ArticlePDF Available

Parametric and Nonparametric statistics

Authors:
Henshaw Okoroiwu Uchechi at University of Calabar
Henshaw Okoroiwu Uchechi
Euphoria Akwiwu
Euphoria Akwiwu
Euphoria Akwiwu
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Download full-text PDF
Read full-text
Download citation

Abstract

Statistical literacy is essential in biomedical research as an author or reader. Lack of basic statistical knowledge as well as inappropriate statistical tool choice hinders understanding of biomedical research as well as its application. This research detailed basics of parametric and nonparametric statistical procedures. The advantages, disadvantages, indications, examples and analysis of parametric and nonparametric procedures were discussed.
Content uploaded by Henshaw Okoroiwu Uchechi
Author content
All content in this area was uploaded by Henshaw Okoroiwu Uchechi on Jul 28, 2019
Content may be subject to copyright.
Sokoto Journal of Medical Laboratory Science 2019; 4(2): 5 - 15
SJMLS Volume 4, Number 2 June, 2019 Page 5
SJMLS
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 6
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 7
X
_
X
_
S
_
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 8
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 9
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 10
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 11
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 12
Fig 1: Flow chart for choice of inferential statistics for single sample data.
Fig 2: Flow chart for choice of inferential statistics for two sample data.
Fig 3: Flow chart for choice of inferential statistics for two or more sample data.
Fig 4: Flow chart for choice of statistical tests for measure of association/correlation.
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 13
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 14
Citation: Choice of Parametric and Non-parametric Statistical
Procedures in Clinical and Biomedical Research. Sokoto Journal of Medical Laboratory
Science;4(2): 5 - 15.
Copyright. This is an open-access article distributed under the terms of the Creative Commons
Attribution License, which permits unrestricted use, distribution, and reproduction in any medium,
provided the original author and source are credited.
Okoroiwu, H. U. and Akwiwu E. C.
SJMLS
SJMLS Volume 4, Number 2 June, 2019 Page 15
... Parametric statistics is a branch of statistics that makes inferences about the parameters based on the assumption that the data came from a certain sort of probability distribution (normal distribution). Once the assumptions verify the applicability of parametric tests, they could yield a more accurate estimate and as a result, they're frequently considered robust (Uchechi, 2020). On the other hand, non-parametric tests are sometimes known as assumption-free or distribution-free tests. ...
... On the other hand, non-parametric tests are sometimes known as assumption-free or distribution-free tests. It means they could be applied to nominal or ordinal data and also on the scales that don't follow the normal distribution, such as interval or ratio scales (Uchechi, 2020). Regardless of parametric tests' robustness, in comparison to non-parametric tests, they offer other advantages such as adaptability to all sample sizes, applicability on different data types (nominal, interval), and practicability with the dataset including outliers, or data that has been measured imprecisely (Spiegel, 1972). ...
Statistical Analysis of Cost Overrun Causes in Construction Projects: A Demonstration of Selection and Implementation Statistical Tests
Conference Paper
Full-text available
  • Oct 2022
Nowadays, clients in the construction industry are becoming increasingly concerned about the incapacity of executors to complete projects within the specified time and budget. Generally, time and cost variations versus the project's objectives represent the performance of the project. Eventually, to evaluate the project performance and hence the financial risks involved in project execution, it is vital to measure the cost variation in construction projects. Cost variation or overrun which became a typical occurrence throughout the world refers to the deviation between the planned budget and the actual cost of the project. Recently several studies strived to evaluate the causes of cost overruns to explore probable explanations for this phenomenon. One of the commonly adopted methods of withdrawing useful information from the collected data is the application of different statistical tests. However, most of the researchers failed to distinguish between the purpose and applicability of these tests which may lead to inaccurate results and interpretation. Therefore, this study focused on demonstrating the procedure for the selection and application of the aforementioned tests. This study was performed in Iran since the potential of cost overrun occurrence in construction projects in Iran is significantly high. Hence a survey is conducted among different parties including clients, contractors, and consultants who were involved in the construction projects to collect their responses based on probability, impact, and manageability for 38 identified causes of cost overrun. Accordingly, several statistical tests including the Mann-Whitney U test, Kruskal-Wallis H test, and Post hoc test were performed to evaluate the level of agreement between parties from different sectors (Public and Private) as well as different positions (Clients, Contractors, and Consultants). Moreover, Spearman rank-order correlation is adopted to evaluate the ranking of 38 causes of cost overrun based on their probability, impact, and manageability according to the opinion of respondents from different sectors and positions. The results revealed that firstly evaluating the assumptions leads to the selection of non-parametric tests. Secondly, there was a significant agreement between different parties concerning the probability, impact, and manageability of most of the causes of cost overrun except for a few. Finally, the correlation between ranking the causes indicated a strong and positive association between owners and contractors as well as public and private sector respondents in terms of ranking the causes based on their probability and impact.
View
... To establish the significance, a T-test with two independent samples was applied, and the resulting significance level (P-Value) was determined from the test results (Okoroiwu and Akwiwu 2019;Vafadar et al. 2023). The T-test facilitated a comparison of the means between two statistical samples. ...
An intercomparison of the groundwater level estimations by GRACE and GRACE-FO satellites and groundwater modeling in Iran
Article
  • Feb 2024
  • ACTA GEOPHYS
The performance of gravity recovery and climate experiment (GRACE) and GRACE-Follow On (GRACE-FO) satellites in estimating groundwater level (GWL) changes on a local scale is a challenging issue. Then, this study aims to investigate the performance of GRACE and GRACE-FO in monitoring GWL changes on a local scale compared to observations at groundwater wells and the results of groundwater modeling. The study utilized hundreds of groundwater observational data points and 180 satellite data from 2002 to 2020 in five Iranian provinces. The data from satellites GRACE and GRACE-FO were modified by subtracting hydrological parameters outputs of the global land data assimilation system (GLDAS) from the satellites’ estimations. The significant trends in GWL changes were studied by Sen’s slope and Mann–Kendall, which represented a significant declining trend in GWL in all studied provinces. Applying 1–2 month time lags to the observational data improved the correlation coefficients between satellite estimations and the observations at groundwater wells. The best correlation coefficients between observational GWL changes and GRACE estimations in Fars, Khorasan Razavi, Sistan and Baluchistan, East Azerbaijan, and Golestan provinces were calculated as 0.53, 0.42, 0.4, 0.51, and 0.36. Those values for GRACE-FO were calculated as 0.95, 0.67, 0.72, 0.78, and 0.3, respectively, which proved the better performance of GRACE-FO compared to GRACE. Meanwhile, the GWL changes estimated from GRACE-FO were compared to the results of groundwater modeling, which was performed by using MODFLOW via the GMS10.4 interface in Azarshahr aquifer located at East Azarbaijan revealed a satisfactory agreement.
View
... The study adopted a parametric test that assumes normal distribution criteria for the parameters within the population distribution from which the sample is drawn (Uchechi, 2019). Variables used in the model were subjected to normal distribution tests such as skewness and kurtosis. ...
Awareness and attitudes of retailers toward various baobab products in Kenya: Rural townships versus urban markets
Article
Full-text available
  • May 2023
In the wake of climate change, failing of conventional food systems, and low agricultural productivity, baobab tree is central to the livelihoods of many individuals in ASALs. In Kenya, the baobab is a high-priority tree with high economic value than use value. However, products derived from the tree remain rare and only a few are traded. This paper sought to establish the determinants of awareness and attitudes of retailers toward baobab products. Descriptive statistics, Zero-truncated Poisson model, and Exploratory factor analysis were employed to assess awareness levels, attitudes, and their underlying determinants. Data was collected from 352 retailers in rural and urban markets. Descriptive indicated a low product awareness across markets. Further, attitudes of retailers towards baobab were positive and relatively homogeneous. Out of the 13 statements, 10 scored positively on the Likert scale. The model revealed that gender, age, education, years in retailing, and group membership positively influenced awareness, while distance to the market and income from other sources had a negative influence. Exploratory factor analysis generated five factors that explained 57.93% of the total variance. “Source of employment”, “livelihood and survival”, and “nutritive value and freshness,” had the highest factor loadings respectively. The study, therefore, recommends the need to develop strategies that could promote awareness of baobab products. This includes; designing appropriate educational and training programs that focus on gender disparity, youth, and nutritional value. Likewise, governments and the private sector should invest in baobab value chain and infrastructure to enhance market employability, access and availability of products.
View
Evaluation of Satisfaction in Research and Community Service in University
Article
Full-text available
  • Jun 2022
The evaluation of research and community service management in university is carried out institutionally. Indicators in national higher education standards need to be reviewed annually. The object of this research is the LPPM of the Universitas Islam Bandung (Unisba), using a quantitative approach with a survey method. Primary data were collected through questionnaires to the partner population through cluster sampling, internal samples of 191 and external samples of 87. Data analysis was descriptive with parametric statistical tests as descriptions on a Likert scale with eight sub-indicators of a satisfaction survey. Secondary data was collected through focus group discussions on internal and external stakeholders. The results showed that most of the respondents were satisfied with the management of research and community service managed by LPPM Unisba. However, there are suggestions that can be made, including third-party funding, research based on community needs, and conducting ongoing evaluations.
View
ResearchGate has not been able to resolve any references for this publication.