1. |
On the Appropriateness of the Correlation Coefficient with a 0, 1 Dependent Variable |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 501-509
John Neter,
E.Scott Maynes,
Preview
|
PDF (518KB)
|
|
摘要:
This article deals with the use and misuse of the correlation coefficient when the dependent variable is of a dichotomous 0,1 nature. It focuses particularly on problems relating to curvilinearity and the nature of the prediction being made. The prediction of consumer purchases from reported subjective probabilities provides a vehicle for illustrating problems discussed.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481099
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
2. |
A Reevaluation of the Predictive Ability of Plant and Equipment Anticipations |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 510-519
Irwin Friend,
William Thomas,
Preview
|
PDF (640KB)
|
|
摘要:
This article suggests that anticipations alone do a better job of forecasting business plant and equipment expenditures than fitted functions which include only non-anticipatory data. Anticipations can also make a significant contribution in the presence of such data. Since previously published studies have come to different conclusions, the focus of this article is an evaluation of the methodology and results of those studies.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481100
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
3. |
Forecasting Specific Turning Points |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 520-531
Richard Long,
Preview
|
PDF (743KB)
|
|
摘要:
The trade-off between accuracy of the call of a specific turn and the recognition lag is calculated for 17 monthly series from the NBER short list of indicators based on smoothing by Months of Cyclical Dominance (MCD), Average Duration of Run (ADR), and Declining Weights (DW). With a two-month recognition lag and only 1/3 of calls correct, both MCD and DW outperformed ADR. MCD was relatively better for smooth and ADR for irregular series. With each series smoothed to obtain 50 percent likelihood changes are cyclical, the typical leading series led reference peaks by seven months but showed no lead at troughs.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481101
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
4. |
Measuring the Value of Housing Quality |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 532-548
JohnF. Kain,
JohnM. Quigley,
Preview
|
PDF (1053KB)
|
|
摘要:
Based on an extensive sample of individual dwelling units, this article estimates the market value, or the implicit prices, of specific aspects of the bundles of residential services consumed by urban households. Quantitative estimates were obtained by regressing market price of owner- and renter-occupied dwelling units on measures of the qualitative and quantitative dimensions of the housing bundle. The measures of residential quality associated with individual dwelling units were obtained by using factor analysis to aggregate some 39 indexes of the quality of narrowly defined aspects of the dwelling units, structures, parcels, and micro-neighborhoods.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481102
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
5. |
A Report on the Accuracy of Some Widely Used Least Squares Computer Programs |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 549-565
RoyH. Wampler,
Preview
|
PDF (1127KB)
|
|
摘要:
Linear least squares test problems based on fifth degree polynomials have been run on more than twenty different computer programs in order to assess their numerical accuracy. The programs tested, all in present-day use, included representatives from several statistical packages as well as some from the SHARE library. Essentially five different algorithms were used in the various programs to obtain the coefficients of the least squares fits. The tests were run on several different computers, in double precision as well as single precision. By comparing the coefficients reported, it was found that those programs using orthogonal Householder transformations, classical Gram-Schmidt orthonormalization or modified Gram-Schmidt orthogonalization were generally much more accurate than those using elimination algorithms. Programs using orthogonal polynomials (suitable only for polynomial fits) also proved to be superior to those using elimination algorithms. The most successful programs accumulated inner products in double precisionand made use of iterative refinement procedures.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481103
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
6. |
Response Error and Questioning Technique in Surveys of Earnings Information |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 566-575
MichaelE. Borus,
Preview
|
PDF (678KB)
|
|
摘要:
This article compares two questioning techniques for securing earnings information. Two broad earnings questions and detailed work history information were asked of 300 residents of low income neighborhoods. Systematic differences, based on the level of earnings, the age and the number of jobs of the respondents, were found between the estimates from the two techniques.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481104
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
7. |
Distributional Effects in Demand Analysis: Observations and Predictive Tests |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 576-585
D.J. Laughhunn,
Preview
|
PDF (603KB)
|
|
摘要:
Most previous empirical demand analyses using time series data have ignored the possible demand effect due to temporal variation in the population's demographic structure. Following an earlier study by Lippitt, this demand effect is denoted as a distributional effect. This article summarizes results of predictive tests designed to isolate the contribution to predictive accuracy attributable to the distributional effect. Nine expenditure categories are included in the predictive tests. With the exception of two expenditure categories (house operation and house furnishing), the distributional effect was not found to contribute to predictive accuracy.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481105
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
8. |
Estimation of Dynamic Demand Relations from a Time Series of Family Budget Data |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 586-597
Feng-Yao Lee,
Preview
|
PDF (824KB)
|
|
摘要:
The demand parameters are estimated by fitting dynamic and static equations to a time series of Japanese multi-cross-section data using various methods. The results indicate that habit formation is predominant and income is much more important than prices and that it is worthwhile to use dynamic forms.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481106
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
9. |
Coefficient of Interarea Variation as a Measure of Spatial Income Inequality |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 598-601
BarbaraB. Murray,
Preview
|
PDF (198KB)
|
|
摘要:
“How large would an areal grouping of political units have to become in order to reduce substantially the income fragmentation associated with the political fragmentation of the large metropolitan areas?” Generally the county is the size short of metropolitan status that provides a substantial reduction in the existing interarea variations in income.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481107
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|
10. |
A Quantitative Measure of the Risk Factor in Investment Decisions |
|
Journal of the American Statistical Association,
Volume 65,
Issue 330,
1970,
Page 602-612
T.M. Hammonds,
D.I. Padberg,
Preview
|
PDF (564KB)
|
|
摘要:
Investment theory has traditionally divided risk into two parts: (1) the risk of business failure and (2) the uncertainty associated with cash flow prediction. Analysis then proceeds to disregard attrition as a variable and to focus on cash flow forecasting. Though high attrition may be typical in the pattern of industry growth, it is certainly an attribute of structural development that has not been investigated extensively. This article explores the character of attrition and develops an analytical device that may be used to adjust separately estimated cash flows for the risk of failure.
ISSN:0162-1459
DOI:10.1080/01621459.1970.10481108
出版商:Taylor & Francis Group
年代:1970
数据来源: Taylor
|