widely used to secure estimates of inter-rater reliability. Psychologist A.L. Ebel proposed use of this index and indicated its relation to other estimates of reliability such as the product-moment correlation, average inter-rater correlation, and Horst's generalized reliability coefficient. Earlier psychologist C. Hoyt also developed an estimate of reliability based on analysis of variance.

The article focuses on the Cornell Medical Index, a self-administered 195 item questionnaire of medical and psychiatric items was given to 45 male and 56 female psychiatric outpatients, with the two sex groups equated for age, education and type of illness, as well as ape proximate socio-economic background. Analyses revealed few sex differences on the medical scales and none on the psychiatric scales. The psychiatric scales were analyzed to determine possible differences in complaints between the sexes and between the individual scales themselves for both sexes.