What the Quantitative Hypotheses Would Be
In the discussed case, the quantitative hypothesis would be; the introduction of on-job training improves the performance of the employees. The independent variable is the on-job training, while the dependent variable is the employees’ performance.
Hypothesis Testing Tool
Quantitative hypothesis testing is one of the statistical methods that is used by researchers to answer questions that present themselves while studying or resolving research issues. For instance, the human resource department of an engineering firm is interested in determining whether the introduction of on-job training improves the employee’s performance. As such, it is prudent to assess the viability of the decision before its actual implementation. Similarly, the introduction of on-job training and comparing the performance metrics of the trained and untrained staff seems the solution. However, the approach raises questions of whether the proposal applies to all engineering firms. As such, quantitative hypothesis testing base on numerical analysis on collected data using a nine steps systematic approach known as hypothesis testing (Wilcox, 2012 p.1) .
Delegate your assignment to our experts and they will do the rest.
The approach starts by defining the research hypothesis. A research hypothesis is what the research seeks to determine, such as the effect of on-job training on the employees in an engineering firm. Secondly, the research needs operationalization by setting the metrics of measurement (Wilcox, 2012, p.2) . In the above example, measures the variable of employee performance by using methods such as Management by Objective or Graphic Rating Scale. The measured metrics collected from the selected participants (sample) provides the data for analysis representing the whole population (workers in engineering firms).
The research hypothesis has two aspects that are constructed in the third step: A null-hypothesis and an alternate-hypothesis. With the example of the engineering firm in mind, the null hypothesis would be on-job training improves the performance of employees in engineering firms. It agrees with the question that the research question seeks an answer. The alternate hypothesis, on the other hand, opposes the null hypothesis. It, therefore, states that on-job training does not improve the performance of employees in engineering firms.
The researcher then needs to determine the p-level at which they wish to perform the research. The p -value dictates the risk of the researcher to either reject or accept the null hypothesis based on finding falsely. As such, it results in type I or type II error. A type one error is the conclusion that on-job training does not improve the performance of employees in engineering firms falsely. Contrary, a type II error, is the false acceptance that on-job training improves the performance of employees in engineering firms. A p -value of 0.01 indicates that there is a 1% chance that the acceptance or rejection of whether on-job training improves the performance of employees in engineering firms will be false. A p -value of 0.02 increases the risk to 2% in both cases, the percentage significance the significance level of the research.
The results of the statistical-data analysis guide the rejection or acceptance of the null-hypothesis. Analysis requires a determination of the type of test: Either single or double-tailed test, and the selection of the appropriate test method based on the type of distribution. For instance, a t-test suits a normally distributed with a sample size of less than thirty. Finally, the interpretation of the results leads to the conclusion of the research.
References
Wilcox, R. (2012). Introduction to Robust Estimation and Hypothesis Testing. Burlington: Elsevier Science.
