Test procedure and sample size determination for a proportion study using a double-sampling scheme with two fallible classifiers

2017 ◽  
Vol 28 (4) ◽  
pp. 1019-1043 ◽  
Author(s):  
Shi-Fang Qiu ◽  
Xiao-Song Zeng ◽  
Man-Lai Tang ◽  
Wai-Yin Poon
Keyword(s):  
Sample Size ◽  
Null Hypothesis ◽  
Test Procedure ◽  
Sample Size Determination ◽  
Double Sampling ◽  
Score Statistic ◽  
Wald Statistic ◽  
Test Procedures ◽  
Practical Applications ◽  
Logit Transformation

Double sampling is usually applied to collect necessary information for situations in which an infallible classifier is available for validating a subset of the sample that has already been classified by a fallible classifier. Inference procedures have previously been developed based on the partially validated data obtained by the double-sampling process. However, it could happen in practice that such infallible classifier or gold standard does not exist. In this article, we consider the case in which both classifiers are fallible and propose asymptotic and approximate unconditional test procedures based on six test statistics for a population proportion and five approximate sample size formulas based on the recommended test procedures under two models. Our results suggest that both asymptotic and approximate unconditional procedures based on the score statistic perform satisfactorily for small to large sample sizes and are highly recommended. When sample size is moderate or large, asymptotic procedures based on the Wald statistic with the variance being estimated under the null hypothesis, likelihood rate statistic, log- and logit-transformation statistics based on both models generally perform well and are hence recommended. The approximate unconditional procedures based on the log-transformation statistic under Model I, Wald statistic with the variance being estimated under the null hypothesis, log- and logit-transformation statistics under Model II are recommended when sample size is small. In general, sample size formulae based on the Wald statistic with the variance being estimated under the null hypothesis, likelihood rate statistic and score statistic are recommended in practical applications. The applicability of the proposed methods is illustrated by a real-data example.

scholarly journals Sampling, Sample Preparation, and Analytical Variability Associated with Testing Wheat for Deoxynivalenol

2000 ◽  
Vol 83 (5) ◽  
pp. 1285-1292 ◽  
Author(s):  
Thomas B Whitaker ◽  
Winston M Hagler ◽  
Francis G Giesbrecht ◽  
Anders S Johansson
Keyword(s):  
Sample Preparation ◽  
Sample Size ◽  
Variance Component ◽  
Small Sample Size ◽  
Test Procedure ◽  
Small Sample ◽  
Test Procedures ◽  
Analytical Variability ◽  
Total Variability ◽  
Regression Techniques

Abstract The variability associated with testing wheat for deoxynivalenol (DON) was measured using a 0.454 kg sample, Romer mill, 25 g comminuted subsample, and the Romer Fluoroquant analytical method. The total variability was partitioned into sampling, sample preparation, and analytical variability components. Each variance component was a function of the DON concentration and equations were developed to predict each variance component using regression techniques. The effect of sample size, subsample size, and number of aliquots on reducing the variability of the DON test procedure was also determined. For the test procedure, the coefficient of variation (CV) associated with testing wheat at 5 ppm was 13.4%. The CVs associated with sampling, sample preparation, and analysis were 6.3, 10.0, and 6.3%, respectively. For the sample variation, a 0.454 kg sample was used; for the sample preparation variation, a Romer mill and a 25 g subsample were used; for the analytical variation, the Romer Fluoroquant method was used. The CVs associated with testing wheat are relatively small compared to the CV associated with testing other commodities for other mycotoxins, such as aflatoxin in peanuts. Even when the small sample size of 0.454 kg was used, the sampling variation was not the largest source of error as found in other mycotoxin test procedures.

Reliability of Laboratory Tests for the Control of Oral Anticoagulation

1974 ◽  
Vol 32 (02/03) ◽  
pp. 483-491
Author(s):  
E. A Loeliger ◽  
M. J Boekhout-Mussert ◽  
L. P van Halem-Visser ◽  
J. D. E Habbema ◽  
H de Jonge
Keyword(s):  
Human Brain ◽  
Laboratory Tests ◽  
Test Procedure ◽  
Rabbit Brain ◽  
Normal Range ◽  
Test Procedures ◽  
Discrimination Power ◽  
Power Of The Test ◽  
Assay Procedure ◽  
Low Sensitivity

SummaryThe present study concerned the reproducibility of the so-called prothrombin time as assessed with a series of more commonly used modifications of the Quick’s onestage assay procedure, i.e. the British comparative reagent, homemade human brain thromboplastin, Simplastin, Simplastin A, and Thrombotest. All five procedures were tested manually on pooled lyophilized normal and patients’ plasmas. In addition, Simplastin A and Thrombotest were investigated semiautomatically on individual freshly prepared patients’ plasmas. From the results obtained, the following conclusions may be drawn :The reproducibility of results obtained with manual reading on lyophilized plasmas is satisfactory for all five test procedures. For Simplastin, the reproducibility of values in the range of insufficient anticoagulation is relatively low due to the low discrimination power of the test procedure in the near-normal range (so-called low sensitivity of rabbit brain thromboplastins). The reproducibility of Thrombotest excels as a consequence of its particularly easily discerned coagulation endpoint.The reproducibility of Thrombotest, when tested on freshly prepared plasmas using Schnitger’s semiautomatic coagulometer (a fibrinometer-liJce apparatus), is no longer superior to that of Simplastin A.The constant of proportionality between the coagulation times formed with Simplastin A and Thrombotest was estimated at 0.64.Reconstituted Thrombotest is stable for 24 hours when stored at 4° C, whereas reconstituted Simplastin A is not.The Simplastin A method and Thrombotest seem to be equally sensitive to “activation” of blood coagulation upon storage.

Perceived Influence of Students’ Demographic Variables on Their Access to Financial Aids in Public Universities in Rivers State, Nigeria

2018 ◽  
Vol 8 (2) ◽  
pp. 32-50
Author(s):  
Emmanuel Olorunleke Eseyin
Keyword(s):  
Sample Size ◽  
Public Universities ◽  
Sampling Technique ◽  
Demographic Variables ◽  
Sample Size Determination ◽  
Interview Schedule ◽  
The Public ◽  
Research Questions ◽  
Level Of Significance ◽  
Rivers State

The paper investigated the perceived influence of students’ demographic variables on their access to financial aids in public Universities in Rivers State, Nigeria. Six questions were formulated to guide the study and five hypotheses tested at 0.05 level of significance. The design adopted for the study was an analytical survey. The population of the study included 78, 216 students (34,997 male and 43,219 female) in the three public Universities in Rivers State. The sample of the study covered 791 students (Male= 395 and Female= 396) selected through the random sampling technique while Taro Yamane method of sample size determination was used for determining the sample size. The instruments used for collecting responses from students were questionnaire and a ten items interview schedule. The research questions were answered using frequency, percentage and cumulative percentage. Findings of the study revealed that students’ demographic variables have an influence on their access to financial aids in public Universities in Rivers State, Nigeria. The implication of this is that the government’s expenditure on education will continue to increase in the absence of these alternative financial aids in the public Universities in Rivers State, Nigeria.

Sign in / Sign up

Export Citation Format

Share Document