populations Flashcards Preview

Quiz 3 biostatistics > populations > Flashcards

Flashcards in populations Deck (11)
Loading flashcards...
0

How do you calculate standard error?

Standard error=Std Dev/Sqrt (n)

1

what's the difference between standard dev and standard error?

The standard error quantifies the variation of the sample mean. The standard deviation quantifies the variation of individual observations in a population.

2

What does the central limit theorem state?

The mean of the sampling distribution will be the same as the population mean, and the standard deviation of the sampling distribution will be equal to the standard error

standard error of the sample mean is smaller than the standard deviation of the population values

3

how would you calculate the 95 percent confidence interval of a sample?

Mean plus or minus two standard errors. This would tell you that the true mean would be within that range 95 percent of the time.

4

assume the true distribution of a population is bimodal. What happens if you calculate the sample means--what will the distribution look like?

It will have a normal distribution

5

What does the test statistic tell you?

which describes the disagreement between the observed data and the null hypothesis, relative to the std error

6

when would u reject a null hyp based on its t stat?

If it is greater than 2 or less than -2

7

What is type I error?

rejection of the null hypothesis when the null hypothesis is correct

8

What is type II error?

Acceptance of the null hypothesis when it is actually false

9

What is statistical power?

Measures the rate of Type II errors (accepting the null when it should be rejected). In this case, if the power is .80, the rate of type II is .20. Usually powers are set between .80-.90

10

What sample size do you need to calculate a specific power?

n =( (zα/2 x SD(Null) + z1-β x SD(Alternative))/
(mean(Null) - mean(Alternative)) )^2