Search

This article examines the impact on interstate net migration of differential state and local property tax and transfer policies in the United States by race, age and sex for 1965-70. The results offer considerable support to the Tiebout hypothesis that the consumer-voter moves to that area which best satisfies his preferences for public goods. [ABSTRACT FROM AUTHOR]

Demographic forecasting techniques fail with post-transition populations dominated by fluctuating fertility; time series analysis of fertility can improve the forecasts. This article develops the optimal forecast and its variance for births to an age-structured population subject to serially correlated random fertility. The white noise, first-order auto- regressive, second-order autoregressive and random walk fertility specifications are analyzed, each leading to different forecasts and very different variances, as shown by illustrative applications to U.S. data, 1917-1972. [ABSTRACT FROM AUTHOR]

American census-taking procedures had evolved slowly from the inception of the decennial census in 1790 until 1840, when a new high seemed evident in the many additional categories included in the survey. On publication, however, numerous errors were discovered in the figures, precluding the usefulness of the census data. Paradoxically, the discovery of these errors in the sixth census was to become the catalyst for reforms that would spearhead the government's use of modern statistical procedures. [ABSTRACT FROM AUTHOR]

The presumed objectivity of statistical methods of comparative terrain studies has a powerful appeal in a science dependent largely on qualitative descriptions of terrain differences. Nevertheless use of statistical methods of terrain description and comparison has not been widespread. The article attempted to show that maps of average slope, although they have a quantitative aspect are highly subjective depictions of slope conditions in an area. The sources of the subjective element are, the arbitrary nature of the selection of slope categories, the determinative effect of the selected slope categories on the delimiting of areas of contrasting slope conditions, and others.

Anyone who has constructed isarithmic maps has at one time or another been faced with the question as to how closely his isarithms should fit the plotted data on which they are based. The fitting of isarithms to plotted data is not, however, simply a matter of understanding the factors that influence a variable and of applying this understanding in a judgment sense. This study examines the relationship between the reliability of plotted data and the degree of precision that should reasonably be exercised in the drawing of isarithrns to fit the data. A simple statistical method is developed for estimating goodness of fit of isarithms and this method is applied for illustrative purposes to the drawing of a map showing mean July temperatures in the state of Kansas.

The effects of different monetary rules on the rates of inflation and unemployment are studied by stochastic simulation of the Federal Reserve Board-MIT-Pennsylvania (FMP) Econometric Model and the St. Louis "Monetarist" Model. A number of heuristic and more formal statistical methods are used in evaluating the results, It is shown that simple feedback control rules--involving proportional and derivative controls--reduce the variability of the target variables relative to the rule in which the money supply is increased at a constant rate. The improvement is considerably greater in the St. Louis model than in the FMP model. [ABSTRACT FROM AUTHOR]

The linking of statistically estimated relationships with an engineering linear programming model offers important potentials for simulation and forecasting models of industries. This article describes such a model of the U.S. petroleum refining industry. Econometric techniques are used to specify product demands, prices, and some technical adjustments. A linear programming specification of the production function, assuming cost minimization, determines crude oil input requirements, the output of by-products, and the utilization of capacity. As applications of the model, a sample period calculation and a five-year forecast are presented along with a discussion of alternative cases and forecast error. [ABSTRACT FROM AUTHOR]

The possibility that some time series that arise in economics hove error or innovation terms that come from infinite variance distributions throws doubt on most of the classical methods of analysis. The evidence in favor of infinite-variance is discussed and a variety of alternative explanations of the long-tailed property of observed distributions examined. Some of these alternative explanations are based on mixtures of distributions and suggest data-transformations that reduce or remove the problem. Clipping of the series seems to be o particularly useful technique and is applied to U.S. Treasury daily cash flow data. [ABSTRACT FROM AUTHOR]

The article presents tables of normal percentile points "P". The U.S. National Bureau of Standards gives two 20 decimal place tables of percentile points of the normal distribution. The central role of the normal distribution in many types of statistical analysis dictates that adequate tables should be readily available. These tables should be sufficient for almost all problems requiring values of the normal distribution function. Interpolation in the National Bureau of Standards tables is time consuming and complicated. Since computers do much statistical computation, the statistical constants used by the computer should be accurate to the length of the computer word. There is no economy in entering, for example, the 97.5 normal percentile point as 1.96 rather than 1.9599640, if the computer word holds 8 decimal digits for IBM 7094, 360, etc. or 1.95996,39845,40054 for a 16 digit word for IBM 360 double precision, CDC 6600, etc. The computations were performed on the University of Minnesota CDC 6600 computer using a double precision program, which carries about 29 significant figures.

The development of a statistically adequate set of construction price indexes is the goal of a research effort recently instituted at the Bureau of the Census. This paper describes research done to date on price indexes for single-family houses and indicates plans for future research. Using data from the Bureau's Housing Sales Survey, indexes of the price of new one-family houses sold (including value of site) have been computed by determining the most important characteristics of these houses and estimating, by regression analysis, the price change in houses with a constant "mix" of these characteristics. [ABSTRACT FROM AUTHOR]

In this study death statistics are used to estimate the United States population 85 years of age and over by a procedure based on Vincent's "method of extinct generations." The resulting estimate is found to be quite similar to the census count for this population in 1950. Such a finding disputes the theory that greater exaggeration of age in the census than on vital records is responsible for distorted death rates for the extreme aged population. Death rates invariably mount with age, and since it seems likely both census and vital records data overstate the age of persons to some degree, an inference that the reported death rates for the population 85 years and over are too low can be made. [ABSTRACT FROM AUTHOR]

Suppose given a set of similarities (or dissimilarities) between pairs of of objects from some set of objects, such as animal species, books, colours. We wish to construct from this similarity matrix a tree, or nested set of clusterings of the objects; graphs of trees provide a striking visual display of similarity groupings of the objects. The construction requires (1) a definition specifying when a similarity matrix has exact tree structure, (2) a measure of distance between any two similarity matrices, which yields (when combined with (1)) a measure of distance between any similarity matrix and any tree, (3) a family of local operations on a tree, which can be used to search out trees which best fit a given similarity matrix. The construction technique is applied to voting behaviour of the 50 United States in the last 13 presidential elections, giving a tree clustering of the states. [ABSTRACT FROM AUTHOR]

This article focuses on the developments in the field of statistics in the U.S. during the 20th century. In many of these developments, members of the American Statistical Association, past and present, were prominent leaders, advisors and active participants. They played important roles in the rise of modern business, government and education; the progress of the sciences; the achivement of rationality in administration and in the professions; the improvement of working and living conditions; and the enhanced productivity of human effort in both manual and intellectual enterprises. During these momentous years, the theory and practice of statistics have been shaped by the kinds of problems our members have encountered in their diverse activities. Today, the growth and evolution of statistics are proceeding more rapidly than ever. Clearly, there is a great demand for more and better statistical information than is now available and for better availability of what does exist. In the face of all these changes: more urgent and more exacting demands for statistics, the introduction of electronic computers and increasing sophistication in their use, mounting concern about the dangers of centralized data files, and other trends of our time, we must remind ourselves that the fundamental obligation of many statisticians remains the day-by-day work of operating existing systems of statistical reporting and of making such improvements as the circumstances permit.

As is well known, the U. S. national accounts contain a "Statistical Discrepancy" which serves to reconcile estimates of GNP from the product and from the income side. While the Discrepancy is a measure only of overall consistency rather than of error, its magnitude and pattern over time (to give some indication of the quality of the nation:d accounts data. In the past, the Statistical Discrepancy has not always behaved as a quantitatively unimportant random error term--a disturbing sign with regard to the GNP statistics. The presence of a systematic Discrepancy also causes difficulties in some specific problems. For example, it is necessary to assume a value for the Discrepancy in the identities of an econometric model when forecasts are made. The Discrepancy can also seriously affect estimates involving those GNP categories, such as savings, which are customarily calculated as residuals with the consequence that the Discrepancy is allocated to them. Earlier studies of the Discrepancy by Gartaganis and Goldberger [3], and by de Janosi [2], have shown: (1) A positive mean value for the Statistical Discrepancy (in the 1929-1959 data, X=$485 million, and sigma=$1,515 million) (2) No significant evidence of non-normality (3) Some evidence of autocorrelation (4) A declining trend in the statistical discrepancy relative to GNP in the most recent data. The purpose of the present note is, first, to see how the Discrepancy has behaved since the completion of this earlier work and, specifically, to examine the Discrepancy in the 1965 revision of the United States national accounts statistics. Secondly, we will study the movement of the Discrepancy with respect to GNP and with respect to the main components of the national accounts. [ABSTRACT FROM AUTHOR]

The article comments on the report of 1965 of board of directors of American Statistical Association. The report mentioned in the article covers highlights of a few of the Association's Committees which have been busy on various aspects of Association activities. The work of the Committee on Chapter, District and Regional Activities and the Special Committee on Plans and Progress are covered under Future Needs and Projects. The Committee on Membership works very closely with the national office on follow-ups to unpaid members, using the good offices of District Representatives and chapter officers, to attempt to reduce the number of persons who are dropped each year for non-payment of dues. In addition, the Subcommittee on Corporate Membership will begin an intensive campaign to increase the number of organizations on the corporate member list. During 1965 the American Farm Economic Association and the American Statistical Association appointed a joint Advisory Committee to the U.S. Department of Agriculture.

Data are available to study the variation in mortality in this country occurring month by month for fully six decades. Death rates by month have been computed and published for the expanding death-registration area of the United States of 1900-1932 and for the complete nation (48 States and ultimately 50 States) from 1933 to the present. Even a cursory glance at the available data leads to the obvious conclusion that a definite pattern of seasonal variation of deaths exists. This seasonal swing is characterized by a high death rate in the early part of the year dropping to a trough in the summer months, and rising again during the latter part of the year. The general pattern is well recognized, as are similar seasonal curves for various causes of death. Despite the apparent wealth of statistical material at hand relatively little analytical matter has been produced in this country measuring seasonality of mortality as compared with the wide range of data compiled for statistical series portraying the nation's economic operations. Yet seasonal variation is receiving increasing attention in the evaluation of statistics of vital events. The very factors which make seasonal indices so valuable to economists and analysts also have proved to be of service to demographers and public health researchers. Seasonal adjustments provide refined information about current trends; they separate the seasonal components of statistical data from cyclical and irregular fluctuations; they provide indices with which to measure the significance of month to month change. Seasonal variation in the crude birth rate has been analyzed for the period 1933-40 using the link relative method [1]. Seasonal indices for 1948-54 were prepared with the aid of Univac, the high-speed electronic computer of the United States Bureau of the Census, using an adaptation of the standard ratio to moving average method [2]. The indices prepared by the Bureau of the Census became the basis for the regular computation of seasonally adjusted figures of births by the National Vital Statistics Division, U. S. Public Health Service 131. Similarly, marriage data published by the National Vital Statistics Division have been "deseasonalized" with the aid of methods developed by the Bureau of the Census [4]. This paper presents the results of an effort made with the assistance of Univac to eliminate seasonal variation from mortality data. Some of the particular problems encountered in adjusting mortality data, and the attempts to surmount these are described. [ABSTRACT FROM AUTHOR]

The article comments on a report presented by the auditors of American Statistical Association. The auditors have examined the balance sheet of the American Statistical Association, a non-profit organization, as of December 31, 1965, and the related statements of income and expense, and association equity for the year then ended. The examination was made in accordance with generally accepted auditing standards, and accordingly included such tests of the accounting records and such other auditing procedures. The auditors made a similar examination for the preceding year. The accompanying balance sheet and statements of income and expense, and association equity present fairly the financial position of the American Statistical Association at December 31, 1965, and the results of its operations for the year then ended, in conformity with generally accepted accounting principles applied on a basis consistent with that of the preceding year. The examination of American Statistical Association for the year ended December 31, 1965, was made primarily for the purpose of formulating an overall opinion on the Association's balance sheet at December 31, 1965, and its statements of income and expense and association equity for the year then ended.

The article presents summaries of papers delivered at the 125th annual meeting of the American Statistical Association. The meeting took place on September 1965 in Philadelphia, Pennsylvania. In the paper "On the Construction of Stochastic Working Life Tables," by Haskel Benishay, stochastic working life tables are constructed and evaluated. The essence of the construction of stochastic rather than the traditionally deterministic working life tables is in the utilization of the realistic assumptions that the number of births, the number of entries into the labor force, the duration of life, and the duration of working life, are random variables. The end result is a working life table with a double entry in each cell rather than the single traditional one. The implications of this approach for the evaluation of fluctuations in various subcomponents of the labor force are evaluated. Another paper "Measuring Elasticities of Air Travel," by Samuel L. Brown, summarizes research on the response of demand for air travel to differences of fares, incomes, and elapsed travel time. There are three kinds of studies. Multiple regression studies of time series of air traffic, fares and income in the national domestic market yield short-period fare elasticities and income-elasticities. A quarterly first-difference model stands well the usual statistical tests.

This section presents the text of a presidential address given by W. Allen Wallis at the 125th annual meeting of the American Statistical Association in Philadelphia, Pennsylvania on September 9, 1965. The American Statistical Association is the second oldest national learned society, the American Philosophical Society being the oldest. Statistics is somehow still regarded by some as a new and youthful subject; or to put it another way, as a perpetually immature and adolescent subject, one which is by now perhaps beyond hope of ever maturing. The lack of widespread esteem for statistics is explained by an inherent characteristic of the subject. Pure statistics is a realm of ideas, like philosophy. Statistics makes important contribution to defense, economy, to health, to social organization, to science and scholarship, and to the government. But in these applications, statistics is always secondary. The complaint that statistics is never the popular is not unlike the complaint that a lineman on a football team rarely scores any points. When the statistician does something outstanding of a practical nature that captures attention and admiration, his specific contribution is not dramatic and probably not individually distinguishable.

The article presents information about Samuel S. Wilks, a great contributor to statistics. Wilks' behavior toward applications was peculiarly split, he encouraged his students to work on applications, not always an easy thing to do in a strongly theoretical mathematics department; he often told students about applications that he regarded as "neat" or "cute" or "clever"; the statistical colloquium he guided often had speakers on practical applications of mathematical statistics; he himself wrote some practical papers in statistics, but in the classroom he rarely discussed applications. Repeatedly, however, practical problems explicitly influenced both his own publications and those of his students and Wilks often used applications as motivation for the discussion of distribution theory, usually going well beyond the needs of the original problem. The papers to be discussed exhibit incompletely and fragmentarily a major influence on the work of the man and his students. Wilks watched the development of the statistical theory of order statistics closely. Indeed he wrote a masterful summary of the literature. The general area involves the study of the statistical properties of ordered measurements.

In a previous paper [12], an attempt was made to show how spectral techniques could be used to compare the effects of two seasonal adjustment procedures on the series to which they were applied. The two procedures compared were: (a) the technique currently used by the Bureau of Labor Statistics for seasonally adjusting employment, unemployment, and labor force monthly statistics, and (b) the so-called "residual" method, proposed by Brittain [2], Samuelson [16], and others. Spectra of the original and the seasonally adjusted series and the cross spectrum of the two were used to aid in the assessment of whether either procedure removed more than could be considered seasonal, introduced spurious regularities, and/or distorted temporal relationships. It was concluded that both techniques removed more than seasonal effects from, and produced some temporal distortion in, the series to which they were applied. Neither method appeared to be superior to the other. It is the purpose of this paper to carry the previous analysis one step further and to compare the BLS procedure with a modified version of the regression method of seasonal adjustment suggested by Cowden [3] and Mendershausen [11], and recently revived by Harman [9, 10] in an exceptionally sophisticated form. In addition to Hannan's work along the lines suggested, Nettheim [13] and Rosenblatt [15] have made studies. Rosenblatt [15] has carried out analyses similar to those reported here. [ABSTRACT FROM AUTHOR]

Regression upon principal components of the percentage points of the income and education distributions for 1950 census tracts in the city of Chicago led to the estimation of "beta coefficient profiles" for television receiver and refrigerator ownership, for central heating system usage, and for a measure of dwelling unit overcrowding. The betas are standardized coefficients of regression of a dependent variable upon the proportions of families in the classes of the marginal income and education distributions. They measure the relative contribution of families in these classes to the over-all per cent saturation of the dependent variable in the tract. The coefficients were estimated by techniques developed in the first portion of the paper; estimation by classical regression methods would have been impossible because of multicollinearity. The empirical results are in substantial agreement with findings from regressions of the dependent variables upon the mean values of income and education, and their squares. The statistical devices appear to be useful in exploratory empirical research. [ABSTRACT FROM AUTHOR]

This article focuses on the empirical research on U.S. legal institutions. The central problem of such studies is not the repetition of the canons of ideal procedures, but the development of what one might call canons of prudence, concerning the proper limits of compromise and the proper modes of inference from imperfect data. In the main it reproduces the criticism the authors has imposed on themselves, merely emphasizing their different amount of concern. In the several instances where they have gone beyond criticism, they are not always persuasive. To be sure, they have taken their chances and have analyzed the unique data to their limits. Some critics, such as the present ones, felt these limits were set too generously, and perhaps they were. But progress in their knowledge cannot come from reemphasis of their own disclosures of imperfection and from a citation of the canons for perfect data. Their was a study of a large and unknown territory. Somewhat romantically seen, it was not unlike a first expedition to the bottom of the sea.