Example of Bootstrapping for 2-sample means

A healthcare consultant wants to determine the difference in patient satisfaction ratings of two hospitals.

  1. Open the sample data, HospitalComparison.MTW.
  2. Choose Calc > Resampling > Bootstrapping for 2-Sample Means.
  3. In Samples, enter Rating.
  4. In Sample IDs, enter Hospital.
  5. Click Options. Enter 1 in Base for random number generator.
    Note

    Using Base for random number generator ensures that your results match the example.

  6. Click OK in each dialog box.

Interpret the results

The 95% CI indicates that the consultant can be 95% confident that the difference in population means of the patient satisfaction ratings of two hospitals is between 14.4 and 27.6. The histogram shows that the bootstrap distribution appears to be normal, so the consultant can trust the results.

Bootstrapping for Difference in Means: Rating by Hospital

Bootstrap Histogram for Rating by Hospital

Observed Samples Hospital N Mean StDev Variance Minimum Median Maximum A 20 80.30 8.18 66.96 62.00 79.00 98.00 B 20 59.30 12.43 154.54 35.00 58.50 89.00
Difference in Observed Means Mean of A - Mean of B = 21
Bootstrap Samples for Difference in Means Number of 95% CI for Resamples Average StDev Difference 1000 20.960 3.279 (14.400, 27.600)
By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy