Busn311-Quantitative_Methods_and_Analysis_-Apa_Format

Unit 4 – Hypothesis Testing & Variance Type your Name Here American InterContinental University Abstract Intrinsic factors about job satisfaction were analyzed to determine if there was any correlation between genders and extrinsic factors about job satisfaction were analyzed to determine if there was any correlation between hourly vs. salaried workers. There was not enough evidence to conclude the former, but there was for the latter. Introduction The lesson required the student to use statistics to formulate hypotheses about office job satisfaction surveys and then test them to see if those same hypotheses should be rejected. The student was required to use Excel to conduct t tests, calculate test statistics and critical values. Finally, the student had to interpret the statistical results to make observations for an office manager. Hypothesis Test #1 Looking at Intrinsic Satisfaction by Gender Null and alternate hypotheses. ( = .05) The test A separate F test was conducted to confirm that the sample variances (S12 and S22) were equal. From this result, the two-tailed Student’s t test was done with a pooled estimate for the standard deviation, SP (Johnson, 1976). Using Excel’s TTEST function, the probability that the populations have the same mean intrinsic job satisfaction was 0.51. The significance level () was given as 0.05. The test statistic t was computed to be -0.6545. Using Excel’s TINV function with 31 degrees of freedom and a probability of 0.05, the critical value for t was found to be 2.039. State your decision The analysis indicates that I should fail to reject the null hypothesis statement. Explanation of decision made The test statistic (t= -0.6545) is in the rejection region (T>2.039), therefore, do not reject the null hypothesis. Applications for managers The manager should feel confident that the office environment is not causing one gender to enjoy/dislike the job more than the other. The information is valuable so that the manager can focus their efforts in other areas as this is not a problem area. Hypothesis Test #2 Looking at Extrinsic Satisfaction by Position Null and alternate hypotheses ( = .05) The test A separate F test was conducted to confirm that the sample variances (S12 and S22) were unequal. From this result, the two-tailed Student’s t test was done with both sampled standard deviations (Johnson, 1976). Using Excel’s TTEST function, the probability that the populations have the same mean extrinsic job satisfaction was 0.967. The significance level () was given as 0.05. The test statistic t was computed to be 0.04142. Using Excel’s TINV function with 16 degrees of freedom and a probability of 0.05, the critical value for t was found to be 2.12. State your decision The analysis indicates that I should reject the null hypothesis statement. Explanation of decision made The test statistic (t= 0.04142) is not in the rejection region (T< 2.12), therefore, reject the null hypothesis. Applications for managers The hourly workers clearly have a lower level of extrinsic job satisfaction than their salaried counterparts. This could be used in determining new ways to motivate employees and for management to be prepared for labor negations. Z and T Tests The Z test is used when the population you are examining is sufficiently large (N>30) and can assumed to be normally distributed. Alternatively, the T test is used when you do not have enough samples (N<30), but the distribution is still symmetric about the mean and is generally bell-shaped (Johnson, 1976). Samples and Populations A sample is a subset of an entire population who’s mean and variance are known. When one wants to make comparisons about a particular sample to its corresponding population, hypothesis testing can be done. Samples are used so that you can conduct an experiment on a much smaller portion of the population and then test that sample to see how it compares to the larger population and determine if the outcome of the experiment is significant. Drug testing is done this way to compare the effects of a drug on a sample of patients who received it compared to the larger population who did not receive it. Conclusion Hypothesis testing is an excellent way to use sampled data about a population to determine certain characteristics about the whole or to determine if some experiment you did on the sample had statistically significance results. References Johnson, R. (1976). Elementary statistics (2nd ed.). North Scituate, MA: Duxbury Press.