IR WEEK 3 Flashcards
what would the null hypothesis be for a chi square analysis?
There is no relationship between variable A and variable B
what would the research hypothesis be for a Chi Square analysis
there is a relationship between variable A and variable B
Describes and predicts genotype and allelic frequencies in a non-evolving population
hardy weinberg principle and equation
what are the assumptions of the hardy weinberg principle
large populations
random mating
no mutation or mutation equilibirum
no migration
no selection: genotypes reproduce with equal success
frequency of the A allele
p
frequency of the a allele
q
defined as the ability of an analytical method to assess small variations of the concentration of the analyte
analytical sensitivity
defined as the ability of an assay to determine specifically the concentration or detection of the target analyte in the presence of interfering substances
analytical specificity
defined as the fraction of patients with a disease that the assay correctly identifies
clinical sensitivity
defined as the fraction of patients without a disease that the assay correctly identifies
clinical specificity
Equation for % sensitivity
proportion of positive tests among patients that have the disease
True Pos/ (True Pos+ False Neg)
Equation for % specificity proportion of negative tests among patients that are healthy
True Neg
_______________________
(False Pos + True Neg)
positive predictive value
True pos
___________________
(True Pos+ False Pos)
Disease Prevalence
(TP+ FN)
________________
TP+FN+FP+TN
how to choose a non parametric test
if you cannot assume a normal/ guassian population
if variance is unequal
if you have very small samples
if you have nominal or ordinal data
non parametric version of the t-test for comparing two samples. requires at least ordinal scale
Mann-Whitney U test
One way parametric version of the ANOVA; assumes ordinal data; three or more groups
Kruskal-Wallis one way ANOVA
non parametric version of paired parametric tests; compares two paired groups
Wilcoxon Matched Pairs signed-Ranks
non parametric version of a repeated-measures ANOVA; compares three or more paired groups; followed with post tests
Friedman Test
can handle outliers skewed data and small samples better than parametric, chance of making type two error is increased
non parametric test
examines the question of whether two categories of classification are independent of each other
contingency tables
chi square formula
expected count
if chi square value is greater than the critical value……
then their is a significant difference and you can reject the null hypothesisf
if the chi square is less than the critical value………
there is not a significant difference, fails to reject the null hypothesis