1. |
Statisticians and Shoemakers (“Who is Worse Shod than the Shoemaker's Wife,” from Heywood's Proverbs.) |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 9-21
A.Ross Eckler,
Preview
|
PDF (919KB)
|
|
摘要:
Statistical data have become increasingly important with the past 20 years showing rapid growth in several areas, particularly in the production of general-purpose statistics. Despite these advances, the author contends that statisticians have largely failed to apply their skills to measuring demand for, and supply of, statistical data. Recommendations are offered for reducing this neglect and encouraging a new comprehensive treatment of the subject.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481058
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
2. |
Some Effects of Errors of Measurement on Multiple Correlation |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 22-34
W.G. Cochran,
Preview
|
PDF (788KB)
|
|
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481059
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
3. |
Collegiate Football Scores, U.S.A. |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 35-48
Frederick Mosteller,
Preview
|
PDF (661KB)
|
|
摘要:
In collegiate football, ties are now rare, only two percent of the games ending this way in 1967, the highest scoring tie being 37–37. Ties happen less than half as often as one-point differences. The most frequent outcome of a game was 14–7, although the most frequent winning score was 21 and the most frequent losing score was 0. The average winning score was 27, the average losing score, 10. A team score of 11 has a 25 percent chance of being a winning score, a score of 16 a 50 percent chance, a score of 23 a 75 percent chance and a score of 40 is practically certain to win, based on a freehand curve. Scores of 3, 9, 10 are more favorable to winning than their size would suggest, while 18 and 22 are less favorable than theirs suggests. Indeed, a score of 9 is more likely to win than is a score of 15, and nearly as likely as a score of 18.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481060
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
4. |
An Experimental Comparison between Fixed Weight and Linear Programming Food Price Indexes |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 49-60
JosephL. Balintfy,
John Neter,
William Wasserman,
Preview
|
PDF (754KB)
|
|
摘要:
A linear programming food price index permits the possibility of routine substitutions in response to price changes, while a fixed weight index does not. This paper cites a variety of evidence indicating that consumers do trade off among foods in response to both long-term and seasonal price changes. Implications of this for food price indexes are discussed. A linear programming food price index is then developed, based on an empirical menu-planning model, and compared with corresponding fixed weight price indexes over a nine-month period. The linear programming index shows a significantly smaller increase in food prices over the nine-month period than the fixed weight index with initial period weights.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481061
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
5. |
The Multiple Uses of Primary Sampling Areas of National Probability Samples |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 61-70
Seymour Sudman,
Preview
|
PDF (508KB)
|
|
摘要:
This article discusses the use of existing samples of primary sampling areas for special subpopulations. Existing samples are shown to be more efficient in most cases because the costs of developing new field organizations are large relative to the reductions in sampling variance obtained in the new sample. Procedures are specified for modifying an existing sample if there are too few PSU's or if the PSU's are too small.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481062
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
6. |
Ideal Multiple-choice Items |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 71-89
R.A. Weitzman,
Preview
|
PDF (1033KB)
|
|
摘要:
A multiple-choice item is called ideal if all its alternatives are equally attractive to every person who cannot answer the item correctly without guessing. This paper discusses reasons for attempting to construct ideal items, develops methods for testing whether items are ideal or at least more nearly ideal than other items, and presents examples of both ideal and nonideal items.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481063
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
7. |
Forecasting Daily Hog Prices and Quantities: A Study of Alternative Forecasting Techniques |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 90-107
R.M. Leuthold,
A.J. A. Maccormick,
A. Schmitz,
D.G. Watts,
Preview
|
PDF (893KB)
|
|
摘要:
Relatively few investigations treat the problem of short-run or daily price and quantity variations. This study concerns forecasting daily hog prices and quantities in selected terminal markets in the U. S. by using various causal and noncausal models. The purpose is to examine the economic and mathematical characteristics of the time series data, and then compare the developed models in terms of their forecasting ability. The performance of each model is evaluated using the Theil coefficient.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481064
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
8. |
Discriminatory Bias in Rates Charged by the Canadian Automobile Insurance Industry |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 108-122
R.A. Holmes,
Preview
|
PDF (653KB)
|
|
摘要:
Automobile insurance rates in Canada are promulgated by the Canadian Underwriters' Association (the C.U.A.) and all member companies are bound to adhere to them. Other rate schedules are set out by the Independent Automobile Insurers' Conference and by the Independents, but these usually conform very closely to the C.U.A. rates, so that the C.U.A. rate manual actually provides the basis for all automobile insurance premiums in Canada [2]. Consequently, the question of whether the C.U.A. rate-making procedure yields premiums which accurately reflect risks is interesting. In this study, the determining features of the C.U.A. approach are applied to situations in which risks are known. Comparison of C.U.A. rates with actual risks then yields an assessment of the validity of the C.U.A. procedure.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481065
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
9. |
A Problem in Integration of Surveys—A Case Study |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 123-135
M.N. Murthy,
A.S. Roy,
Preview
|
PDF (881KB)
|
|
摘要:
Integration of surveys is usually achieved by having acommon sample ofultimate units or at least penultimate-stage units for different subjects. However, if the ultimate units relevant for a subject are unevenly spread over the region, they may not be adequately caught through a common general purpose sample. Such a situation did arise while planning for the 23rd round (July 1968–June 1969) of the Indian National Sample Survey owing to the inclusion of an enquiry on small-scale manufacturing establishments in this round. The modifications introduced to orient the common design toward this enquiry are discussed in this article.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481066
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
10. |
A Model of the Distribution of Federal Expenditures among States |
|
Journal of the American Statistical Association,
Volume 65,
Issue 329,
1970,
Page 136-149
MawLin Lee,
Preview
|
PDF (822KB)
|
|
摘要:
This study explores factors associated with the allocation of federal expenditures by states and examines the relation of the level of these expenditures to the level of income of each state. The allocation of federal expenditures is functionally oriented toward the objectives for which various government programs are established. The geographical distribution of federal expenditures, therefore, historically was considered to be a problem incidental to government activity. Because of this, relatively little attention has been given to the question of why some states receive more federal funds than others.1In addition, the implications of the pattern of allocation on income distribution among states have not been investigated intensively.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481067
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|