9.11
Probar una afirmación sobre la media: DE de población conocida
Aquí se explica un procedimiento completo para probar la hipótesis sobre una media poblacional.
Para estimar una media poblacional es necesario que la…
La exposición a diferentes longitudes de onda de luz puede afectar la tasa de desove en el pez cebra.
Por lo tanto, se lleva a cabo un experimento en el que un grupo de 50 peces cebra se expone a la luz azul y su tasa de desove se compara con el grupo de control que tiene el mismo tamaño de muestra.
Para probar la afirmación, comenzamos con la hipótesis nula de que la tasa media de desove en el grupo expuesto y en el grupo de control es la misma y una hipótesis alternativa de que la luz azul aumenta la tasa media de desove.
El experimento mostró que la tasa media de desove en el grupo expuesto fue de 550 por pez, mientras que en el grupo de control fue de 250.
El cálculo del estadístico de prueba a partir de estos datos requiere un conocimiento previo de la desviación estándar de la población, que es 146, conocida a partir de los estudios anteriores.
Con estos datos, podemos calcular el estadístico z y observar que se encuentra en la región crítica con un nivel de significación de 0,05.
Además, el valor P para este estadístico z es inferior a 0,05, lo que concluye que la luz azul mejora la tasa de desove en el pez cebra.
View the full transcript and gain access to JoVE Core videos
Q1: Why is population standard deviation important when testing a claim about the mean?
When population standard deviation is known, hypothesis testing about the mean becomes straightforward using the z distribution and normality assumption. Known standard deviation allows direct calculation of the z statistic from sample data, enabling comparison with critical values and significance levels. This method is rare in practice but highly efficient when the parameter is available from prior studies.
Q2: What conditions must be met before testing a hypothesis about a population mean?
Sample data must be collected from randomly selected samples with no sampling bias, and the sample size must exceed 30 to satisfy normality assumptions. The population standard deviation must be known beforehand. These conditions ensure the z distribution applies reliably and the test statistic accurately reflects the population parameter.
Q3: How do null and alternative hypotheses differ in a mean testing scenario?
The null hypothesis states that the population mean equals a specific value, representing no effect or change. The alternative hypothesis uses an inequality sign to claim the mean differs from that value. The direction of the inequality determines whether the test is right-tailed, left-tailed, or two-tailed, guiding the critical region placement.
Q4: What does it mean when a z statistic falls in the critical region?
When the calculated z statistic falls in the critical region at a chosen significance level like 0.05, it indicates the sample data provides strong evidence against the null hypothesis. This outcome leads to rejecting the null hypothesis and supporting the alternative hypothesis, suggesting a statistically significant effect exists.
Q5: How do the traditional method and P-value method compare in hypothesis testing?
The traditional method compares the calculated z statistic directly with the critical z score from the z table at a specified confidence level. The P-value method calculates the probability of observing sample data as extreme as or more extreme than what was observed, assuming the null hypothesis is true. Both methods lead to the same conclusion about rejecting or failing to reject the null hypothesis.
Q6: In the zebrafish spawning study, how did researchers conclude that blue light enhances spawning rate?
The z statistic calculated from the sample means (550 versus 250) and known population standard deviation of 146 fell within the critical region at the 0.05 significance level. Additionally, the P-value was less than 0.05, providing strong statistical evidence that blue light increases mean spawning rate compared to the control group.
Q7: When would you use testing a claim about mean with unknown population SD instead of known SD?
Most realistic situations involve unknown population standard deviation, requiring the t distribution instead of the z distribution. When population standard deviation is unavailable from prior research, you must estimate it from sample data. This approach is more common in practice than testing with known standard deviation.