Sample Size Calculation

Sampling

It is the process of choosing adequate and representative elements from the population.

sampling

makes the scope of the study manageable due to the smaller

number of respondents to be covered, and increases the likelihood of obtaining more

reliable and accurate results due to less error in gathering data.

Pearson Correlation analysis

An absolute minimum of 200

samples are required for

covariance-based structural equation

modelling (CB-SEM) programs

require larger sample sizes than

partial least squares structural equation

modelling (PLS-SEM) programs (e.g.

SmartPLS) due to the latter’s estimation

techniques (Hair et al., 2017; Ringle et al.,

2018; Ryan, 2020).

Sample-to-Item Ratio

Sample-to-Variable Ratio

Krejcie and Morgan’s table

is well known for sample size determination

among behavioral and social science

researchers.

Krejcie and Morgan’s table

should be used to determine

sample size when probability

sampling (e.g. simple random,

systematic, stratified) is the

appropriate choice.

Online calculators

are among the better

known ones. Given their ease of use, these calculators

have been frequently applied in social science research.

A-priori sample size for structural

equation models

is a popular application among users of 2nd

generation multivariate data analysis

techniques

Roscoe’s

(1975)

guidelines

• Small populations (<30): Sample size of at least 30 is recommended.

• Medium populations (30-50): Sample size between 30 and 50 is acceptable.

• Large populations (>50): Sample size of 100 or more is ideal.

  .

Green’s (1991) procedures

N ≥ 50+8m (where m refers to the number of predictors in the model) to determine the sample size for the coefficient of determination

Kline’s (2005,

2016) sample size

guidelines for SEM

• Minimum Sample Size: minimum sample size of 200 for SEM studies

• Rule of Thumb (N: 5-10 per Parameter): Kline recommends having at least 5 to 10 observations per estimated parameter in the model. For example, if a model has 10 parameters, the sample size should ideally range from 50 to 100.