Can spss be used for bootstrap?

If you want to know more about bootstrap, you can click: bootstrap tutorial

SPSS is the first statistical software in the world to adopt a graphical menu-driven interface. Its most outstanding feature is that the operation interface is extremely friendly and the output results are beautiful. It displays almost all functions in a unified and standardized interface, using Windows window mode to display functions of various management and analysis data methods, and dialog boxes to display various function options. As long as users master certain Windows operating skills and are proficient in statistical analysis principles, they can use this software to serve specific scientific research work.

spss can be used for bootstrap. The following is an introduction to the principles and engineering.

1. Principle:

An important statistical method in non-parametric statistics that estimates the variance of statistics and then performs interval estimation, also known as For self-help method. The core ideas and basic steps are as follows:

1. Use resampling technology to extract a certain number of samples (given by yourself) from the original samples. This process allows repeated sampling.

　2. Calculate the given statistic T based on the extracted samples.

　3. Repeat the above N times (generally greater than 1000) to obtain N statistics T.

4. Calculate the sample variance of the above N statistics T to obtain the variance of the statistics.

It should be said that Bootstrap is a popular statistical method in modern statistics, and it works well when working with small samples. Confidence intervals can be constructed through the estimation of variance, and its application scope is further extended.

Specific sampling method example: If you want to know the number of fish in the pond, you can first extract N fish, mark them, and put them back into the pond. Carry out repeated sampling, draw M times, and draw N fish each time. Examine the proportion of marked fish among the fish drawn each time, and calculate the statistics based on the proportion of M times.

2. Supported process

1. Frequency

　◎Statistical tables support mean, Bootstrap estimates of standard deviation, variance, median, skewness, kurtosis, and percentiles. ◎The frequency table supports bootstrap estimation of percentages.

2. Descriptive

◎The descriptive statistics table supports bootstrap estimates of mean, standard deviation, variance, skewness and kurtosis.

3. Explore

◎The description table supports mean, 5% trimmed mean, standard deviation, variance, median, skewness, kurtosis and inner distance The bootstrap estimate. ◎M estimator scale supports Huber’s M estimator, Tukey’s dual weight, Hampel’s M estimator and Andrew’s Wave’s bootstrap estimator. ◎The percentile table supports bootstrap estimation of percentiles.

4. Crosstab

◎The directional measurement table supports the bootstrap estimation of Lambda, Goodman and Kruskal Tau, uncertainty coefficient and Somers' d. ◎The symmetry scale supports Phi, Cramer's V, contingency coefficient, Kendall's tau-b, Kendall's tau-c, Gamma, Spearman correlation and Pearson's R bootstrap estimates. ◎The risk assessment table supports bootstrap estimation of odds ratio. ◎Mantel-Haenszel general odds ratio table supports bootstrap estimation and significance test of ln(Estimate).

5. Mean

◎The report table supports mean, median, group median, standard deviation, variance, kurtosis, skewness, and harmonic mean and bootstrap estimates of geometric means.

6. One-sample T test

◎The statistical table supports bootstrap estimation of mean and standard deviation. ◎The test table supports bootstrap estimation and significance testing of mean differences.

7. Independent sample T test

◎The group statistical table supports bootstrap estimation of mean and standard deviation. ◎The test table supports bootstrap estimation and significance testing of mean differences.

8. Paired sample T test

◎The statistical table supports bootstrap estimation of mean and standard deviation. ◎The correlation table supports bootstrap estimation of correlation. ◎The test table supports bootstrap estimation of the mean.

9. One-way analysis of variance

◎The descriptive statistics table supports bootstrap estimation of the mean and standard deviation. ◎Multiple comparison tables support bootstrap estimation of mean differences. ◎The contrast test table supports bootstrap estimation and significance testing of contrast values.

10. GLM single variable

　◎The descriptive statistics table supports bootstrap estimation of mean and standard deviation. ◎The parameter estimate table supports bootstrap estimation of coefficients, B and significance testing. ◎The comparison results table supports bootstrap estimation and significance testing of differences. ◎Estimated marginal mean: The estimate table supports bootstrap estimation of the mean. ◎Estimated marginal means: Pairwise comparison tables support bootstrap estimation of mean differences. ◎Pairwise comparison test: Multiple comparison tables support bootstrap estimation of mean differences.

11. Bivariate correlation

　◎Descriptive statistics table supports bootstrap estimation of mean and standard deviation. ◎The correlation table supports bootstrap estimation of correlation.

12. Partial correlation

　◎The descriptive statistics table supports bootstrap estimation of mean and standard deviation. ◎The correlation table supports bootstrap estimation of correlation.

13. Linear regression

　◎The descriptive statistics table supports bootstrap estimation of mean and standard deviation. ◎The correlation table supports bootstrap estimation of correlation. ◎The model summary table supports Durbin-Watson's bootstrap estimation. ◎The coefficient table supports bootstrap estimation and significance testing of coefficients and B. ◎The correlation coefficient table supports bootstrap estimation of correlation. ◎The residual statistics table supports bootstrap estimation of mean and standard deviation.

14. Ordinal Regression

◎The parameter estimate table supports bootstrap estimation of coefficients and B and significance testing.

15. Discriminant analysis

◎The standardized rule discriminant function coefficient table supports bootstrap estimation of standardized coefficients. ◎The canonical discriminant function coefficient table supports bootstrap estimation of non-standardized coefficients. ◎The classification function coefficient table supports bootstrap estimation of coefficients.

16. GLM multivariable

◎The parameter estimate table supports bootstrap estimation of coefficients and B and significance testing.

17. Linear mixed model

　◎The fixed effects estimate table supports bootstrap estimation and significance testing of estimated values. ◎The covariance parameter estimate table supports bootstrap estimation and significance testing of estimated values.

18. Generalized Linear Models

◎The parameter estimate table supports bootstrap estimation of coefficients, B and significance testing.

19. Cox regression

◎The variable table in the equation supports bootstrap estimation of coefficients, B and significance testing.

20. Binary Logistic Regression

◎The variable table in the equation supports bootstrap estimation of coefficients, B and significance testing.

21. Multinomial Logistic Regression

◎The parameter estimate table supports bootstrap estimation and significance testing of coefficients and B.

The above is the detailed content of Can spss be used for bootstrap?. For more information, please follow other related articles on the PHP Chinese website!