This paper compares the use of confidence intervals (CIs) and a sensitivity analysis called the number needed to disturb (NNTD), in the analysis of research findings expressed as 'effect' sizes. Using 1,000 simulations of randomised trials with up to 1,000 cases in each, the paper shows that both approaches are very similar in outcomes, and each…

In their response to our paper, Nicholson and Ridgway agree with the majority of what we wrote. They echo our concerns about the misuse of inferential statistics and NHST in particular. Very little of their response explicitly challenges the points we made but where it does their defence of the use of inferential techniques does not stand up to…

In this interview, we discuss my early uses of meta-analytic procedures, first to combine "p"-values and then to combine effect sizes as well. My interest in quantifying the magnitude and the statistical significance of the effect of interpersonal expectations probably grew out of the following: (1) a long-held interest in the concept of…

The effective evaluation of correctional programs is critically important. However, research in corrections rarely allows for the randomization of offenders to conditions of the study. This limitation compromises internal validity, and thus, causal conclusions can rarely be drawn. Increasingly, researchers are employing propensity score matching…

A latent variable modeling procedure is discussed that can be used to test if two or more homogeneous multicomponent instruments with distinct components are measuring the same underlying construct. The method is widely applicable in scale construction and development research and can also be of special interest in construct validation studies.…

A classic TV commercial once asked, "How many licks does it take to get to the center of a Tootsie Roll Tootsie Pop?" The narrator claims, "The world may never know" (Tootsie Roll 2012), but an Internet search returns a multitude of answers, some of which include rigorous systematic approaches by academics to address the…

Many librarians use data from surveys to make decisions about how to spend money or allocate staff, often making use of popular online tools like Survey Monkey. In this era of reduced budgets, low staffing, stiff competition for new resources, and increasingly complex choices, it is especially important that librarians know how to get strong,…

This methodological brief introduces the readers to the propensity score matching method, which can be used for enhancing the validity of causal inferences in research situations involving nonexperimental design or observational research, or in situations where the benefits of an experimental design are not fully realized because of reasons beyond…

Very little explanatory power is required in order for regressions to exhibit statistical significance. This article discusses some of the causes and implications. (Contains 2 tables.)

In this note the Nearest Neighbour Index is investigated in three cases, linear, 2-dimensional and 3-dimensional. In each case the formula is investigated and the numerical values for the data points to be viewed as attracting each other, repelling each other or being randomly distributed are justified. Also, in each of the three cases mentioned…

Hypothesis testing is one of the more difficult concepts for students to master in a basic, undergraduate statistics course. Students often are puzzled as to why statisticians simply don't calculate the probability that a hypothesis is true. This article presents an exercise that forces students to lay out on their own a procedure for testing a…

Extreme-value statistics is often used to estimate so-called return values (actually related to quantiles) for environmental quantities like wind speed or wave height. A basic method for estimation is the method of block maxima which consists in partitioning observations in blocks, where maxima from each block could be considered independent.…

The sampling distribution is a common source of misuse and misunderstanding in the study of statistics. The sampling distribution, underlying distribution, and the Central Limit Theorem are all interconnected in defining and explaining the proper use of the sampling distribution of various statistics. The sampling distribution of a statistic is…

Demonstrates a statistically valid method allowing students to explore randomization. Described are two examples: counting techniques for a small set of data and simulation for a large sample. (YP)

If risk taking is in some measure a signal to others by the person taking risks, the model of "costly signaling" predicts that the more the apparent cost of the risk to others exceeds the perceived cost of the risk to the risk taker, the more attractive that risk will be as a signal. One hundred and twelve visitors to youth…