← Every exhibit
What is measurement error not?
| Object | Core question | Why it is different |
|---|---|---|
| Measurement error | Does the indicator represent the declared target under a stated model? | The target-to-observation relationship is the object |
| Missing data | Is the observation unavailable, censored, or not collected? | Absence of a record is not automatically a value of zero or a noisy value |
| Selection bias | Which units entered the observed comparison? | The population boundary can change even when each recorded value is accurate |
| Confounding | Which common causes affect treatment and outcome? | A causal contrast can fail even with a well-measured variable |
| Common-method bias | Could the method create covariance among variables? | The shared measurement context is the object, not one indicator's target gap |
| Measurement invariance | Does the instrument operate comparably across groups or time? | The comparison across groups is the object |
| Model residual error | What remains unexplained after a model is specified? | A residual is not automatically the measurement error in an input or outcome |
| Data provenance | Can the recorded value be traced through its source and transformations? | Provenance describes the path; it does not by itself establish construct validity |
Swipe or scroll horizontally if the table is wider than your screen.
Reference & Evidence
Source: Table from this essay. Sources and interpretation are given in the article.
Related exhibits
-
The measurement-error indicator audit
From the essay What is measurement error? The gap between a construct and its indicator
-
What are the construct, domain, indicator, and observation?
From the essay What is measurement error? The gap between a construct and its indicator
-
Which mechanisms can create the gap?
From the essay What is measurement error? The gap between a construct and its indicator