.DOCX

# Confidence Interval

For this discussion, you will state a research question on the difference in two population means, a null hypothesis, and an alternative hypothesis on a research topic in your field.

• Address the question 1 (p. 144) in your Quantitative Research Methods for Professionals in Education and Other Fields text:

• Which would you choose, if you had to choose between using estimation with confidence intervals and measures of statistical significance? Why?

• How does this relate to your ability to make generalizations to the population from which you have taken a random sample?

• Which would you use in a Capella dissertation? Why?

Research Question

Does the rapid growth and change in technology cause problems for digital forensics experts face difficulties in their investigations?

Null hypothesis (H0): There is no correlation exist between the rapidly changing technology and the difficulties the digital forensics experts face in their investigations.

Alternate hypothesis (Ha): There is a correlation between the rapidly changing technology and the difficulties the digital forensics experts face in their investigations.

"The parameter is an unknown constant and no probability statement concerning its value may be made." —Jerzy Neyman, original developer of confidence intervals.

According to Frost (2015) who is a scholar in statistics, confidence intervals serve as good estimates of the population parameter because the procedure tends to produce intervals that contain the parameter. In statistics margin of error can play an important role, because the margin of error indicates the amount of uncertainty that surrounds the sample estimate of the population parameter.

You can use confidence intervals to assess whether the sample estimate is precise. In a narrow confidence interval between 90 and 110 may indicate a more precise estimate of the population parameter than a wider confidence interval between 50 and 150 (Frost, 2015).

As we did in previous assignments we can use P values or we can use confidence intervals to determine the results whether they are significant or not. If a hypothesis test produces both, these results will agree.

According to Frost (2015) the confidence level is equivalent to 1 – the alpha level. So, if your significance level is 0.05, the corresponding confidence level is 95%. Both null hypothesis mean and sample mean of confidence interval are always in agreement. You need to compare the correct pairs of P values and confidence intervals. In real world statistically significant effect is not meaningful, the effect might be too small to be of any practical value for the real world.

Therefore I would pick confidence intervals, because confidence intervals not only indicate magnitude and precision of the estimated effect, they also allow you to assess characteristics with the statistical significance which is more meaningful in real world. I would use Confidence intervals in my Capella dissertation.

Reference