USING DUMMY VARIABLES TO CHECK FOR ROUNDING ERROR IN COMPUTERIZED REGRESSION PROGRAMS*

After a brief review of the role of dummy variables in regression analysis and the current state-of-the art in rounding/truncation error detection in computerized least squares programs, this paper presents a theorem that can be used to detect this type of error whenever an analyst is running a regression program that has one (or more) dummy variables as independent variables.     

Feelings About Fracking: Using the Affect Heuristic to Understand Opposition to Coal Seam Gas Production

The rapid expansion of coal seam gas (CSG) extraction across Australia has polarized public opinion about the risks, benefits, and the future of the industry. We conducted a randomized controlled experiment to assess the impact of CSG messaging on opposition to the CSG industry. Residents of a major Australian city (N = 549), aged between 21 and 87 years, were randomly assigned to view one of three brief video messages (pro‐CSG, anti‐CSG, or a neutral control) sourced from the Internet. They then completed measures assessing CSG affective associations, perceived risks and benefits of CSG, and degree of opposition to the CSG industry. A subsample of 317 participants also completed the measures of affect, risks, benefits, and opposition two weeks following the initial message presentation. Message type significantly predicted message effects in a pattern consistent with the affect heuristic model, although overall, the message effects were modest in magnitude. Respondents who viewed the anti‐CSG video (relative to the control) reported more negative affective responses to CSG, perceived higher risks, fewer benefits, and greater opposition to the CSG industry. Those who viewed the pro‐CSG video (relative to the control) reported stronger positive affective responses to CSG, perceived more CSG benefits and fewer risks, and expressed less opposition to the industry. The effects persisted over a two‐week interval for the anti‐CSG message, but not for the pro‐CSG message. Our findings suggest that people's risk perceptions and views about the acceptability of CSG are malleable by messaging that targets affective pathways.     

Altruistic and Private Values For Saving Lives With an Oyster Consumption Safety Program

We use data from an Internet-based survey and estimate the benefits of an oyster consumption safety policy with the contingent valuation method. In addition to providing a context-specific estimate of willingness-to-pay for oyster safety, we consider an important issue in the contingent valuation mortality risk reduction literature. A number of studies find that willingness-to-pay for mortality risk reduction is not sensitive to the scope of the risk change. We present the scope test as a difference in the number of lives saved by the program, instead of small changes in risk, and find that referendum votes are responsive to scope. A third feature of this article is that we identify those at-risk respondents who would most benefit from the policy and decompose willingness-to-pay into use values and altruistic nonuse values. We find that willingness-to-pay per life saved ranges from $3.95 million to $7.69 million for the private good of lives saved when the respondent is at risk (i.e., use values). Willingness-to-pay per life saved including both use and altruistic nonuse values ranges from $6.89 million to $12.87 million.     

The economic fallout from divorce: Issues for the 1990s

Economic consequences of divorce, especially for women, are negative and persistent according to a range of research studies. The question is whether, given changing social circumstances, this negative economic fallout from divorce is likely to diminish in the 1990s and beyond. Dramatic changes suggest both reasons for optimism and pessimism. On the positive side are the trends toward more continuous labor force participation among women and smaller contemporary family sizes. Negative influences include changes in the labor market for women, continuing problems with child support compliance, the persistence of the wage gap, and the difficulties of combining parenting and employment.The writing of this paper was supported in part by National Institute on Aging grants AG04895 and AG06591. We are grateful to Marina Adler, Sharon Price, Mara Skruch and Lynn White for their helpful comments on an earlier draft of this paper.(Ph.D., University of Southern California) conducts research on divorce, widowhood, older women's issues, and family support in later life families.(Ph.D., University of North Carolina, Chapel Hill) focuses her research on divorce, bereavement, and the impact of life events on adjustment.(Ph.D., Case Western Reserve University) studies economic trends in U.S. society.     

Modelling age variation in survival and reporting rates for recovery models

In this paper, we focus on models for recovery data from birds ringed as young. In some cases, it is important to be able to include in these models a degree of age variation in the reporting probability. For certain models this has been found, empirically, to result in completely flat likelihood surfaces, due to parameter redundancy. These models cannot then be fitted to the data, to produce unique parameter estimates. However, empirical evidence also exists that other models with such age variation can be fitted to data by maximum likelihood. Using the approach of Catchpole and Morgan (1996b), we can now identify which models in this area are parameter-redundant, and which are not. Models which are not parameter-redundant may still perform poorly in practice, and this is investigated through examples, involving both real and simulated data. The Akaike Information Criterion is found to select inappropriate models in a number of instances. The paper ends with guidelines for fitting models to data from birds ringed as young, when age dependence is expected in the reporting probability.     

A Comparison of the Cost-efficiencies of the Sequential, Group-sequential, and Variable-sample-size-sequential Probability Ratio Tests

Wald and Wolfowitz (1948) have shown that the Sequential Probability Ratio Test (SPRT) for deciding between two simple hypotheses is, under very restrictive conditions, optimal in three attractive senses. First, it can be a Bayes-optimal rule. Second, of all level α tests having the same power, the test with the smallest joint-expected number of observations is the SPRT, where this expectation is taken jointly with respect to both data and prior over the two hypotheses. Third, the level α test needing the fewest conditional-expected number of observat ions is the SPRT, where this expectation is now taken with respect to the data conditional on either hypothesis being true. Principal among the strong restrictions is that sampling can proceed only in a one-at-a-time manner. In this paper, we relax some of the conditions and show that there are sequential procedures that strictly dominate the SPRT in all three senses. We conclude that the third type of optimality occurs rarely and that decision-makers are better served by looking for sequential procedures that possess the first two types of optimality. By relaxing the one-at-a-time sampling restriction, we obtain optimal (in the first two senses) variable-s ample-size- sequential probability ratio tests.     

Racial differences in marriage and childbearing: oral history evidence from the South in the early twentieth century

Using oral histories collected in 1938 and 1939 in the Southern United States, this article examines how African-Americans and whites viewed marriage and nonmarital childbearing. The authors document distinct racial differences in family norms and the sanctions that supported those norms. Giving birth outside a marital relationship was clearly not the stigmatizing event for African-Americans that it was for whites. The authors also found that African-Americans were more likely than whites to end marriages under similar conditions. These results suggest that debates about contemporary racial differences need to take into account the historical background, both cultural and demographic, of diverse groups.     

Emancipation studies: The demise of slavery in Pennsylvania and New York

Freedom By Degrees: Emancipation in Pennsylvania and Its Aftermath. By GARY B. NASH and JEAN R. SODERLUND. New York and Oxford: Oxford University Press, 1991. xvi, 249 pp. £20.

Somewhat More Independent: The End of Slavery in New YorkCity, 1770–1810. By SHANE WHITE. Athens, Ga. and London: University of Georgia Press, 1991. xviii, 278 pp. $35.     

Multiplicity: discussion points from the Statisticians in the Pharmaceutical Industry multiplicity expert group

In May 2012, the Committee of Health and Medicinal Products issued a concept paper on the need to review the points to consider document on multiplicity issues in clinical trials. In preparation for the release of the updated guidance document, Statisticians in the Pharmaceutical Industry held a one‐day expert group meeting in January 2013. Topics debated included multiplicity and the drug development process, the usefulness and limitations of newly developed strategies to deal with multiplicity, multiplicity issues arising from interim decisions and multiregional development, and the need for simultaneous confidence intervals (CIs) corresponding to multiple test procedures. A clear message from the meeting was that multiplicity adjustments need to be considered when the intention is to make a formal statement about efficacy or safety based on hypothesis tests. Statisticians have a key role when designing studies to assess what adjustment really means in the context of the research being conducted. More thought during the planning phase needs to be given to multiplicity adjustments for secondary endpoints given these are increasing in importance in differentiating products in the market place. No consensus was reached on the role of simultaneous CIs in the context of superiority trials. It was argued that unadjusted intervals should be employed as the primary purpose of the intervals is estimation, while the purpose of hypothesis testing is to formally establish an effect. The opposing view was that CIs should correspond to the test decision whenever possible. Copyright © 2013 John Wiley & Sons, Ltd.     

A Solar-Centric Approach to Improving Estimates of Exposure Processes for Coronal Mass Ejections

We present a solar-centric approach to estimating the probability of extreme coronal mass ejections (CME) using the Solar and Heliospheric Observatory (SOHO)/Large Angle and Spectrometric Coronagraph Experiment (LASCO) CME Catalog observations updated through May 2018 and an updated list of near-Earth interplanetary coronal mass ejections (ICME). We examine robust statistical approaches to the estimation of extreme events. We then assume a variety of time-independent distributions fitting, and then comparing, the different probability distributions to the relevant regions of the cumulative distributions of the observed CME speeds. Using these results, we then obtain the probability that the velocity of a CME exceeds a particular threshold by extrapolation. We conclude that about 1.72% of the CMEs recorded with SOHO LASCO arrive at the Earth over the time both data sets overlap (November 1996 to September 2017). Then, assuming that 1.72% of all CMEs pass the Earth, we can obtain a first-order estimate of the probability of an extreme space weather event on Earth. To estimate the probability over the next decade of a CME, we fit a Poisson distribution to the complementary cumulative distribution function. We inferred a decadal probability of between 0.01 and 0.09 for an event of at least the size of the large 2012 event, and a probability between 0.0002 and 0.016 for the size of the 1859 Carrington event.