Line Chart

A line chart represents data points connected by straight line segments, almost always used to show how a variable changes over a continuous ordered sequence, most commonly time — daily active users over a year, stock price over a trading session, temperature over a day. The connecting line itself carries real visual meaning beyond just marking individual data points: it implies continuity and trend, visually emphasizing the shape and direction of change over the sequence rather than any single point's value in isolation, which is the specific property that makes a line chart the standard choice for time series data and a poor choice for unordered categorical comparisons, where no meaningful continuous path exists between adjacent categories for a line to represent.

Because a line chart's primary signal is a trend's shape and direction rather than an absolute bar length compared against zero, the rule requiring a y-axis to start at zero — strict and important for bar charts — is more negotiable for line charts, though not without limits: a y-axis that's zoomed in too tightly around a narrow range of values can still visually exaggerate how dramatic an actual change looks, even without literally lying about the data, which is why "doesn't start at zero" isn't automatically disqualifying for a line chart the way it is for a bar chart, but an axis range chosen specifically to maximize visual drama rather than to genuinely inform is still a form of manipulation worth watching for. This distinction between bar charts and line charts on the zero-baseline question is one of the more commonly misunderstood rules in data visualization literacy, where "always start at zero" gets applied as a blanket rule when it actually applies more strictly to one chart type than the other.

Plotting multiple series on the same line chart using a dual y-axis — two different scales, one on the left and one on the right — is a frequently flagged source of misleading visualization, because the visual overlap or divergence between two differently-scaled lines can create the strong visual impression of a correlation between the two variables that the underlying numbers don't actually support, simply as an artifact of how the two independent scales happen to have been chosen; this specific pattern is common enough in misleading media and marketing visualizations that recognizing a dual-axis chart and specifically checking whether its implied correlation holds up under each series' actual, independently-scaled values is a standard, recommended data literacy check.

Smoothing — applying a moving average or other smoothing technique to a line chart's raw data before plotting it — is a common and often genuinely useful technique for making an underlying trend more visible through short-term, noisy fluctuation, but it comes with a real tradeoff worth stating explicitly: smoothing necessarily discards some real information (genuine short-term spikes or dips get averaged away along with random noise), and a smoothed line chart presented without disclosing that smoothing was applied, or without showing the raw underlying data alongside it, can obscure real volatility a viewer might reasonably want to see and interpret for themselves.

Read a line chart as the standard tool for showing change over a continuous sequence, where the connecting line itself — not just the individual data points — is the primary carrier of meaning: its relationship to the zero-baseline rule is genuinely different from a bar chart's, since a line chart's signal is trend shape rather than absolute bar length, and its two most common sources of real-world distortion — an overly narrow y-axis range and a misleading dual-axis scale comparison — are both specific, recognizable patterns worth actively checking for before trusting what a line chart's shape appears to be telling you.