Multiple Comparison Procedures for the Differences of Proportion Parameters in Over-Reported Multiple-Sample Binomial Data

Rahardja, Dewi

doi:10.3390/stats3010006

Cited by 3 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, a within‐subjects Z ‐test of equality of proportions was performed to assess the significance differences in the proportion of new registrations from one decade to the next decade for each population group and gender 28 . To control for type I error rate, Bonferroni correction was used 29 . Proportion differences, P ‐values and 95% Confidence Intervals (CI) for proportion differences were used to assess significance and for interpretation of the results.…”

Section: Methodsmentioning

confidence: 99%

Demographic transformation of the physiotherapy profession in South Africa: A retrospective analysis of HPCSA registrations from 1938 to 2018

Louw

Berner

Tiwari

et al. 2020

Evaluation Clinical Practice

View full text Add to dashboard Cite

Rationale, aim and objective The physiotherapy profession did not escape the effects of racially based segregatory practises. While numerous strategies and initiatives have been employed to redress the inequities of the past, the extent of demographic transformation within the physiotherapy profession in South Africa remains uncertain. Transformation is defined in this article as an intentional change aimed at addressing inequalities and the ultimate goal is for population group and gender profiles of higher education graduates to be representative of the national epidemiological profile. This paper describes the demographic patterns of Health Professions Council of South Africa (HPCSA) registered physiotherapists from 1938 to 2018. Method A retrospective record review of the HPCSA database from 1938 until 2018 was performed. De‐identified data were extracted, coded and analyzed for descriptive purposes. Z‐tests were used for analysis of proportion differences, along with P‐values and 95% confidence intervals for interpretation. Results In 2018, 7663 physiotherapists (6350 women and 1313 men) were registered with the HPCSA. Most registered physiotherapists (55.6%) were classified as white, followed by black (17.3%), coloured (10.3%) and Indian (9.8%). A progressive increase was found in the number of new registrations over time (1949‐2018) by black (0.00%‐24.38% of total new registrations), coloured (0.00%‐15.47%) and Indian individuals (0.00%‐10.03%), with a statistically significant increase in newly registered black therapists in the decade prior to 2018 (P = .005). Gender transformation appears to be occurring at a slower pace as the profession remains female‐dominated (82.9% of registered physiotherapists in 2018). Conclusion There has been a steady transformation of the South African physiotherapy graduates composition regarding population categories and gender. However, it is clear that much more than selection criteria is needed to transform the profession in a way that is nationally representative, remain actively accountable for transformation and apt for local context.

show abstract

Section: Methodsmentioning

confidence: 99%

Demographic transformation of the physiotherapy profession in South Africa: A retrospective analysis of HPCSA registrations from 1938 to 2018

Louw

Berner

Tiwari

et al. 2020

Evaluation Clinical Practice

View full text Add to dashboard Cite

show abstract

“…If we use a multi-categorical factor in the general linear model and want to verify whether there is a significant difference between the different pairs of categories of the relevant factor in terms of target variable mean, then we use Multiple Comparison Methods (Lee & Lee, 2018;Rafter et al, 2002;Rahardja, 2020). Various multiple comparison methods are known, and for our purposes the suitable ones are those that perform pairwise comparisons of the target variable means…”

Section: N σmentioning

confidence: 99%

Segmentation and estimation of claim severity in motor third-party liability insurance through contrast analysis

Reiff¹,

Šoltés²,

Komara³

et al. 2022

View full text Add to dashboard Cite

Research background: Using the marginal means and contrast analysis of the target variable, e.g., claim severity (CS), the actuary can perform an in-depth analysis of the portfolio and fully use the general linear models potential. These analyses are mainly used in natural sciences, medicine, and psychology, but so far, it has not been given adequate attention in the actuarial field. Purpose of the article: The article's primary purpose is to point out the possibilities of contrast analysis for the segmentation of policyholders and estimation of CS in motor third-party liability insurance. The article focuses on using contrast analysis to redefine individual relevant factors to ensure the segmentation of policyholders in terms of actuarial fairness and statistical correctness. The aim of the article is also to reveal the possibilities of using contrast analysis for adequate segmentation in case of interaction of factors and the subsequent estimation of CS. Methods: The article uses the general linear model and associated least squares means. Contrast analysis is being implemented through testing and estimating linear combinations of model parameters. Equations of estimable functions reveal how to interpret the results correctly. Findings & value added: The article shows that contrast analysis is a valuable tool for segmenting policyholders in motor insurance. The segmentation's validity is statistically verifiable and is well applicable to the main effects. Suppose the significance of cross effects is proved during segmentation. In that case, the actuary must take into account the risk that even if the partial segmentation factors are set adequately, statistically proven, this may not apply to the interaction of these factors. The article also provides a procedure for segmentation in case of interaction of factors and the procedure for estimation of the segment's CS. Empirical research has shown that CS is significantly influenced by weight, engine power, age and brand of the car, policyholder's age, and district. The pattern of age's influence on CS differs in different categories of car brands. The significantly highest CS was revealed in the youngest age category and the category of luxury car brands.

show abstract

Omnibus Tests for Multiple Binomial Proportions via Doubly Sampled Framework with Under-Reported Data

Rahardja

2022

Stats

View full text Add to dashboard Cite

Previously, Rahardja (2020) paper (in the first reference list) developed a (pairwise) multiple comparison procedure (MCP) to determine which (proportions) pairs of Multiple Binomial Proportions (with under-reported data), the significant differences came from. Generally, such an MCP test (developed by Rahardja, 2020) is the second part of a two-stage sequential test. In this paper, we derived two omnibus tests (i.e., the overall equality of multiple proportions test) as the first part of the above two-stage sequential test (with under-reported data), in general. Using two likelihood-based approaches, we acquire two Wald-type (Omnibus) tests to compare Multiple Binomial Proportions (in the presence of under-reported data). Our closed-form algorithm is easy to implement and not computationally burdensome. We applied our algorithm to a vehicle-accident data example.

show abstract

Multiple Comparison Procedures for the Differences of Proportion Parameters in Over-Reported Multiple-Sample Binomial Data

Cited by 3 publications

References 25 publications

Demographic transformation of the physiotherapy profession in South Africa: A retrospective analysis of HPCSA registrations from 1938 to 2018

Demographic transformation of the physiotherapy profession in South Africa: A retrospective analysis of HPCSA registrations from 1938 to 2018

Segmentation and estimation of claim severity in motor third-party liability insurance through contrast analysis

Omnibus Tests for Multiple Binomial Proportions via Doubly Sampled Framework with Under-Reported Data

Contact Info

Product

Resources

About