Interpret the key results for Bootstrapping for 1-Sample Proportion

Complete the following steps to interpret a 1-sample proportion bootstrapping analysis. Key output includes the histogram, the estimate of the proportion, and the confidence interval.

Step 1: Examine the shape of your bootstrap distribution

Use the histogram to examine the shape of your bootstrap distribution. The bootstrap distribution is the distribution of proportions from each resample. The bootstrap distribution should appear to be normal. If the bootstrap distribution is non-normal, you cannot trust the results. The distribution is usually easier to determine with more resamples. For example, in these data, the distribution is ambiguous for 50 resamples. With 1000 resamples, the shape looks approximately normal. In this histogram, the bootstrap distribution appears to be normal.

Step 2: Determine a confidence interval for the population proportion

First, consider the proportion from the bootstrap sample, and then examine the confidence interval.

The proportion of the bootstrap sample is an estimate of the population proportion. Because the proportion is based on sample data and not the entire population, it is unlikely that the sample proportion equals the population proportion. To better estimate the population proportion, use the confidence interval.

Confidence intervals are based on the sampling distribution of a statistic. If a statistic has no bias as an estimator of a parameter, its sampling distribution is centered at the true value of the parameter. A bootstrapping distribution approximates the sampling distribution of the statistic. Therefore, the middle 95% of values from the bootstrapping distribution provide a 95% confidence interval for the parameter. The confidence interval helps you assess the practical significance of your estimate for the population parameter. Use your specialized knowledge to determine whether the confidence interval includes values that have practical significance for your situation.

Note

Minitab does not calculate the confidence interval when the number of resamples is too small to obtain an accurate confidence interval.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy