Question 1

How do you choose the right chart type for a given analytical question?

Accepted Answer

Match the chart to the relationship in the data: comparison across categories calls for bars, trends over continuous time call for lines, correlation between two numeric variables calls for a scatter plot, and distribution shape calls for a histogram or box plot. The question you are answering — not aesthetics — drives the choice.

Question 2

What is the data-ink ratio and how do you apply it when designing a chart?

Accepted Answer

Coined by Edward Tufte, the data-ink ratio is the proportion of ink (or pixels) in a chart that encodes actual data, divided by the total ink used. Maximizing it means removing every element — gridlines, borders, tick marks, legends, decorative shading — that does not carry information the viewer cannot infer from the remaining ink.

Question 3

What is the difference between a histogram, a bar chart, and a KDE plot, and when do you use each?

Accepted Answer

A bar chart displays counts or aggregates for distinct categories separated by gaps; a histogram displays the distribution of a single continuous variable by dividing it into adjacent bins with no gap; a KDE (kernel density estimate) plot is a smoothed, continuous approximation of the same distribution without requiring a bin-width choice.

Question 4

When should you avoid a pie chart, and what should you use instead?

Accepted Answer

Pie charts work only when you have two to three parts whose proportions differ substantially and sum to a meaningful whole. Beyond that, humans compare angles and arc lengths poorly, making slices of similar size indistinguishable. A sorted bar chart almost always communicates the same information more accurately.

Question 5

How do you choose colors that are both accessible to colorblind viewers and analytically meaningful?

Accepted Answer

About 8 % of men have red-green color deficiency, making the default red-green diverging palette unreliable. Use colorblind-safe palettes such as Okabe-Ito or ColorBrewer, match palette type to data type (sequential for ordered magnitudes, diverging for values around a meaningful midpoint, qualitative for unordered categories), and always add a redundant encoding such as shape, pattern, or label.

Question 6

What are the core principles of effective dashboard design?

Accepted Answer

An effective dashboard places the most critical metric in the top-left, groups related charts into logical sections, uses consistent scales and color across panels, limits the view to 5–9 metrics per screen, and is designed around a single primary question rather than trying to surface everything at once.

Question 7

How do you use a heatmap to visualize correlations, and what are its limitations?

Accepted Answer

A correlation heatmap encodes the pairwise Pearson or Spearman correlation coefficients of a numeric feature matrix as a color grid, making it fast to spot highly correlated feature pairs. Its limitations are that it shows only linear (or rank) association, hides nonlinear structure, and becomes unreadable past roughly 20 features.

Question 8

What makes a chart misleading, and how do you spot truncated y-axes, dual axes, and 3D distortion?

Accepted Answer

Charts mislead when visual area or slope no longer encodes the underlying ratio faithfully. The three most common traps are a truncated y-axis that magnifies trivial differences, dual axes that let the designer set any ratio between scales, and 3D perspective that foreshortens far elements and inflates near ones.

Question 9

What are small multiples, when should you use them instead of overlaying series on one chart, and what are the design rules?

Accepted Answer

Small multiples (also called trellis or facet charts) repeat the same chart structure across panels, one per category, using identical scales, axes, and visual encodings. They let viewers compare patterns across groups without the visual tangle of many overlapping lines or bars, and are the right choice when you have more than three to four groups or when overlap obscures individual trends.

Question 10

When should you use a logarithmic scale on a chart axis, and what does it change about interpretation?

Accepted Answer

A log scale is appropriate when data spans multiple orders of magnitude, when multiplicative growth is the natural frame of reference, or when you want to compare percentage change rather than absolute change. On a log scale, equal visual distances represent equal ratios, not equal differences.

Question 11

How do you structure a data story so it drives a decision rather than just presenting findings?

Accepted Answer

A data story has three components: a clear narrative arc (situation, complication, resolution), charts that each advance one argument rather than display all available data, and deliberate attention direction through annotation, color emphasis, and sequencing. The goal is that a viewer reading only the titles and callouts should understand the conclusion without reading every axis.