Inferential Statistical Analysis
Conducting inferential statistical analysis
In examining the different inferential statistical methods, consider their fundamental characteristics,
underlying assumptions, strengths, weakness and suitability for producing generalisations regarding an
unbeknown population.
Inferential statistical methods are the critical component of testing and estimating
different parameters of statistical hypotheses. Primarily, unlike descriptive statistics that mainly
focus on analyzing data and summarizing the result in a meaning way, inferential statistical
Inferential Statistical Analysis 2
methods distinguish between a study population and a sample thereby assessing the strength and
weakness of the relationship between dependent variables and independent variables (Dien,
- p. 142). Based on unknown population or statistical data that do not comply with
inferential statistical criteria, different inferential statistical methods enable determination of the
strength and weakness of sample relationships. According to Fernández and Hermida (1998),
inferential statistical methods enable characteristics probability exploration of the population
under study based on sample characteristics.
On a broad front, the fundamental characteristics of inferential statistics rely heavily on
the means difference tests (t-tests), analysis of variance and sophisticated statistical model
application. However, the primary characteristics of inferential statistics are reflected on the
individual type of inferential statistic methods such as multiple-variate regression, bivariate
regression, confidential interval, one sample hypothetical test, t-test or ANOVA, Chi-Square
Statistic and contingency table as well as the Pearson correlation. Kalbfleisch and Prentice
(2011.p.147) states that as ANOVA or t-test provide continuous and categorical variables
characteristics of the unknown population data generation, confidence interval provide basic
features of estimated scores or values in that population sample.
Comparatively, the underlying assumptions of different inferential statistical methods
during the production of data generation in the unknown population are usually based on three
different conditions. Before analysis inferential statistics, a complete list of the participants of the
unknown population has to be provided for analysis. Besides, assumptions are made that a
random sample has been drawing from the unknown population. Similarly, it’s pre-assumed that
the sample size of the unknown population is large enough advocated by Box and Tiao
(2011.p.167) theoretical arguments.
Inferential Statistical Analysis 3
The suitability of applying different inferential statistical methods in data generation of
unknown populations is multiple. Inferential statistical methods, unlike descriptive statistical
methods, provide reliable and validity of the unknown population study findings and results
since they can determine and demonstrate the strength of the relationships of the study samples
by assessing the impacts and outcomes of the study variables (Huitema, 2011.p. 49). Besides, the
inferential statistical methods are suitable for determining the unknown population
characteristics probabilities, generalizing findings and the results of larger and unknown
population and comparing the responses of the unknown population participants (Fernández and
Hermida, 1998.p.198).
The strength of applying different inferential statistical methods in data generation of
unknown populations is that they can analyze and describe with data transformation provides
larger predictions for an unknown set of data population. Besides, inferential statistical methods
can provide confident of the predicted outcome within a specified range based on categorical and
continuous variables as described by Kalbfleisch and Prentice (2011.p.39). Therefore, more
mathematical standardization is applied in inferential methods to provide valid and reliable data
for unknown population compared to descriptive statistical methods. The weakness of inferential
statistical methods in producing the generalization of an unknown population is that the
fundamental conditions and assumptions have to be made for the inferential statistical methods
to be applicable (Hayes and Scharkow, 2013.p.63). However, inferential statistical methods
needs basic mathematical skills for the method to be utilized effectively since multiple
mathematical manipulations may expose the findings to multiple statistical errors (Dien,
2010.p.146).
Inferential Statistical Analysis 4
Bibliography
Box, G.E. and Tiao, G.C., 2011. Bayesian inference in statistical analysis (Vol. 40). John Wiley
& Sons.
Inferential Statistical Analysis 5
Dien, J., 2010. The ERP PCA Toolkit: An open source program for advanced statistical analysis
of event-related potential data. Journal of neuroscience methods, 187(1), pp.138-145.
Fernández, J.R. and Hermida, R.C., 1998. Inferential statistical method for analysis of
nonsinusoidal hybrid time series with unequidistant observations. Chronobiology
international, 15(2), pp.191-204.
Hayes, A.F. and Scharkow, M., 2013. The relative trustworthiness of inferential tests of the
indirect effect in statistical mediation analysis does method really matter?. Psychological
Science, p.0956797613480187.
Huitema, B., 2011. The analysis of covariance and alternatives: Statistical methods for
experiments, quasi-experiments, and single-case studies (Vol. 608). John Wiley & Sons.
Kalbfleisch, J.D. and Prentice, R.L., 2011. The statistical analysis of failure time data (Vol. 360).
John Wiley & Sons.
