Running Head: Correlation and Bivariate Regression

Running head: CORRELATION AND BIVARIATE REGRESSION 1
Correlation and Bivariate Regression
Student’s Name
Institutional Affiliation
CORRELATION AND BIVARIATE REGRESSION 2
Correlation and Bivariate Regression
Correlation and bivariate regression helps in the establishment of the association between two
factors of interest. Correlation method also helps the researcher to determine the strength of the
linear association between two variables (Frankfort-Nachmias & Leon-Guerrero, 2017). The
correlation values range from -1 to 1, where 0 indicates no relationship. Bivariate regression, on
the other hand, is a statistical tool that helps in understanding the link between independent and
dependent variables.
The article under consideration in this assignment is by De Haas et al. (2007). The title of the
article is “Genetic correlations between body condition scores and fertility in dairy cattle using
bivariate random regression models." The authors of the article employed a bivariate random
regression research design. This approach is usually appropriate while analyzing longitudinal
genetic data. The authors opted to use correlation and bivariate regression. These approaches
help in the estimation of genetic factors for score situation on body and prolificacy traits in dairy
cattle. This choice was valid because the research design works best with cross-sectional and
longitudinal data (Frankfort-Nachmias & Leon-Guerrero, 2017). Besides that, it fitted the linear
modelY = Xb+Zu+ e. In this case, Y represents the outcome, while Xb depicts the fixed effects of
the design. Zu shows the randomly distributed sire effects, and e indicates the errors incurred in
the model (De Haas et al., 2007). This design enabled the researchers to obtain the correlation
between the two variables under study.
The longitudinal design came in play while fitting the genetic level using the following
n
model;Y ij =X ij + ∑ u ℑ ∅ m ( DIM j ) +e ij
m=1
Y ij shows the score condition of a particular heifer, while 'ij' indicates the sire number and day,
respectively. X ij , on the other hand, represents the fixed effects in the design while 'u' and m
indicate the random cause and coefficient, respectively. DIM is the abbreviation of day in milk
while 'eij' shows the residuals incurred.
The authors of the article displayed the data using bar charts, line graphs, and tables. The bar
charts helped in the depiction of the descriptive statistics of the data. For instance, figure 1
showed the number of lactating heifers per month. The line graphs assisted the authors in
displaying the results of longitudinal random regression analysis (De Haas et al., 2007). The
representations are in figures four to eight. The tables, on the other hand, helped the researchers
in representing the correlation outcomes. These ways of displaying data are pleasing and
effortlessly understandable hence appropriate. The authors gave a stand-alone results section.
This action was necessary because the readers can easily relate the methods used in the research
and the results, hence increasing understandability levels. Apart from that, the authors
subdivided the results section. For example, the article had the descriptive, cross-sectional, and
longitudinal parts. These portions gave detailed information, which will enable the readers to
comprehend the findings of the study genuinely.
The authors of this article did not display the effect size, a fundamental aspect of any research
study. The exclusion of effect size is, in this case, disadvantageous. The reason is that the target
readers will not know if the statistical significance of the study reflects the scientific
meaningfulness (Wagner, 2019). The basis for this conclusion is that at times, the figures may
indicate statistical significance, but it does not reflect the reality in real life. The effect size
would have helped in determining the intensity of the correlation between the two parameters in
this article.
References
De Haas, Y., Janss, L. L. G., & Kadarmideen, H. N. (2007). Genetic correlations between body
condition scores and fertility in dairy cattle using bivariate random regression
models. Journal of Animal Breeding and Genetics, 124(5), 277-285.
Frankfort-Nachmias, C., & Leon-Guerrero, A. (2017). Social statistics for a diverse society. Sage
Publications.
Wagner III, W. E. (2019). Using IBM® SPSS® statistics for research methods and social
science statistics. Sage Publications.

Running Head: Correlation and Bivariate Regression

Uploaded by

Copyright:

Available Formats

Running Head: Correlation and Bivariate Regression

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Running Head: Correlation and Bivariate Regression

Uploaded by

Copyright:

Available Formats

Running head: CORRELATION AND BIVARIATE REGRESSION 1

Correlation and Bivariate Regression

Correlation and Bivariate Regression

correlation values range from -1 to 1, where 0 indicates no relationship. Bivariate regression, on

between the two variables under study.

while 'eij' shows the residuals incurred.

comprehend the findings of the study genuinely.

models. Journal of Animal Breeding and Genetics, 124(5), 277-285.

science statistics. Sage Publications.

You might also like