John J. Wiorkowski

Auditory evoked responses in control subjects and in patients with problem-tinnitus.

Auditory brainstem responses (ABRs) and middle latency responses (MLRs) recorded from problem-tinnitus patients were compared with responses from normal hearing, hearing loss, and elderly subjects. Ten stimulus frequencies were presented in counterbalanced sequence and all frequencies were presented before any given frequency was presented again. The variables of importance were problem-tinnitus, hearing loss, subject age and stimulus frequency. Repeated measures analysis of variance showed a significant difference only in the latency of ABR wave 7. The intrinsically high variability in the problem-tinnitus and elderly groups rendered standard statistical analyses ineffective with the sample sizes used. Alternative analyses were employed in which the MLR waves of the normal hearing subjects were taken as the standard against which the other groups were compared. Very large MLR waves occurred in some, but not all, of the subjects in the problem-tinnitus and elderly groups. Different MLR waves were large in different subjects without correspondingly large ABR potentials. These results suggest: (1) selective alteration of MLR generators in different forms of tinnitus; and (2) differing effects of age on auditory physiology. Stimulus frequency and hearing loss contributed to this multivariate picture. Another variable, the average sound pressure level of the long-term acoustic environment, may also be important.

Capture-Recapture Sampling for Estimating Software Error Content

Mills capture-recapture sampling method allows the estimation of the number of errors in a program by randomly inserting known errors and then testing the program for both inserted and indigenous errors. This correspondence shows how correct confidence limits and maximum likelihood estimates can be obtained from the test results. Both fixed sample size testing and sequential testing are considered.

Estimating Volumes of Remaining Fossil Fuel Resources: A Critical Review

Abstract A number of problems arise in applying standard statistical techniques to the estimation of remaining volumes of crude oil and natural gas resources. This article reviews and criticizes past approaches, which include methods based on geology and methods that are primarily statistical in nature. Two newer approaches to the problem are described and their results summarized. It is clear that more statistical work is needed in this area.

The use of time series analysis and intervention analysis to assess the effects of external factors on traffic indices: A case study of the effects of the speed limit reduction and energy crisis in the state of Texas

The analysis of time series data expoused by G.E.P. Box and G.M. Jenkins is introduced and motivated within the context of time series data collected on traffic indices. Simple models for a set of six traffic indices collected for the State of Texas are developed. During the time period spanned by these series two significant events occurred. A fuel shortage was experienced in the months of February and March 1974 and in February of 1974 the maximum speed limit on all roads in the state was lowered to 55 miles per hour. Using the methods of intervention analysis developed by G.E.P. Box and G. Tiao, the magnitude of the effects of these two factors on the traffic indices in the state were assessed. It is shown that the combined effect of the fuel shortage and the speed limit reduction induced significant shifts in the course of the traffic series and that the effects of the speed limit reduction have persisted but are diminishing over time.

Toward models for probabilistic program correctness

Program testing remains the major way in which program designers convince themselves of the validity of their programs. Software reliability measures based on hardware reliability concepts have been proposed, but adequate models of software reliability have not yet been developed. Investigators have recently studied formal program testing concepts, with promising results, but have not seriously considered quantitative measures of the “degree of correctness” of a program. We present models for determining, via testing, such probabilistic measures of program correctness as the probability that a program will run correctly on randomly chosen input data, confidence intervals on the number of errors remaining in a program, and the probability that the program has been completely tested. We also introduce a procedure for enhancing correctness estimates by quantifying the error reducing performance of the methods used to develop and debug a program.

Local asymptotic normality for multivariate nonlinear AR processes

In this paper, we establish local asymptotic normality (LAN) for the log-likelihood ratio of a class of multivariate nonlinear autoregressive processes generated by independent identically distributed (i.i.d.) random vectors. This result generalizes LAN for multivariate linear processes to multivariate nonlinear autoregressive processes.

Estimating the correctness of computer programs

Abstract Program testing will for some time remain the major means by which program designers convince themselves and others of the correctness or validity of their programs. Thus it is desirable to be able to use test results to measure the degree to which a program approaches correctness. The probability of correctness of a program can sometimes be estimated according to the success of testing. A general parameter is introduced which has the property that its value is zero for a correct program and is greater than zero for an incorrect program. Under reasonable interpretations, the parameter is related, through probability density functions, to characteristics which are observable through program testing. For instance, if the parameter is interpreted as the number of errors in a program, a related, observable characteristic is the number of errors discovered through testing. Upper bounds on the parameter value are established as a function of the value of the observed characteristic and the desired level of confidence in the result. Results are presented for cases of combinations of interpretations, observable characteristics, and probability density functions.

Redressing Metropolitan Imbalances in Service Delivery: A Time-Series Intervention Analysis of a User Charge Policy*

While a quarter of a century of contributions to the literature on central city-suburb relationships indicates that within a metropolitan context suburban exploitation of central cities may not exist, there is no lessening of the desire to reduce imbalances within a particular urban service delivery sector. This paper assesses the impact of an urban administrative policy intervention aimed at shifting the burden of supporting a municipal service to those who actually use and benefit from it. An interrupted time-series quasi-experimental design is merged with a data analysis strategy employing integrated moving average models. The evidence endorses the adoption of user charges for certain urban services as an effective strategy open to urban bureaucracies for redressing urban public finance imbalances.