-
Tuning a Model in Climatology and Calibrating One in Hydrogeology: An Informative Comparison
Issue:
Volume 11, Issue 3, May 2022
Pages:
83-88
Received:
17 April 2022
Accepted:
5 May 2022
Published:
12 May 2022
DOI:
10.11648/j.ajtas.20221103.11
Downloads:
Views:
Abstract: A November 2021 article in the journal Chance on a misuse of statistics by hydrogeologists in their modeling of water levels below ground raises the question of whether climatologists might be committing the same statistical errors in their modeling of global warming above ground. In seeking to answer that question, the research reported in this article finds the answer to be, yes, both research communities corrupt data by altering values of independent variables to reduce error variation or to achieve particular model results. That data alteration not only creates an impermissible negative correlation between estimates and errors but also creates model estimates that exaggerate trends in the observations. The exaggerated trends occur regardless of the nature or the intent of the data alteration. For that reason, use of trends in model estimates resulting from data alteration as a guide to future research or as a basis for conclusions may lead researchers astray. This article suggests an alternative research strategy consisting of random sampling of observation zones which, by limiting a study to thousands rather than millions of zones, could enable researchers to obtain sufficiently accurate input data to make the alteration of data unnecessary. Use of this procedure could also help avoid exaggerated and misleading predictions from models.
Abstract: A November 2021 article in the journal Chance on a misuse of statistics by hydrogeologists in their modeling of water levels below ground raises the question of whether climatologists might be committing the same statistical errors in their modeling of global warming above ground. In seeking to answer that question, the research reported in this ar...
Show More
-
On the Coverage Properties of the Ratio Based Estimator in Presence of Non Response Error
Charles Wanyingi Nderitu,
Herbert Imboga,
Samuel Mwangi Gathuka
Issue:
Volume 11, Issue 3, May 2022
Pages:
89-93
Received:
23 April 2022
Accepted:
7 May 2022
Published:
19 May 2022
DOI:
10.11648/j.ajtas.20221103.12
Downloads:
Views:
Abstract: Sample surveys are taken with the assumption that all the sampled elements will respond. However, this is not always the case. Sometimes missing values occur in the survey data due to some reasons. In cases of such missing values, any inference from the data will survey from a non-response error. Therefore, the researcher needed to put all measures in place to prevent the occurrence of the missing values in the data. However, this is not easily achieved. The non-response may occur even after all measures to prevent it have been put in place. Therefore, there is a need to correct the error if it so happens. The current paper seeks to improve the Hansel and Hurwitz (1946) estimator using poststratification. The proposed estimator can be as well be improved. Therefore, the current study proposes an improvement of the Hansel and Hurwitz (1946) estimator using the median of the auxiliary variable. The efficiency of the new proposed estimator is checked using the confidence interval length. Which is the on-coverage property of the estimator. On to the recommendation a band with that will reduce the variance in case of high non-response rate is thus suggested for further studies. Beside we suggest further studies on how both variances and bias will be minimized without any of them being minimized in expense of the other.
Abstract: Sample surveys are taken with the assumption that all the sampled elements will respond. However, this is not always the case. Sometimes missing values occur in the survey data due to some reasons. In cases of such missing values, any inference from the data will survey from a non-response error. Therefore, the researcher needed to put all measures...
Show More
-
Population Dynamics and Africa’s Poise for Post-COVID-19 Growth: Panel Data Analysis
Ayoola Femi Joshua,
Gbadamosi Idris Isaac,
Odularu Gbadebo Olusegun,
Ikem Fidelis
Issue:
Volume 11, Issue 3, May 2022
Pages:
94-101
Received:
9 April 2022
Accepted:
3 May 2022
Published:
8 June 2022
DOI:
10.11648/j.ajtas.20221103.13
Downloads:
Views:
Abstract: The outbreak of COVID-19 has led to an unprecedented impact on the health, population growth, and economic development of countries globally. The government in most countries came up with measures to curtail the spread of this deadly virus not minding its impacts on their economic growth and population growth. This study examined the relationship between Population Dynamics (PD) and Economic Growth (EG) in twenty-five selected African countries using panel data spanning from 1993 to 2020. Levin, Lin, and Chu test and Lm, Pesaran, and Shin W-stat were used to determine the stationarity conditions of the variables. Also, the pooled mean autoregressive distributed lag model was used to determine the short-run and long-run relationship existing among the variables while the Granger causality test was adopted to determine the direction of the relationship between the dependent and independent variables. The outcome of research findings showed that Levin, Lin, and Chu test and Lm, Pesaran, and Shin W-stat test reveal that the variables were stationery at different orders and the pooled mean autoregressive distributed lag model analysis reveals there are short run and long-run relationships between economic EG and PD. The Granger causality analysis reveals the bidirectional causality between EG and PD. It has shown that PD has a significant impact on EG with the birth rate having a long-run relationship with GDP per Capita which implies that when the economy is booming or viable, there is every tendency that the population will increase through birth rate in a long run in these developing African countries.
Abstract: The outbreak of COVID-19 has led to an unprecedented impact on the health, population growth, and economic development of countries globally. The government in most countries came up with measures to curtail the spread of this deadly virus not minding its impacts on their economic growth and population growth. This study examined the relationship b...
Show More
-
Profile Likelihood Confidence Intervals for the Parameters of a Nonhomogeneous Poisson Process with Linear Rate
Issue:
Volume 11, Issue 3, May 2022
Pages:
102-108
Received:
9 April 2022
Accepted:
9 May 2022
Published:
27 June 2022
DOI:
10.11648/j.ajtas.20221103.14
Downloads:
Views:
Abstract: Nonhomogeneous Poisson Processes (NHPP) are commonly used to model count data where the rate of occurrence of events in a given time period is dependent on time. Examples exist in the literature where NHPP has been used to model real life count data for the purpose of parameter estimation and prediction. The most common methods used to obtain the point estimates of the parameters of the NHPP are the method maximum likelihood and the ordinary least squares method. The commonly used Wald-type confidence intervals are based on the assumption of asymptotic normality and are inaccurate when this assumption is violated This study considers an alternative method based the profile likelihood function to construct approximate confidence intervals for the parameters of a nonhomogeneous Poisson process with linear rate λ(t)=α+βt, based on the number of counts in measurement subintervals. Such a linear rate function is applicable in situations where piecewise-linear approximation to a general rate function is adequate. The profile likelihood confidence intervals for the two parameters are constructed from the graphs of their respective relative profile likelihood functions, which are obtained numerically from the joint relative likelihood function. Simulations were used to compare the profile likelihood and Wald confidence intervals on the basis of coverage probability and mean length. The effects of sample size (number of subintervals) on the interval estimates of the parameters were also investigated. The results of the simulation study show that the profile likelihood method is superior to the Wald method since it yields shorter confide intervals containing plausible values of each of the two parameters.
Abstract: Nonhomogeneous Poisson Processes (NHPP) are commonly used to model count data where the rate of occurrence of events in a given time period is dependent on time. Examples exist in the literature where NHPP has been used to model real life count data for the purpose of parameter estimation and prediction. The most common methods used to obtain the p...
Show More
