EMPLOYEE ENGAGEMENT 1

Employee Engagement

Student Name

Institutional Affiliation
EMPLOYEE ENGAGEMENT 2

Introduction

Statistical modelling using regression analysis is one of the business tools used by

firms to measure or predict their future performance. Taking advantage of various

predictive analysis tools, organizations are able to establish the future market

performance. Both linear regression and logistic regression can enable companies to

model their performance depending on the variables under study. For instance, measuring

financial distress in firms can be measured using the Altman Z-Score, which is basically a

logit model for predicting chances of bankruptcy (Kitowski et al., 2022). In contrast, firms

can build linear models to forecast future likelihoods based on a set of variables that

influence performance related indicators, such as return on investment, return on assets and

return on equity. Multiple linear regression is widely applied in predicting the extent to

which firm characteristics or macroeconomic factors influence financial performance.

Multiple linear regression can be used to test the relative influence or weights of predictors

that affect firm engagement. In light of this background, this paper seeks to establish the

influence of age and sex on employee engagement.

Research Questions

i. What is the effect of sex on employee engagement?

ii. What is the effect of age on employee engagement?

Research Hypotheses

The following research hypotheses are tested:

Ho1: Sex has no statistically significant effect on employee engagement.

Ho2: Age has no statistically significant effect on employee engagement.

Variables and Levels of Measure

Variables have different levels of measurement depending on their nature. The various

levels of measurement include ratio, interval, nominal, and ordinal measurements. Ratio or

interval measurements are continuous variables, such as the age or score of an individual.

Most data sets are collected as continuous variables before they are recoded into different

variables to create categories. For instance, computation of logistic regression requires a

binary outcome, signifying that a continuous variable must be recoded into binary variable

to meet the assumptions of logistic regression. Scaled variables are at the interval level of

measurement (Allanson & Notar, 2020). Use of Likert scales is an example of interval

measurement since there are equal distances from one data point to the next one. Ratio

scales have a true zero value, suggesting that age is a ratio variable.

Nominal level of measurement names variables based on their attributes, but without

any specific order. For instance, the sex of an individual in a nominal data since a person

can biologically be either male or female. Being a man or a woman does not have any

order or weight. Nominal measures only names and does not order variables, thus it is

considered the weakest level of measurement. For instance, the postal zip code, blood type

and race are only emblems and do not reflect any order. In this paper, the sex of the

employees is a nominal measure since it only points out the attributes of being male or

female devoid of any ranking. In contrast, ordinal measurement ranks and orders

variables, but does not give proportions between data points. For instance, the socio-

economic status of an individual, such as income can be ranked as low, moderate or high

income. Conversely, interval scale gives information on ranking and distance from one
EMPLOYEE ENGAGEMENT 4

data point to the next. For example, credit scores and temperature are some of the interval

scales.

Discussion of the Findings

The analysis of data applied Pearson correlation analysis and multiple linear regression

analysis to assess the effect of age and sex on employee engagement. From the output

results, it is evident that there is a moderate, negative and significant correlation between

age and employee engagement, r= (30), -.586, p< .05. In contrast, there is a weak, positive

and statistically insignificant association between sex and employee engagement , r= (30),

.000, p> .05. Findings from the Pearson correlation indicate that the level of employee

engagement is not dependent on an employee being male or female. However, the age of

the employees has a statically significant effect on the level of organizational citizenship

behavior. This seems to imply that younger or older employees will have higher

commitment or interactions with the organization.

The output results for multiple linear regression analysis indicate that the two predictor

variables (age and sex) have a moderately strongly association with employee engagement

as indicated by a correlation coefficient (R) of .590. This association is statistically

significant since the probability value is less than the standard alpha value (p=0.003).

From the coefficient of determination (R 2), age and sex explain 34.8% of variation or

changes in employee engagement. This suggests that other predictors of employee

engagement that were not part of the research contribute 65.2% of variations in the level

of organizational citizenship behavior. From the ANOVA results, it is clear that the model

is significant in predicting the association between predictor variables (sex and age) and

employee engagement. Holding all factors constant, employee engagement is 5.202. The
EMPLOYEE ENGAGEMENT 5

multiple linear regression coefficients indicate that a unit change in sex will lead to -.069

change in employee performance. However, the association between sex and employee

engagement is not statistically significant (p> .05). on the contrary, a unit change in age

will lead to -.021 changes in employee engagement. The relationship between age and

employee engagement is statistically significant (p< .05). From the multiple linear

regression results, the substitution of the multiple linear equation become:

Y= 5.202+ -.069Sex+ -.021Age+ 0

The findings from the output partially agree and disagree with the existing literature on

the interplay between sex and employee engagement. For instance, Khodakarami and

Dirani (2020) disagrees with the findings of this study by stating that women are more

engaged and loyal compared to women. On the relationship between age and employee

engagement, Dhir and Shukla (2018) agree with the findings of the current study that age

differences are significantly associated with the level of organizational commitment and

citizenship behavior. This comparison has decision-making implications since the studies

were undertake in different settings with distinct methodological and statistical approaches.

Thus, generalizations should be applied sparingly.

Implications of the results for Management Practice

Multiple linear regression results indicate that the combined effect of sex and age

significantly influences organizational commitment by employees. However, results from

the Pearson correlation and multiple linear regression coefficients indicates that sex does

not have a statistically significant effect of employee commitment. In contrast, age is

significantly associated with employee engagement. The implication for this result is that

organizations should have a right mix of younger and older employees in addition to
EMPLOYEE ENGAGEMENT 6

provision of mentorship programs since age differences is significantly associated with

loyalty and engagement to the organization. Conversely, organizations should sparingly

have a mix of male and female employees since sex differences are not associated with the

level of engagement and loyalty to the organization.

Conclusion

The statistical interpretations show that age differences in organizations influences

organizational citizenship behavior, suggesting that firms should have a proportionate

number of younger and older employees. In contrast, there are no differences in

organizational commitment for male or female employees. From the multiple linear

regression, the combined effect of sex and age significantly influences employee

commitment.
EMPLOYEE ENGAGEMENT 7

References

Allanson, P. E., & Notar, C. E. (2020). Statistics as measurement: 4 scales/levels of

measurement. Education Quarterly Reviews, 3(3), 375-384.

Dhir, S., & Shukla, A. (2018). The influence of personal and organisational characteristics on

employee engagement and performance. International Journal of Management Concepts

and Philosophy, 11(2), 117-131.

Khodakarami, N., & Dirani, K. (2020). Drivers of employee engagement: Differences by work

area and gender. Industrial and Commercial Training, 52(1), 81-91.

Kitowski, J., Kowal-Pawul, A., & Lichota, W. (2022). Identifying Symptoms of Bankruptcy

Risk Based on Bankruptcy Prediction Models—A Case Study of

Poland. Sustainability, 14(3), 1416.