====== Sample Size Fallacy ======

The **[[Sample Size]] [[Fallacy]]** refers to the **[[misinterpretation]] or [[overestimation]] of the [[reliability]] of [[study]] findings based on an insufficient or inappropriately small sample size**. It occurs when conclusions are drawn with unwarranted confidence despite inadequate statistical power or representativeness.

===== Characteristics =====
  * Treating results from a **small or underpowered study** as if they were conclusive
  * Failing to account for **random variation**, **outliers**, or **false positives**
  * Reporting **subgroup differences** or **dose-response trends** in small samples as if statistically robust
  * Using limited data to justify broad or clinical recommendations

===== Consequences =====
  * Inflated **effect sizes** due to random variation
  * Increased risk of **type I (false positive)** and **type II (false negative)** errors
  * Misleading interpretations, especially in **exploratory** or **post hoc** analyses

===== Examples =====
  * A study with 12 patients per arm concluding that one drug is “more effective”
  * Subgroup analysis in a trial with 8 total responders
  * Descriptive statistics used to define “optimal dosing” without statistical significance

===== Why It Matters =====
  * Undermines **scientific validity**
  * Leads to **publication of spurious results**
  * Wastes resources on follow-up studies of **false leads**

===== Related Concepts =====
  * [[underpowered_study|Underpowered Study]]
  * [[publication_bias|Publication Bias]]
  * [[overgeneralization|Overgeneralization]]
  * [[rhetorical_inflation|Rhetorical Inflation]]
  * [[statistical_significance|Statistical Significance vs. Clinical Relevance]]

===== See Also =====
  * [[critical_review|How to identify flaws in scientific articles]]
  * [[effect_size|Effect Size Interpretation]]