A Simulation Showing the Role of Central Limit Theorem in Handling Non-Normal Distributions

Abstract

This simulation employed a compiler which explains the role of central limit theorem in dealing with populations that are not normally distributed. A group of 10000-data-point populations were simulated according to five different kinds of distribution: uniform, platykurtic normal, positively-skewed exponential, negatively-skewed triangular, and bimodal. Three 500-data-point sampling distributions of sample sizes of 2, 10, and 30 were created from each population. All populations and sampling distributions were displayed in histograms for analysis along with their means and standard deviations. The results verified the principles of the central limit theorem and indicated that if the population is close to normality, a smaller sample size is needed so that the central limit theorem can take effect. But if the population is far from normality, a large sample size might be required. A proportion of population was proposed for a sample size based on the simulation results. Further studies and implications are discussed.

Investigation of AEC/FM practices in adaptive reuse projects

“…Careful consideration was taken to their years of experience at the professional industry. Second, the selection of 30 respondents, as a sample size of each questionnaire survey, was targeted on the basis of the central limit theorem (CLT), which entails that researchers in social and practical related studies should at least involve a sample of 30 respondents in case of conducting a random survey on a particular population, to assume an approximately normal distribution of the data to be processed (Barri, 2019; Chang et al , 2008).…”

Parametric or nonparametric statistical tests: Considerations when choosing the most appropriate option for your data

“…Principles of the Central Limit Theorem include the following: a sampling distribution looks more normal as the sample size increases even for non-normal distributions; the variability of the sampling distribution decreases as the sample size increases; a sampling distribution has a mean equal to the mean of the population it was collected from. 18 A word of caution before leaving the impression that large sample sizes give a blanket pass for use of parametric tests. As the sample size increases, so does the probability of obtaining significant results.…”

“…In other words, with a large enough sample (often cited as larger than n = 30), parametric tests can be used since the distribution of the mean of the sample will approximate a normal distribution. Principles of the Central Limit Theorem include the following: a sampling distribution looks more normal as the sample size increases even for non‐normal distributions; the variability of the sampling distribution decreases as the sample size increases; a sampling distribution has a mean equal to the mean of the population it was collected from 18 …”

Preferencias de estilos de aprendizaje en el alumnado español de entre 11 y 15 años

“…En el análisis de los resultados se aplicaron estadísticos de tipo descriptivo, correlacional e inferencial, partiendo de un nivel de significación del 5% en la interpretación de los contrastes de hipótesis. Dado que la muestra obtenida fue de gran tamaño (n=1066), atendiendo a las propiedades demostradas del teorema central del límite (Barri, 2019), se decidió aplicar contrastes de hipótesis de carácter paramétrico. En concreto, tras el cálculo de los estadísticos descriptivos básicos de tendencia central, dispersión y posición para la exploración de las variables criterio, se analizó su relación a partir de la obtención del coeficiente de correlación de Pearson.…”