Research Methods, Final Project?

1

6

Sun Coast’s Hypothesis Testing

Data Analysis: Hypothesis Testing

Hypothesis testing is the examination of the relationship between two or more variables. It tests whether two variables affects one another or not (Keysers&Wagenmakers, 2020) It also tests the strength of relationship that exists between the variables. One variable is assumed to be dependent while the other is assumed to be independent (Creswell, 2018). The dependent variable relies on the independent variable. On the other hand, independent variable does not rely on dependent variable and would happen either way with or without dependent variable (Creswell, 2018). Here we will explore two parametric statistical procedures used to test hypothesis. They are the t test and ANOVA. The two tests are similar yet different. The t test is used to compare two means and ANOVA is used to compare more than two means (Creswell, 2018).

Independent Samples tTest: Hypothesis Testing

Ho4: There are no statistically significant differences in the effectiveness of the revised training program versus the prior training program.

Ha4: There are statistically significant differences in the effectiveness of the revised program versus the prior training program.

t-Test: Two-Sample Assuming Unequal Variances
	Group A Prior Training Scores	Group B Revised Training Scores
Mean	69.79032258	84.77419
Variance	122.004495	26.96457
Observations	62	62
Hypothesized Mean Difference	0
df	87
t Stat	-9.666557191
P(T<=t) one-tail	9.69914E-16
t Critical one-tail	1.66255735
P(T<=t) two-tail	1.93983E-15
t Critical two-tail	1.987608241

Interpretation:

The mean value is lower for Group A (Prior training) than Group B (Revised training). We used the alpha of 0.05; the results of the independent samples t test show a p-value (two-tailed) of 1.94E-15, which is lower than the alpha of 0.05. Therefore we reject the null hypothesis and accept the alternative hypothesis. There are statistically significant differences in mean values of the DV between the prior training program and revised training program. Respectfully, Sun Coast should replace the prior training program with the revised training program.

Dependent Samples (Paired Samples) tTest: Hypothesis Testing

Ho5: There is no statistically significant difference in employee blood lead levels between pre-exposure and post-exposure.

Ha5: There is a statistically significant difference in employee blood lead levels between pre-exposure and post-exposure.

	t-Test: Paired Two Sample for Means
		Pre-Exposure μg/dL	Post-Exposure μg/dL
	Mean	32.85714286	33.28571
	Variance	150.4583333	155.5
	Observations	49	49
	Pearson Correlation	0.992236043
	Hypothesized Mean Difference	0
	df	48
	t Stat	-1.92980256
	P(T<=t) one-tail	0.029776356
	t Critical one-tail	1.677224197
	P(T<=t) two-tail	0.059552711
	t Critical two-tail	2.010634722

Interpretation:

We were provided with an alpha of 0.05 and the results show a p-value of 0.06 which is greater than the given alpha of 0.05. We must reject the alternative hypothesis and accept the null hypothesis which states that there are no statistically significant differences in the lead levels in the blood pre exposure and post exposure of employees working where lead remediation is being conducted.

ANOVA: Hypothesis Testing

Ho6: There are no statistically significant differences with return on investment and each line of service.

Ha6: There are statistically significant differences with return on investment and each line of service.

Anova: Single Factor
SUMMARY
Groups	Count	Sum	Average	Variance
A = Air	20	178	8.9	9.357895
B = Soil	20	182	9.1	3.042105
C = Water	20	140	7	6.631579
D = Training	20	108	5.4	1.410526
ANOVA
Source of Variation	SS	df	MS	F	P-value	F crit
Between Groups	182.8	3	60.93333333	11.9231	1.75888E-06	2.72494395
Within Groups	388.4	76	5.110526316
Total	571.2	79

Interpretation:

The ANOVA p-value is 1.76E-06 which is less than our alpha of 0.05. Therefore, we reject the null hypothesis and accept the alternative hypothesis. There are statistically significant differences between return on investment and the four lines of service offered at Sun Coast.

References

Creswell, J. W., & Creswell, J. D. (2018).Research design: Qualitative, quantitative, and mixed methods approaches (5th ed.). SAGE.

Keysers, C., Gazzola, V., &Wagenmakers, E. J. (2020).Using Bayes factor hypothesis testing in neuroscience to establish evidence of absence. Nature neuroscience, 23(7), 788-799.