|
Size: 1500
Comment:
|
← Revision 7 as of 2013-03-08 10:17:19 ⇥
Size: 1713
Comment: converted to 1.6 markup
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 1: | Line 1: |
| = Bootstrap Confidence Interval for the percentage bend correlation = | |
| Line 2: | Line 3: |
= Bootstrap Confidence Interval for the percentage bend correlation = It should be mentioned that in lot of cases the percentage bend correlation is so robust to outliers and changes in sampling distributions that there is little or no variation in the correlations computed for each of the bootstrap samples. The bootstrapping, however, may be done in the EXCEL spreadsheet as follows: |
You may wish to back up your data file before doing the bootstrap as each bootstrapped sample overwrites the original data. The bootstrapping may be done in the EXCEL spreadsheet as follows: |
| Line 11: | Line 7: |
| 1. Firstly highlight the cells cell AO3 which contains the percentage bend correlation in the spreadsheet |
|
| Line 13: | Line 11: |
| 1. A dialogue box should appear: prompting you to insert the original sample which are the cells in columns A and B contianing the two sets of data to be correlated | 1. A dialogue box should appear: prompting you to insert the original sample which are the cells in columns A and B containing the two sets of data to be correlated |
| Line 15: | Line 13: |
| 1. Next choose a block of unoccupied cells of the same size as the ones just chosen to represent the space where the bootstrap samples are written | 1. Next choose the same block of cells containing the data as above to represent the space where the bootstrap samples are written |
| Line 23: | Line 21: |
| 1. The results of each computation of the selected cell (percentage bend) for each bootstrap sample are outputted. These can be used to obtain 95% confidence intervals for the correlation. | 1. The results of each computation of the cell you selected in step one (the percentage bend) for each bootstrap sample are outputted in a sheet called 'Bootraw'. These can be used to obtain endpoints for a 95% confidence interval for the correlation using, for example, the percentile function by typing in a couple of cells commands of form: PERCENTILE(A2:A1001,0.025) and PERCENTILE(A2:A1001,0.975) in the outputted 'Bootraw' spreadsheet. |
Bootstrap Confidence Interval for the percentage bend correlation
You may wish to back up your data file before doing the bootstrap as each bootstrapped sample overwrites the original data. The bootstrapping may be done in the EXCEL spreadsheet as follows:
- Ensure that you only enter complete cases in the spreadsheet in columns A and B
- Firstly highlight the cells cell AO3 which contains the percentage bend correlation in the spreadsheet
- Go to Add-ins and click on 'bootstrap' in the far left corner which opens up the bootstrap macro written by Barreto and Howland.
- A dialogue box should appear: prompting you to insert the original sample which are the cells in columns A and B containing the two sets of data to be correlated
- Next choose the same block of cells containing the data as above to represent the space where the bootstrap samples are written
- Highlight cell AO3 which contians the percentage bend correlation and enter this in the box corresponding to the cell to be tracked
- You can keep the 1000 as the default number of bootstrap samples. (Wilcoxon's R programs uses 599 bootstrap samples). You can also ask for all the raw bootstrap values to be outputted.
- Click the 'Proceed' button
- The results of each computation of the cell you selected in step one (the percentage bend) for each bootstrap sample are outputted in a sheet called 'Bootraw'. These can be used to obtain endpoints for a 95% confidence interval for the correlation using, for example, the percentile function by typing in a couple of cells commands of form: PERCENTILE(A2:A1001,0.025) and PERCENTILE(A2:A1001,0.975) in the outputted 'Bootraw' spreadsheet.