The measure of dispersion is used to describe the spread of data around a central value. In the context of a data set containing actual and projected sales, the measure of dispersion will help to understand the variability or consistency of sales figures. The variance is themost appropriate statistical method for finding the measure of dispersion because it calculates the average of the squared differences from the Mean, providing a clear picture of data spread. It is especially useful in comparing the spread between different data sets and understanding the distribution of data points.
Mean is a measure of central tendency, not dispersion.
Correlation measures the relationship between two variables, not the spread of a single variable.
Confidence intervals are used to estimate the range within which a population parameter will fall, but they do not measure dispersion within the data set itself.
Reference:
Measures of Dispersion in Statistics1
Measures of Dispersion - Definition, Formulas, Examples2
Statistical dispersion - Wikipedia3

For a dashboard that aims to tell a story about sales and the sales customer ratio, a column chart is an effective choice. Column charts are particularly useful for showing data changes over a period of time or for illustrating comparisons among items. In this case, a column chart can clearly display the sales figures for each site, allowing for easy comparison across different sites. Additionally, it can be used to represent the sales customer ratio by showing the proportion of sales per customer, which can provide insights into customer behavior and sales effectiveness.
Line charts are best suited for displaying data trends over time, rather than for comparing individual categories.
Pie charts could show the proportion of sales for each site, but they are not as effective as column charts for comparing multiple categories.
Scatter charts are used to show the relationship between two variables, which is not the focus in this scenario.
Reference:
Effective Use of Column Charts1
Choosing the Right Chart for Your Data2
Sales Dashboards: Examples & Templates3

The rating variable in a survey where participants rate a company on a scale of one to ten is best described as ordinal. This is because the ratings are ranked in order, with each number representing a position on a scale of satisfaction or quality. The numbers are not just labels (which would be nominal), nor do they represent a continuous spectrum (which would be continuous). They also do not fit the definition of categorical, as that implies non-ordered groups or categories. In an ordinal scale, the order of the values is significant and meaningful12.
Reference:
Qualtrics explains that ordinal scales have answer sets that occur in a logical and systematic order, providing qualitative data.
Zonka Feedback describes a 1 to 10 rating scale survey, indicating that the numbers represent a ranking from most negative to most positive experience, which aligns with the characteristics of an ordinal scale.

1. Duplicates
2. Misspellings
The most common data quality issues are difficult to resolve in Excel because of their rigidity. It forces analysts to do a ton of manual work, which results in a high probability of an error being introduced to the data set. Those common issues include:
- Blanks
- Nulls
- Outliers
- Duplicates
- Extra spaces
- Misspellings
- Abbreviations and domain-specific variations
- Formula error codes
When introduced, these errors can skew or even invalidate the resulting analysis. A smart tool would minimize the possibility of error by automating the manual work. In Excel, you might look for data quality issues in one of two ways. First, you might use auto filters on specific columns to scan for anomalies and blanks or you might use a pivot table to find gaps and discrepancies.
In either case, you're scanning for the anomalies yourself. Suffice it to say that's not a very efficient process. It also means accuracy is only as good as the analyst's eye, so the probability of error varies throughout the day.