ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482085

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

The test, proposed by Moore and Wallis [23], of the existence of correlation between the movements in two time series (eliminating at least the primary effects of trends) was justified by them in “the special case of randomly arranged [signs of the] first differences” in both series. Moore and Wallis also noted that the signs of the first differences in a time series will have a negative serial correlation if the time series is a purely random process (or if it is a particular kind of generalization of a purely random process). It is therefore necessary to modify the Moore-Wallis test when applying it to such time series in order to take into account this serial correlation. In the present article, a simple modified form of the Moore-Wallis test is suggested, which can be applied to such time series. Somewhat similar modifications are also suggested for testing the existence of correlation between some more general kinds of time series. The importance of taking into account the effects of trends in the time series and the effects of the serial correlations (between the signs of the first differences) is illustrated by means of two numerical examples. Finally, the study of the movements in three or more time series is briefly discussed.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482086

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

The Consumer Price Index of the Bureau of Labor Statistics is subject to a variety of seasonal influences, some of which are related to supply and some to demand factors. Recent calculations of seasonal indexes for the CPI and its major components reveal that there is little seasonality in the index as a whole, although some items show seasonal price movements of considerable magnitude.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482087

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

A procedure for combining averages, each estimating the same parameter, is proposed. If the averages arise from a multivariate normal sample, the procedure yields the maximum likelihood estimate of the parameter. It is shown that providing the number of vector observations is greater than the number of averages being combined, exact confidence intervals can be obtained based either on Student's “t” distribution or a related distribution (unfortunately not tabulated). If the averages arise from unequal sized samples on independent normal distributions with unequal variances, similar results hold subsequent to random matching and data transformation providing the minimum sample size is greater than the number of averages being combined. In both cases, the proposed estimate is almost linearly optimum in the sense that it has variance equal to that of the minimum variance linear unbiased estimate of the parameter except for a multiplicative factor which approaches unity as all sample sizes become large.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482088

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

In the first half of each intercensal decade in the thirty-year period 1925 to 1955, the age-adjusted death rates for nonwhite persons have declined relatively more rapidly than for white persons. In the second half of each intercensal decade just the opposite situation prevails, an excess of white over nonwhite decline. There are no exceptions to this curious pattern for either males or females in this period. Partial explanation of this phenomenon is suggested in terms of increasing underestimates of the nonwhite relative to the white population in the two intercensal periods 1930–40 and 1940–50.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482089

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

Methods for constructing simultaneous confidence intervals for all possible linear contrasts among several means of normally distributed variables have been given by Scheffé and Tukey. In this paper the possibility is considered of picking in advance a number (saym) of linear contrasts amongkmeans, and then estimating thesemlinear contrasts by confidence intervals based on a Studenttstatistic, in such a way that the overall confidence level for themintervals is greater than or equal to a preassigned value. It is found that for some values ofk, and formnot too large, intervals obtained in this way are shorter than those using theFdistribution or the Studentized range. When this is so, the experimenter may be willing to select the linear combinations in advance which he wishes to estimate in order to havemshorter intervals instead of an infinite number of longer intervals.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482090

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

Some economists have applied multiple regression analysis to national aggregate time series data to measure elasticities of demand for all food marketing services. This paper demonstrates the inappropriateness of the measures of marketing services price, quantity and value used in the analyses. The services price index used was actually a services value index; the services quantity index used was an index of food quantity; and the measure of value used contained errors of observation of such a nature as to lead to biased elasticity estimates. Finally, formulas are suggested which might be used for the construction of a Laspeyre's index of services prices and a Paasche index of quantity of services.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482091

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482092

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

Counts of “Persons of Spanish Surname” in the Southwestern United States were made by the U. S. Census in 1950 and are planned for 1960. Similar counts from other records can furnish numerators to go with denominators from the Census, but difficulties arise in explicit listing and definition of “Spanish Surname”. The problem was here approached from name counts of maiden surnames of mothers of infants with Spanish surnames. A log-normal distribution, fitted to this listing, allowed estimation of the number of names required for explicit listings having various proportions of coverage of all Spanish surnames. Since very long lists are required for high per cents of coverage, a 306-name list, with seventy per cent coverage, of a California population, is proposed for both Census and administrative use. Such a list would generate accurate rates for that portion of the population covered, even though the per cents covered might vary.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482093

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor

摘要:

Individual value of residuals from a least squares regression equation can be analyzed as a set of originally observed quantities. If the analysis of residuals is in the form of another regression analysis, the total analysis of the data can be described as a two-stage regression. Such a two-stage approach is not equivalent to the usual, one-stage analysis, and therefore the resulting estimates and tests are biased. It is the purpose of this paper to obtain expressions for these biases.

ISSN:0162-1459    

DOI:10.1080/01621459.1961.10482094

出版商:Taylor & Francis Group    

年代:1961

数据来源: Taylor