Predicting When Your Survey Will Actually Finish

Fieldwork always follows the same pattern. Big spike on day one when the eager respondents come in. Solid numbers on days two and three. Then it drops. By day five you're getting half the daily completions you got on day one. By day ten you're in the long tail, grinding out 20 completes a day when you need 50 to finish on time.

This decay pattern is predictable. The tool models it using exponential decay curves calibrated to typical panel response patterns, and projects forward to tell you when you'll hit your completion target.

Why this matters for operations

If the projection says you'll finish in 14 days but the client expects results in 10, you know on day three. Not day eight. That early warning gives you time to release additional sample, send reminders, bump the incentive, or manage the client's timeline expectations before it becomes a crisis.

The tool includes soft launch milestones. Most studies do a soft launch of 10-20% of the total sample to check data quality before going full field. The estimator factors in the soft launch period and adjusts the completion forecast accordingly.

Daily completion projections are shown as a chart with actual versus forecasted lines, so you can see immediately whether you're tracking ahead of, on pace with, or behind the model's prediction. Persistent under-performance against the forecast is the signal to take action.

Tech stack

React 18.2 + Babel CDN. The decay model uses a simple exponential function: completions(t) = A × e^(-kt), where A is the initial rate and k is the decay constant. The model parameters are estimated from the first few days of actual field data. Chart rendering is plain SVG.