Statistics Flashcards
A type of statistical test that is used with cardinal data, requires population is normal or meets rules of Central Limit Theorem, and is associated with an increased statistical power
Parametric Test
A type of statistical test that is used with ordinal or nominal data or unknown distribution or fail rules of Central limit theorem and is associated with less power than parametric counterparts
Non-Parametric Test
A test that is used to compare expected value(s) with a sample mean OR or a difference between two samples. This method requires the knowledge of population standard deviation, normal population or normal sampling distribution, and rarely a unknown standard deviation, large n (>30) then t= z
Z Test
A test that is used to compare a sample mean with a population mean, it is used to determine if sample belongs to a population with a known population mean (u) and standard deviation (o’)
p = normcdf(z) ; if z is negative (multiply by 2 for 2-tailed test)
p = 1-normcdf(z); if z is positive (multiply by 2 for 2-tailed test)
One sample Z test
[h,p,ci,zstat] = ztest (x,mu,sigma,alpha,tail)
x = data variable name
mu = population mean
sigma = population standard deviation
alpha = level of significance
tail = ‘both’, ‘left’, or ‘right’
1 sample Z-test MATLAB code
[h,p] - ztest(x, mu, sigma, alpha, tail)
2 sample Z test MATLAB code
What do we do when we have more than 2 samples to test?
[p, atab, stats] anova1(data)
ANOVA test
A summary statistic that quantitatively describes or summarizes features from a collection of information.
Descriptive Statistics
adding all numbers in a data set and dividing them by how many numbers of figures within the set
mean
a measure of how dispersed the data is in relation to the mean
standard deviation
a rule that tells you where most o the values lie in a normal distribution( 68% wihtin 1 std of mean, 95% of values are within 2 std of the mean)
Empirical rule
A research study that follows over time groups of individuals who are alike in many ways but differ by a certain characteristic
ex; female nurses who smoke and those who do not smoke
and compares them for a particular outcome (such as lung cancer)
Prospective Research Study
A study that compares two groups of people: those with the disease or condition under study (cases) and a very similar group of people who do not have the disease or condition (controls). Researchers study the medical and lifestyle histories of the people in each group to learn what factors may be associated with the disease or condition. For example, one group may have been exposed to a particular substance that the other was not. Also called case-control study.
Retrospective Research study
an observational study design
cross-sectional research study
gives a hypothesis and test for the outcome and compare them to the hypothesis.
experimental research study
