Statistcs research paper - due in 4 days

Inferential Statistics

Inferential Statistics to Use for Data Analysis

The data gathered from Maple Grove Hospital will be organized into an excel spreadsheet for data analysis purposes. Excel is one of the data analysis programs that have a wide range of statistical parameters that are of importance to this research study (Remenyi, Onofrei & English, 2011). If need be, the datasheet will be imported into Statistics Package For Social Sciences Tool (SPSS) to acquire any measure that cannot be computed through Microsoft Excel data analysis tool.

Under inferential statistics, the data collected will be used for:

i) Hypothesis testing

ii) Evaluation of normality of the sampled data

i) Hypothesis Testing

Hypothesis testing will be done by performing a t-test. Medicare data and Medicaid data will be treated as two different cases as they represent two different entities in this study. The same null and alternate hypothesis will be tested, in an attempt to establish whether the mean of the adult patients who benefit from these two programs at Maple Group Hospital is less than the mean of children that benefit from the same programs.

The hypothesis being tested will therefore use a one-tailed t-test method with two sets of data for the two programs. This will represent the mean of adult-patient beneficiaries and the mean of the children-patient beneficiaries for each case.

The null and alternate hypothesis under investigation will therefore be:

Null hypothesis Ho : Mean of adults is equal to the children (µ 1= µ 2)

Alternate hypothesis Ha: Mean of adults is greater than mean of children (µ 1> µ 2)

After feeding the data in an excel spreadsheet, the data analysis tool will be used to output the results of the t-test with a confidence level set at 95% (alpha value α= 0.05). This output will represent the calculated value of t-test (t-statistic). A table of the t-values with a degree of freedom of (n-1) will be used to determine the tabulated value of t-test at the stated significance level of 5% (confidence level =95%).

As indicated by Dalgaard (2008), the null hypothesis should be rejected if the value of t-statistic generated by the excel data analysis software is greater than the value of t-test obtained from the t-test table. If the null hypothesis will be retained, the p-value will also be evaluated either from the software or from t-test table to show how strong the data is consistent with the null hypothesis of the data.

ii) Analysis of Parameters

The main parametric measures that will be used to analyze this data are ANOVA and Chi- Square test. As noted by Peck and Devore (2012), analysis of ANOVA and Chi-square test help in testing the normality of the analyzed data. Both Chi –square test and ANOVA tests will be determined by use of the data analysis tool used. The two measures will be used to ascertain whether the sample is a true representative of the population sampled, giving insights on whether one is justified to draw conclusions based on the outcome of hypothesis testing.

Reference

Top of Form

Dalgaard, P. (2008). Introductory Statistics with R. New York: Springer.

Bottom of Form

Top of Form

Peck, R. & Devore, J. L. (2012). Introduction to Statistics and Data Analysis. Boston, MA: Brooks/Cole Cengage Learning.

Top of Form

Remenyi, D., Onofrei, G., & English, J. (2011). An Introduction to Statistics using Microsoft Excel: Research Textbook Collection. Reading: Academic Conferences Publishing International.

Bottom of Form

Bottom of Form