(Basic Statistics for Citizen Data Scientist) Dealing with Missing Data This tutorial is based on the Real Statistics Resource Pack. Another problem faced when collecting data is that some data may be missing. For example, in conducting a survey with ten questions, perhaps some of the people who take the survey don’t answer all ten …
Day: January 23, 2021
(Basic Statistics for Citizen Data Scientist) Box Plots with Outliers Excel 2016 has added a Box and Whiskers chart capability. To access this capability for Example 1 of Creating Box Plots in Excel, highlight the data range A2:C11 (from Figure 1) and select Insert > Charts|Statistical > Box and Whiskers. The chart shown on the right side of Figure 1 will …
(Basic Statistics for Citizen Data Scientist) Outliers and Robustness One problem that we face in analyzing data is the presence of outliers, i.e. a data element that is much bigger or much smaller than the other data elements. For example, the mean of the sample {2, 3, 4, 5, 6} is 4, while the mean of …
(Basic Statistics for Citizen Data Scientist) ROC and Classification Table Data Analysis Tool Real Statistics Data Analysis Tools: The Real Statistics Resource Pack supplies the ROC Curve and Classification Table data analysis tool which provides an easier way to construct the ROC curve and classification table. We show how this is done for Example 1 of Classification Table and ROC Curve. …
(Basic Statistics for Citizen Data Scientist) AUC Confidence Interval For large samples, AUC (area under the curve for a ROC curve) is approximately normally distributed, and so a 1-α confidence interval for AUC may be calculated as described in Confidence Interval for Sampling Distributions. The confidence interval is equal to AUC ± se · zcrit where zcrit is the two-tailed critical value …