Abstract
This paper contains t-test analysis for intrinsic motivation by gender and extrinsic motivation by position based on AIU survey data. In all the two cases, null hypothesis failed to be rejected.
Introduction
Hypothesis refers to a speculative explanation or answer to research problem or question (Lourens & Bedeker, 2007). The process of statistically choosing competing hypotheses is referred to as hypothesis testing (Kruglanski & Higgins, 2003). Some of the statistical methods of testing hypothesis included t-test and z-test.
Null hypotheses
There is no significant difference between intrinsic motivation means of males and females
Ho: µmale -µfemale = 0
Alternative hypothesis
There is significance difference between intrinsic motivation means of males and females
Ha: µmale - µfemale > 0
The test
The significance level used is 0.05 and the corresponding critical value is 1.983037471. The computed t-statistic is 0.608096318.
Decision
The null hypothesis is not rejected. Consequently, there is no significant difference between the intrinsic motivation means of males and females at alpha 0.05.
Explanation of decision made
Null hypothesis was upheld because the absolute value of t-statistic is less than the absolute value of t-critical. Meaning, t statistic fall within the do not reject region. Null hypothesis is not only rejected when t-statistic is greater than or equal to t-critical (Wang & Jain, 2003).
Applications for managers
The above information indicates that there is no statistically significant variation in intrinsic motivation among male and female employees. Both gender, are intrinsically motivated by the same conditions and factors present in the organization. Therefore, the managers should no develop or initiate gender specific interventions to improve intrinsic motivation. Instead, the initiatives should give equal focus to both women and men working in the organization.
Hypothesis Test #2: Looking at Extrinsic Satisfaction by Position
Null hypotheses
There is no significant difference between extrinsic motivation means of hourly and salaried employees
Ho: µhourly -µsalaried = 0
Alternative hypothesis
There is significance difference between extrinsic motivation means of hourly and salaried employees
Ha: µhourly - µsalaried > 0
The test
The significance level used is 0.05 and the corresponding critical value is 2.019540948
The calculated t-statistic is 0.057382003.
Decision
The null hypothesis is not rejected. Consequently, there is no significant difference between the extrinsic motivation means of hourly and salaried employees.
Explanation of decision made
The null hypothesis was upheld because the absolute value of t-statistic is less than the absolute value of t-critical. Meaning, t statistic does not fall in the rejection region of probability distribution.
Applications for managers
The above information shows that there is no statistically significant difference in the way hourly and salaried employees are extrinsically motivated. Therefore, the managers should not come up with motivation initiatives that target either hourly or salaried employees. Instead, working conditions should be improved for both categories employees.
Z and T Tests
Bothe z-test and t-test compares variation between two sample means. However, z-test is used when standard deviation of the population is known and the sample size is large, usually greater than 30 (Jackson, 2030). On the other hand, t-test is more accurate for small sample, usually less than 30. Nonetheless, it is used even with large samples greater than 30. The z-test is based on normal distribution while t-test used student t-distribution.
Samples and Populations
The population in research refers to all cases that posse the characteristics under investigation (Monette, Sullivan & DeJong, 2011). On the other hand sample refers to elements drawn from the population that represent the population in a research. In most social and human researches, the population and sample often consist of people. It is not always possible to estimate the exact mean, standard deviation, and variance of a parameter within the population. For this reason samples are used for hypothesis test because these statistics can be calculated.
Conclusion
Hypothesis testing is used for decision making. The result of t-test analysis for the two cases should be used to make decision relating to means of motivating female/male employees and hourly/salaried employees. The chosen initiative should not be gender or position specific.
References
Jackson, S. (2013). Statisiics plain and simple. Cengage Learning.
Kruglanski, A. W., & Higgins, E. T. (2003). Social psychology: A general reader. New York: Psychology Press.
Lourens, A., & Bedeker, L. (2007). Scientific writing skills: [guidelines for writing theses and dissertations. Stellenbosch, [South Africa: SUN Press.
Monette, D. R., Sullivan, T. J., & DeJong, C. R. (2011). Applied social research: A tool for the human services. Australia: Brookscole.
Wang, G. C. S., & Jain, C. L. (2003). Regression analysis: Modeling & forecasting. Flushing, N.Y: Graceway Pub.
Population
Size, if known, or approximate/estimated sizeSampling
It is impractical and resoue involving to gather data from all units of analysis factored in a researseach. For this reason, a sample which is a representatiove of the population is used for research purposes. A an accyrately drawn sample has most characteristics of the population. Therefore, it can be used to make inferences about the population.
Probability sampling method
Type of samplingStratified sampling methodHow the sample will be drawnSample size and why this was chosen in relation to population size