# Type I error

## Rejecting the null hypothesis when it should not be rejected, a false positive

Hypothesis testing is not a perfect and infallible scientific method. Inferential statistics make inferences, not true causal effects to populations. Statistics, in and of itself, is a flawed mathematical science that necessitates certain assumptions be met before inferences can even be interpreted.

A Type I error is where sample data yields a decision of "reject" the null hypothesis (meaning there is a treatment effect or statistical significance) when the decision should be made to "reject" the null hypothesis (meaning there is NOT a treatment effect or there is NOT a significant difference). Type I errors are also known as "false positives."

Type I errors often occur in non-probability samples or where anomalies are found in the sampling frame. Setting the alpha value at .05 helps detract from this occurrence because significant effects are only thought to occur 5% of the time. Any statistical finding landing in the critical area is thought to be an extreme value that would only occur 5% of the time if the experiment was performed 100 times.

Type I errors can be potentially dangerous. An over-inflated effect that comes from a non-probability sampling methodology can show evidence of an efficacious effect when one does not truly exist. In order to detract from these occurrences, researchers can choose more stringent alpha values of .01 or .001 where the chance of making a Type I error decrease drastically.

A Type I error is where sample data yields a decision of "reject" the null hypothesis (meaning there is a treatment effect or statistical significance) when the decision should be made to "reject" the null hypothesis (meaning there is NOT a treatment effect or there is NOT a significant difference). Type I errors are also known as "false positives."

Type I errors often occur in non-probability samples or where anomalies are found in the sampling frame. Setting the alpha value at .05 helps detract from this occurrence because significant effects are only thought to occur 5% of the time. Any statistical finding landing in the critical area is thought to be an extreme value that would only occur 5% of the time if the experiment was performed 100 times.

Type I errors can be potentially dangerous. An over-inflated effect that comes from a non-probability sampling methodology can show evidence of an efficacious effect when one does not truly exist. In order to detract from these occurrences, researchers can choose more stringent alpha values of .01 or .001 where the chance of making a Type I error decrease drastically.

Click on the

**Type II Error**button to continue.## Hire A Statistician - Statistical Consulting for Professionals

**DO YOU NEED TO HIRE A STATISTICIAN?**

Eric Heidel, Ph.D. will provide statistical consulting for researchers, professionals, and organizations at $100/hour. Secure checkout is available with Stripe, Venmo, Zelle, or PayPal.

- Statistical Analysis
- Research Design
- Sample Size Calculations
- Diagnostic Testing and Epidemiological Calculations
- Survey Design and Psychometrics