When the expected value of the point estimator equals the population parameter, what do we call the point estimator?

When the expected value of a point estimator matches the population parameter, the point estimator is classified as unbiased. This means that on average, over many samples, the estimator will produce values that center around the true parameter being estimated, rather than systematically overestimating or underestimating it.

In statistical terms, if you repeatedly draw samples from a population and compute the point estimator for each sample, the mean of those estimators would equal the actual value of the parameter in question. A point estimator being unbiased is a desirable property because it implies that the estimator does not have a tendency to deviate in one direction from the actual population parameter.

Other properties mentioned in the options address different characteristics of estimators. Consistency refers to the property that as sample sizes increase, the estimates converge in probability to the actual parameter. Robustness indicates the estimator's resilience to violations of assumptions, while being biased would imply that the expected value of the estimator does not equal the population parameter. Therefore, identifying the point estimator as unbiased recognizes its accuracy and reliability in estimation.