Biostats Week 7 Flashcards
µ
Mu. Mean of a population or probability distribution
t
1) a particular probability distribution or 2) a value that obeys that distribution
z-score
s (standard deviation)
s
standard deviation
µ
mean
σ
Sigma. Standard deviation of a population.
m
Mean of a sample
s^2
Sample variance
n
Number of cases
Median
score that divides a distribution in half; the mathematical midpoint
Mode
The value that appears most often during the dataset
Bimodal distribution
a distribution containing two numeric values that appear with equal frequency
Variability
extent to which the scores are dispersed around the mean
Range
difference between the highest and lowest values in a distribution
Deviations from the mean
calculated by subtracting the mean from a given score; sum of the deviations will always equal zero
Mean deviation
Sum of mathematically absolute deviations from the mean of the distribution
Variance
equal to the standard deviation squared
Standard deviation
Standard deviation: square root of the variance
s=standard deviation for sample, σ=standard deviation for a population
Z/Z-score
Z (Z Score): point along the baseline of a standardized normal curve
Hypothesis
Hypothesis: statement of expectations
Null hypothesis
Null hypothesis: statement of equality; statement of no difference; statement of chance
Critical value
Critical value: point on a distribution that marks the beginning of the critical region; point of comparison when making decision about null hypothesis
Calculated test statistic
Calculated test statistic: result of a hypothesis-testing procedure; value that is compared to critical value
Critical region
Critical region: portion of distribution that contains all the values that allow you to reject the null hypothesis; also known as region of rejection
Type I Error
Type I error: rejection of the null hypothesis when it is in fact true
Type II Error
Type II error: failure to reject the null hypothesis when it is false
Single sample with sigma unknown
Single sample with sigma unknown: standard error of the mean is estimated and t is used
Single sample with sigma known
Single sample with sigma known: standard error of the mean is calculated in a direct fashion and Z is used
t-statistic
Used when we do not know the standard deviation of the population mean.
How to calculate t
(Sample std dev/√(sample size))
Matched samples (related):
Samples selected in such a way that cases included in one sample are related to cases in another (before & after sampling, etc)
Standard error of mean difference:
Standard deviation of repeated sampling of mean differences between scores reflected in 2 samples
A nurse researcher wishes to determine if there is a difference in the mean serum phosphorus level for a random sample of clients who have puritis and a random sample of clients who do not have puritis. What would be an appropriate test?
t-test for independent groups
Your study includes an alpha of 0.05 and a power of 0.80. You conduct a student t-test, which has a large sample and a p-value of 0.04. What type of error might you make?
Type I
In order to calculate the necessary sample size for your study you will need to know:
Effect size
Power
You are asked to design a study determining whether there is a difference in the average fasting blood glucose for individuals with diabetes randomized either to a strictly dietary intervention or to a diet and exercise intervention. What are you investigating?
Difference
If you select an alpha of 0.05 and a power of 0.80 for your study and your independent t-test for the difference in the mean serum potassium level of kidney dialysis patients and kidney transplant patients has a p-value of 0.02. You know this means:
There is a significant difference between the 2 groups
Your study includes an alpha of 0.05 and a power of 0.80. You conduct a student t-test, which has a p-value of 0.07. What type of error might you make?
Type II
How does effect size increase statistical power?
The smaller the effect size the more overlap between our distributions and the lower the statistical power.
You conduct a study to determine if there is a difference in average number of hours slept each week between husbands and wives.What would be an appropriate test?
t-test for independent groups
The following is a NONDIRECTIONAL hypothesis.
The relationships among gender identity, religiosity, and social actions are weaker among Arab women than among Jewish women.
FALSE
You anticipate a large effect size in your study, therefore you will need a large sample size.
FALSE
