Using Lancaster's mid-P correction to the Fisher's exact test for adverse impact analyses.

Adverse impact is often assessed by evaluating whether the success rates for 2 groups on a selection procedure are significantly different. Although various statistical methods have been used to analyze adverse impact data, Fisher's exact test (FET) has been widely adopted, especially when sample sizes are small. In recent years, however, the statistical field has expressed concern regarding the default use of the FET and has proposed several alternative tests. This article reviews Lancaster's mid-P (LMP) test (Lancaster, 1961), an adjustment to the FET that tends to have increased power while maintaining a Type I error rate close to the nominal level. On the basis of Monte Carlo simulation results, the LMP test was found to outperform the FET across a wide range of conditions typical of adverse impact analyses. The LMP test was also found to provide better control over Type I errors than the large-sample Z-test when sample size was very small, but it tended to have slightly lower power than the Z-test under some conditions. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

论高压电机交流耐压试验的几个关键问题

根据冶金工业应用高压电机日渐增多的特点，针对电机试验中极其重要的交流耐压试验项目，阐述了必须严格注意的几个关键问题，提出了改进和完善目前沿用的试验方法的建议。     

On so-called test bias.

Notes that when 2 groups differ in criterion performance and on a selection test, the use of the regression equation derived on the higher group tends to overestimate the mean performance of the lower group and the equation based on the lower group tends to underestimate the mean performance of the higher group. This "unfairness" is reduced somewhat by using an equation based on the groups combined. To avoid this "bias" in selection, various definitions of fairness have led to nonregression models. The present article proposes a multiple regression model which renders estimates fair in the sense that group means are accurately predicted, hence "mean-fair." This model is discussed in detail and examples of its use are presented. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The restriction of range problem and nonignorable selection processes.

We describe a general model for estimating test validity when criterion scores cannot be observed for all cases. Unlike the traditional restriction of range correction formula, the proposed procedure can yield accurate estimates in problems in which an unobservable variable, related to y, is the basis for selection. This type of selection process is referred to as being nonignorable. In the nonignorable case, the regression statistics computed in the selected group, as well as the correction formula estimate, will be biased. The potential advantages of the proposed procedure over the correction formula approach are demonstrated in terms of hypothetical data sets in which the selection process is nonignorable. The shortcomings of the proposed analysis and future research needs are also discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

济钢烧结矿的自动化检验

分析了济钢烧结矿现有检验工艺及存在的问题 ,针对检验工艺过程提出了自动化改造方案 ,该系统设备简单、造价低、检测数据直观、快捷、连续、精确 ,可直接指导生产     

Use and evaluation of discrete test information in decision making.

Elementary decision theory is applied to the problems of evaluating discrete tests or test items used to classify people into several categories, and choosing which of several treatments is best for persons falling within each response category. The technique explicitly considers the base rates of various criterion groups and the relative seriousness of different types of errors of classification, as well as the proportion of each criterion group falling in each response category. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Item response theory analysis of diagnostic criteria for alcohol and cannabis use disorders in adolescents: Implications for DSM-V.

Item response theory (IRT) has advantages over classical test theory in evaluating diagnostic criteria. In this study, the authors used IRT to characterize the psychometric properties of Diagnostic and Statistical Manual of Mental Disorders, 4th edition (DSM-IV; American Psychiatric Association, 1994) alcohol and cannabis use disorder symptoms among 472 clinical adolescents. For both substances, DSM-IV symptoms fit a model specifying a unidimensional latent trait of problem severity. Threshold (severity) parameters did not distinguish abuse and dependence symptoms. Abuse symptoms of legal problems and hazardous use, and dependence symptoms of tolerance, unsuccessful attempts to quit, and physical-psychological problems, showed relatively poor discrimination of problem severity. There were gender differences in thresholds for hazardous use, legal problems, and physical-psychological problems. The results illustrate limitations of DSM-IV criteria for alcohol and cannabis use disorders when applied to adolescents. The development process for the fifth edition (DSM-V) should be informed by statistical models such as those used in this study. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

企业开展电平衡测试浅议

以焦家金矿为列,详细介绍了电平衡测试的方法,针对测试评价分析的问题,明确了节电途径,同时提出了电能平衡测试中应注意的问题。     

"Inferences from personnel tests and their validity": Correction to Lawshe.

Reports an error in "Inferences from personnel tests and their validity" by C. H. Lawshe (Journal of Applied Psychology, 1985[Feb], Vol 70[1], 237-238). On page 238, line 4, the word "each" appears and should be "such." The sentence will, therefore, refer "to the use of such cognitive processes as inductive and deductive reasoning and such characteristics of temperament as emotional stability and self-esteem." (The following abstract of the original article appeared in record 1985-16032-001.) Contends that despite clear definitions in standard sources, psychologists persistently refer to the validity of tests instead of the validity of inferences from test scores. This persistence leads to references to "kinds of validity" when, in fact, there are "kinds of validity analysis strategies" whereby data are collected or generated to determine or defend the extent, degree, or strength of the inference or inferences that can be made from a set of test scores. It is concluded that content validity analysis strategies are appropriate only when the job behavior under scrutiny falls at the observation end of the continuum; when such behavior approaches the abstract end of the continuum, a construct validity analysis strategy is indicated. (5 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The validity of three tests of temperament in guppies (Poecilia reticulata).

Differences in temperament (consistent differences among individuals in behavior) can have important effects on fitness-related activities such as dispersal and competition. However, evolutionary ecologists have put limited effort into validating their tests of temperament. This article attempts to validate three standard tests of temperament in guppies: the open-field test, emergence test, and novel-object test. Through multiple reliability trials, and comparison of results between different types of test, this study establishes the confidence that can be placed in these temperament tests. The open-field test is shown to be a good test of boldness and exploratory behavior; the open-field test was reliable when tested in multiple ways. There were problems with the emergence test and novel-object test, which leads one to conclude that the protocols used in this study should not be considered valid tests for this species. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A method for choosing a cutting point on a test.

Elementary decision theory is used to derive a formula for finding a cutting point on a continuous test used to distinguish between 2 criterion groups, when the test scores of each criterion group are distributed approximately normally. The formula considers the difference between the means of the criterion groups, the standard deviations of test scores of the groups, the relative sizes of the groups, and the relative seriousness of a "miss" vs. a "false positive." (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Tests of significance in stepwise regression.

Tests of significance of the sample squared multiple correlation (R–2) in stepwise multiple regression have not been possible because its distribution is unknown. The present study used Monte Carlo simulation and least squares smoothing to construct tables of the upper 95th and 99th percentage points of the sample R–2 distribution in forward selection. A survey of published psychological research that used stepwise regression found a substantial inflation of reported significance levels when compared to the tabled values. Recommendations are given for use of these tables in evaluating results from forward selection and other stepwise methods. (19 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Clinical trials with multiple outcomes: a statistical perspective on their design, analysis, and interpretation

This article tackles both practical and statistical issues in the handling of multiple outcomes in clinical trials, with relevance to trial design, analysis, and reporting. Specific topics illustrated by examples include: the advantage of prespecifying priorities amongst outcomes and analyses, corrections for multiple significance testing and their limited value, problems with adverse event data, the use of a single global test of significance for clinically related outcomes, the use of a combined outcome for clinical event data, and the value of exploring interrelationships amongst outcomes. The problems in handling multiple outcomes are enhanced by trials being too small, dichotomous attitudes (is the trial "positive" or not?), obsession with p-values, and the manipulative instincts of human nature. While predeclarations of priorities in analysis and reporting of multiple outcomes are important in suppressing distortive claims, it would be unfortunate if too inflexible an approach suppressed unpredictable findings from being seriously considered.     

Methodological problems and issues in MMPI, MMPI-2, and MMPI-A research.

Personality questionnaires are among the most versatile and user-friendly approaches to personality assessment. This article focuses on methodological considerations in conducting research on the MMPI-2, the most widely used clinical personality instrument. The article addresses ways of identifying methodological problems in research and alerts researchers to potential pitfalls in conducting personality assessment research. The topics addressed include the following: methodological factors addressing the continuity of the MMPI-2 and the original MMPI; sample selection in MMPI-2 research; issues concerning test administration; the application of exclusionary criteria in developing research samples; methodological factors in processing, reporting, and analyzing data; developing and evaluating new MMPI-2 scales; and assessing test bias in personality research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Multivariate approach to quality control in clinical chemistry

When monitoring analyzer performance in the clinical setting, laboratories are required to test multiple concentrations of control material on a daily basis. Because of the nature of laboratory testing, there is the potential for correlation between the concentrations of control material being monitored. Although traditional clinical quality-control approaches make an underlying assumption of independence with respect to the control concentrations, this will not always be the case. The presence of correlation in some circumstances suggests the use of a new approach for evaluating clinical laboratory monitoring data: the multivariate control chart. Such a chart (the chi2 chart) is evaluated and compared with traditional quality-control approaches used in the laboratory setting. Results indicate that the multivariate approach provides an attractive alternative to many traditional methods of quality assurance when control concentrations are correlated.     

The complex interaction between measurement and national employment policy.

The long history of measurement in psychology was dramatically changed in the early 1960s when the role of measurement as a gate keeper to the rewards of American society achieved national attention. Since that time in the employment context, the U.S. Congress, state and city legislatures, and the courts have had strong roles in determining the future course of measurement. Debates in many circles continue to this day. Because of the results of a large amount of research focused on issues such as possible differential prediction and validity of tests for various societal groups, the focus of the debates has changed. The current issues are (a) alteration of test scores to achieve results consistent with some social policies, (b) accommodation of testing conditions for persons with disabilities, (c) limitations on the use of personality inventories in employee selection, and (d) substitution of alternate selection procedures for standardized tests. All of these issues have different bases in psychological research and present different problems. Particularly when the civil rights policies of the last 30 years are being challenged, psychologists must be even more diligent in efforts to ensure that policy deliberations are informed by sound research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Enhancement of the biodegradability of model wastewater containing recalcitrant or inhibitory chemical compounds by photocatalytic pre-oxidation

Aminopyrine, antipyrine and trimethadione have been widely used for some time as probe drugs to assess non-selective P450 liver function. They have proved useful in evaluating pre- and post-operative liver function when performing surgery, transplantations, etc., in addition to a general evaluation of liver function and drug interactions. Progress has recently been made both in these non-selective P450 function tests and in the analysis of drug-metabolizing enzymes at a molecular level, which has resulted in more selective P450 function tests. The caffeine (CYP1 A2), chlorzoxazone (CYP2E1), lidocaine (CYP3 A) and midazolam (CYP3 A) function tests and the erythromycin breath test (CYP3 A) are currently being used as specific probes. The future use of these tests needs to be discussed in terms of potential clinical implications.     

Antidote to test weariness.

Comments briefly on a letter decrying employment testing. The present author opines that if testing is worth its salt it must benefit both parties. Ideally, this benefit should be equal. The right tests, intelligently administered and carefully interpreted, can help pick the right man for the right job, prevent a good man from being chosen for the wrong job, and an unqualified man from being placed in a job responsibility that is not right for him--emphasis on "help." Because testing procedures have been misused so often and because so many candidates are skeptical, I have long advocated the following as standard practice: When testing is first mentioned in connection with an open position, a simple statement should be made to the candidate making clear that the procedure will benefit him as much as it benefits the company, that the test results will be used as a guide and not be given "make or break" value. The candidate should then be assured that arrangements will be made, at his option and at a mutually convenient time--and always at the employer's expense-- for him to discuss his test results with a qualified person. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Nonconscious Influence of Masked Stimuli on Response Selection Is Limited to Concrete Stimulus-Response Associations.

A pattern-masked arrow negatively biased the "free choice" between 2 manual responses or between 2 vocal responses. This apparently nonconscious influence occurred only when the free-choice trials were intermixed randomly with other trials that terminated in fully visible arrows, which directed a response of the same modality (manual vs. vocal) as that involved in the free-choice test trials. This indicates that recent conscious processing of the association between specific stimuli and specific responses is needed to activate the nonconscious influence of masked arrows on response selection. Because this influence occurred only when a concrete association was activated, it appears not to be based on deep comprehension of the stimuli and instead is attributable to simple stimulus-response bonds. (PsycINFO Database Record (c) 2010 APA, all rights reserved)