We present the
-statistic permutation (USP) test of independence in the context of discrete data displayed in a contingency table. Either Pearson's
-test of independence, or the
-test, are typically ...used for this task, but we argue that these tests have serious deficiencies, both in terms of their inability to control the size of the test, and their power properties. By contrast, the USP test is guaranteed to control the size of the test at the nominal level for all sample sizes, has no issues with small (or zero) cell counts, and is able to detect distributions that violate independence in only a minimal way. The test statistic is derived from a
-statistic estimator of a natural population measure of dependence, and we prove that this is the unique minimum variance unbiased estimator of this population quantity. The practical utility of the USP test is demonstrated on both simulated data, where its power can be dramatically greater than those of Pearson's test, the
-test and Fisher's exact test, and on real data. The USP test is implemented in the R package USP.
Display omitted
•Method to analyze tagging experiments for dependence between tags on the same fish.•Can be applied by field staff to monitor an experiment that is in progress.•Exact Bayesian method ...uses Monte Carlo simulation.•Easily programmed in R, code provided.•Applied to previously published cod tagging data, shows need for reanalysis.
Shedding rates of tags on fish are commonly estimated from double-tagging experiments, for which an assumption of independence between the two tags on a fish is required. For tags of qualitatively different types, a nonparametric test for this assumption was proposed by Myhre (1966), making use of concurrent double- and single-tagging of fish. We extend Myhre’s test by developing a nonparametric Bayesian test that is also applicable to the common situation where the two tags attached to a fish are identical and assumed to shed at the same rate; the validity of this assumption can be checked by an extra test that we supply in the case that each tag is identified uniquely. In addition to dependence between tags, the dependence test can also be triggered by departures from other experimental assumptions, such as marked variation in the expertise of taggers. We recommend the dependence test for monitoring tag-return data on an ongoing basis during an experiment. We apply our test to Atlantic cod tagging data listed by Barrowman and Myers (1996). Frequentist tests based on Fisher’s Exact Test are also presented.
When designing a randomized clinical trial to compare two treatments, the sample size required to have desired power with a specified type 1 error depends on the hypothesis testing procedure. With a ...binary endpoint (e.g., response), the trial results can be displayed in a 2 × 2 table. If one does the analysis conditional on the number of positive responses, then using Fisher's exact test has an actual type 1 error less than or equal to the specified nominal type 1 error. Alternatively, one can use one of many unconditional “exact” tests that also preserve the type 1 error and are less conservative than Fisher's exact test. In particular, the unconditional test of Boschloo is always at least as powerful as Fisher's exact test, leading to smaller required sample sizes for clinical trials. However, many statisticians have argued over the years that the conditional analysis with Fisher's exact test is the only appropriate procedure. Since having smaller clinical trials is an extremely important consideration, we review the general arguments given for the conditional analysis of a 2 × 2 table in the context of a randomized clinical trial. We find the arguments not relevant in this context, or, if relevant, not completely convincing, suggesting the sample‐size advantage of the unconditional tests should lead to their recommended use. We also briefly suggest that since designers of clinical trials practically always have target null and alternative response rates, there is the possibility of using this information to improve the power of the unconditional tests.
Two‐tailed significance testing for 2 × 2 contingency tables has remained controversial. Within the medical literature, different tests are used in different papers and that choice may decide whether ...findings are adjudged to be significant or nonsignificant; a state of affairs that is clearly undesirable. In this paper, it is argued that a part of the controversy is due to a failure to recognise that there are two possible alternative hypotheses to the Null. It is further argued that, while one alternative hypothesis can lead to tests with greater power, the other choice is more applicable in medical research. That leads to the recommendation that, within medical research, 2 × 2 tables should be tested using double the one‐tailed exact probability from Fisher's exact test or, as an approximation, the chi‐squared test with Yates' correction for continuity.
Due to the escalating usage of cellphones, cellphone distracted driving remains one of the fastest-growing traffic safety problems. Two basic types of cellphone distractions are – talking (handheld ...or hands-free) and manipulating (texting, internet browsing, using apps for social networking, navigation, entertainment, etc.). To explore the association between the cellphone distraction type and characteristics of a driver, roadway, and vehicle, we used Fisher's exact test and association rule mining to analyze the data from ten different hour-long observation sessions performed both at intersections and on straight continuous segments. Among 3727 drivers observed, 22.1% were found distracted by cellphones. More drivers were involved in manipulating (12.8%) than talking on the phone (9.3%). The Fisher's exact test results show that intersections and the presence of passengers may be significantly associated with driver distraction type. This study makes a novel attempt to utilize association rule mining in cellphone distraction observation. A set of generated rules and their network visualization demonstrated how a specific group of characteristics can be related to cellphone conversation or manipulation through the measures of support, confidence, and lift. 'Peak hour', 'Absence of passengers', and 'Urban setting' are more likely to be associated with distracted driving than other characteristics. The results from association rules revealed that male drivers were found to be predominantly involved in cellphone manipulation during peak hours on urban segments than female drivers, and they were also largely involved in cellphone conversation during peak hours on the rural segment. Female drivers engaged in manipulating cellphones at the urban intersection during both peak and off-peak hours. In the rural area during peak hours, female drivers were manipulating at the intersection and were talking while driving on the continuous segment. Drivers aged '30–60 years' were found to be more associated with cellphone use compared to '<30 years' and '>60 years' age group. 'Passenger car drivers during peak hours' were more associated with manipulating cellphones than expected compared to any other collective group, whereas 'female passenger car drivers driving on continuous segment' were strongly associated with cellphone conversation. The detailed discussion of the findings from association rule mining will be useful for targeting a specific group of relevant characteristics in potential cellphone distraction reduction strategies.
•Fisher’s exact tests measure significance of cellphone use type with roadway, vehicle, and driver characteristics.•Fisher’s test results indicate significant association of intersections and passenger presence with distraction type.•Association rule mining is utilized for presenting co-occurring collective relationship of observed characteristics.•Association rule mining reveals ‘passenger car drivers during peak hours’ are linked with cellphone manipulation.•Cellphone conversation is more associated with 'female passenger car drivers driving on continuous segment'.
Staphylococcus haemolyticus
is one of the most significant coagulase-negative staphylococci, and it often causes severe infections. Rapid strain typing of pathogenic
S. haemolyticus
is indispensable ...in modern public health infectious disease control, facilitating the identification of the origin of infections to prevent further infectious outbreak. Rapid identification enables the effective control of pathogenic infections, which is tremendously beneficial to critically ill patients. However, the existing strain typing methods, such as multi-locus sequencing, are of relatively high cost and comparatively time-consuming. A practical method for the rapid strain typing of pathogens, suitable for routine use in clinics and hospitals, is still not available. Matrix-assisted laser desorption ionization-time of flight mass spectrometry combined with machine learning approaches is a promising method to carry out rapid strain typing. In this study, we developed a statistical test-based method to determine the reference spectrum when dealing with alignment of mass spectra datasets, and constructed machine learning-based classifiers for categorizing different strains of
S. haemolyticus
. The area under the receiver operating characteristic curve and accuracy of multi-class predictions were 0.848 and 0.866, respectively. Additionally, we employed a variety of statistical tests and feature-selection strategies to identify the discriminative peaks that can substantially contribute to strain typing. This study not only incorporates statistical test-based methods to manage the alignment of mass spectra datasets but also provides a practical means to accomplish rapid strain typing of
S. haemolyticus
.
This study investigates 11 agricultural management practices (AMPs) and their effects on seven visual soil quality indicators and soil aggregate stability. The survey carried out across eight ...pedoclimatic zones in Europe and China was based on visual soil assessments (New Zealand VSA method) performed on soils subject to different soil management practices and nearby similar soils, under similar farming features, without the distinctive soil management practice (control). Fisher's exact test was used to test if the management treatment was independent of the score of each visual soil quality indicator and to test if the management treatment produced a higher frequency of the score ‘good’. The results showed a statistically significant (α < .05) higher frequency of the score ‘good’ for ‘soil structure and consistency’ and/or ‘soil porosity’ for six AMPs. For no‐till AMP, the null hypothesis can also be rejected for ‘susceptibility to erosion’ and ‘soil stability’ and for ‘mulching + permanent soil cover’ AMP, for the ‘presence of tillage pan’ and ‘soil colour’. The hypothesis that the management treatment was independent of the score of each indicator was rejected for ‘soil structure and consistency’ of three AMPs, for ‘soil porosity’ of three AMPs, for ‘soil colour’ of one AMP and for the ‘presence of tillage pan’ of one AMP. This study demonstrates that farming systems sharing a common influential soil management practice at different locations and with different soil types significantly affect the score of some visual soil quality indicators.
Summary
A common situation in biology is where we have count data and wish to explore whether there is an association between two categorical variables, each with two levels (a 2 × 2 contingency ...table). The size of the association can be measured using the odds ratio, with a confidence interval for this measure enclosing unity suggesting no evidence of an association. However, there is no universally agreed method for calculating such a confidence interval.
Here, we provide a review of some commonly used and recently suggested methods.
Of all of the methods currently available, the unconditional approach based on the score statistic was consistently closest to the nominal type I error level in our investigations, and this is the method we generally recommend. This method also offers good agreement with P‐values from null hypothesis testing using the method of Fisher‐Boschloo.
However, some scientists may prefer the recently developed minlike or
Blaker methods, which offered better agreement with P‐values calculated using Fisher's Exact test or Blaker's Exact test, respectively.
Lastly, where calculation without use of a computer is required, we recommend the Woolf method with Haldane‐Anscombe correction.
Veech (2013, Global Ecology and Biogeography, 22, 252-260) introduced a formula to calculate the probability of two species co-occurring in various sites under the assumption of statistical ...independence between the two distributional patterns. He presented his model as a new procedure, a 'pairwise approach', different from analyses of whole presence-absence matrices to examine patterns of co-occurrence. Here I show that: (1) Veech's method is identical to Fisher's exact test, a standard procedure for measuring the statistical association between two discrete variables; (2) in a broad sense, the pairwise approach is very similar to early analyses of spatial association, such as the one advanced by Forbes in 1907; (3) implicit in Veech's formula is a sampling scheme that is indistinguishable from well-known matrix-level null models that randomize the distribution of species among equiprobable sites; (4) pairwise co-occurrence patterns can be analysed using any matrix-level null model, so pairwise comparisons are not limited to using Veech's formula. The methodological distinction that Veech proposed between pairwise and matrix-level approaches does not in fact exist, although the conceptual distinction between the two approaches is still a debated topic.