- Bootstrap methods assume that our sample is an SRS and will give trustworthy conclusions only if this condition is met.
-
These methods make no assumptions about the distribution your data comes from.
- For inference for a single population mean, single-parameter bootstrap tests are an alternative to the one-sample $t$-test when the guidelines for its use are not met (such as when the data is strongly skewed or has outliers with low sample size).
- For inference for a single population proportion, single-parameter bootstrap tests are an alternative to the one-sample $z$-test when the guidelines for its use are not met, that is when the number of successes and failures are not large enough.
| Data | Frequencies | |
| Sample data goes here (enter numbers in columns): | ||
| Number of Successes | Sample Size | |
| Test for a: | ||
| $H_0: \mu =$ $=\mu_0$ | ||
| $H_a:\mu$ $\mu_0$ | ||
| Level of Significance: $\alpha=$ | ||
| Number of Bootstrap Samples: | ||
| Input data as Frequency Table: |
Population Mean
| Sample Size: | $n=$ |
| Sample Mean: | $\overline{x}=$ |
| Lower Critical Value: | $\mu_{L}^*=$ |
| Upper Critical Value: | $\mu_{U}^*=$ |
| $p\mbox{-value}$: | |
| Frequency | ||
| Sample Data | Bootstrap Means $\mu^*$ |
Population Proportion
| Sample Size: | $n=$ |
| Sample Proportion: | $\hat{p}=$ |
| Lower Critical Value: | $p_{L}^*=$ |
| Upper Critical Value: | $p_{U}^*=$ |
| $p\mbox{-value}$: | |
| Frequency | ||
| Failures and Successes | Bootstrap Proportions $p^*$ |
Population Median
| Sample Size: | $n=$ |
| Sample Median: | $M=$ |
| Lower Critical Value: | $M_{L}^*=$ |
| Upper Critical Value: | $M_{U}^*=$ |
| $p\mbox{-value}$: | |
| Frequency | ||
| Sample Data | Bootstrap Medians $M^*$ |
Population Standard Deviation
| Sample Size: | $n=$ |
| Sample Standard Deviation: | $s=$ |
| Lower Critical Value: | $\sigma_{L}^*=$ |
| Upper Critical Value: | $\sigma_{U}^*=$ |
| $p\mbox{-value}$: | |
| Frequency | ||
| Sample Data | Bootstrap Standard Deviations $\sigma^*$ |