Alaska COVID-19 projection

The following information is from the Alaska Department of Health and Social Services COVID-19 website: This graph represents the daily COVID-19 case count in Alaska (yellow). Date of symptom onset was used. Gray bars represent data from the most recent 7 days, which was not included in the analysis due to incomplete data/delay in reporting. The blue dotted line represents the predicted daily case trajectory (assumed exponential), with the gray band representing the 95% Confidence Interval (estimate range) of the projection. For a complete description of the methods please view the Methods tab.

Projection statistics:

The modeled exponential trajectory can be one of growth (getting bigger) or decay (getting smaller). If in growth, the doubling time represents the projected amount of time it will take for the counts to double in size. This assumes a constant growth rate (r) from the observed data under an exponential trajectory. If in decline, the halving time represents the projected amount of time it will take for the counts to reduce in half. This also assumes a constant halving rate (r) from the observed data under an exponential trajectory. The 95% confidence intervals (CI) for these estimates are also provided.

Confidence intervals (CI) provide an indication of precision of an estimated parameter. Specifically, a 95% CI means that if we sampled the same population an infinite number of times, the generated CI's for each sample would contain the true population parameter in 95% of the cases, assuming no systematic (bias) error. Generally speaking however, we can interpret the CI as a range around a point estimate within which the true value is likely to lie with a specified degree of probability, assuming there is no systematic error (bias or confounding). If the sample size is small and subject to more random error, then the estimate will not be as precise, and the confidence interval would be wide, indicating a greater amount of random error. In contrast, with a large sample size, the width of the confidence interval is narrower, indicating less random error and greater precision. One can, therefore, use the width of confidence intervals to indicate the amount of random error in an estimate.