Click on the following links. Please note these will open in a new window.

Article 1: Brennan, R. L. (2007). Unbiased estimates of variance components with bootstrap procedures. Educational and Psychological Measurement, 67(5), 784–803. doi:10.1177/0013164407301534.

Summary/Abstract: This article provides general procedures for obtaining unbiased estimates of variance components for any random-model balanced design under any bootstrap sampling plan, with the focus on designs of the type typically used in generalizability theory. The results reported here are particularly helpful when the bootstrap is used to estimate standard errors of estimated variance components. For the p × i design, Wiley (2000) provided formulas for correcting for bias in bootstrap estimates of variance components. This article extends Wiley’s results to any design and any bootstrap procedure. There are important differences in approach, however. In particular, in this article unbiased estimates of variance components are obtained directly for any bootstrap sample through the use of modified expected T-term (uncorrected sums of squares) equations.

Questions to Consider:

1. The author found that through repeated simulations the:

1. bootstrap methodology was robust and error-free.
2. bootstrap methodology was often poor and biased.
3. estimated standard errors were often poor and biased.
4. estimated standard errors were robust and error-free.

2. What does the author claim is a flaw in using bootstrapping techniques and how does the T-term equation for account for it?

3. The author considers the use of modified expected T-term equations as:

1. unbiased estimates.
2. biased estimates.
3. negatively skewed estimates.
4. positively skewed estimates.
    

Article 2: Feng-Yuan, X., & Feng-Jie, X. (2013). Research note: A study of outliers of international tourism statistics. Tourism Economics, 19(5), 1215–1227. doi:10.5367/te.2013.0233.

Summary/Abstract: As international tourism is an industry that is easily impacted by external shocks, there is always structural mutation of the time series related with it, which causes the existence of outliers. Those outliers will have an impact on analyses based on such data. Using quarterly data from 1994 to 2006, this paper detects outliers in the time series of international tourists to China and finds that the number of international tourists during the second and the third quarters of 2003 are outliers of the time series. To eliminate the impact of outliers, the paper uses the SARIMA model to forecast the values of outliers. By replacing the original value with the forecasted values, the authors conduct a co-integration analysis with the new time series and the corresponding quarterly gross domestic product (GDP) data. The results show that research conducted without considering outliers overestimates the effect of international tourism on economic growth.

Questions to Consider:

1. Concerning outliers in their data, what did the authors determine was there effect?

2. How did the authors detect outliers in their data set?

1. Kendall’s Tau
2. Cronbach’s Alpha
3. Chi square
4. Welsh-Kuch statistic

3. When detecting outliers, _____ of the regression model must be _____ distributed.

1. residue; normally
2. residue; non-normally
3. slope; normally
4. slope; non-normally