Week 1 Day 1 Flashcards
Log(x)=y
10^y=x
Y=mx+b Calculate slope:
M= (y2-y1)/(x2-X1)
Accuracy
How close the average of measured values are to the true value
- assessed by the percent error of measurement
Precision
How close the measured values are to each other
- assessed by calculating the standard deviation of measurements
% error
(Measured value-“true” or accepted value)/true or accepted value
Standard Deviation
Quantifies the amount of variation (precision) of data values. Low standard deviation indicates data points are close to the mean.

Peta (P)
1015
Tera (T)
1012
Giga (G)
109
Mega (M)
106
Kilo (k)
103
Hecto (h)
102
Deca (da)
10
Deci (d)
10-1
Centi (c)
10-2
Milli (m)
10-3
Micro (µ)
10-6
Nano (n)
10-9
Descriptive statistics
Describe a data set; used to organize and summarize the data
Inferential statistics
Used to draw conclusions about the data
Population
The group from which data is collected
Sample
A subset of a population
Variable
A characteristic of any member of a population possibly differing in quality or quantity from one member to another
Categorical variables
Variable with qualitative values:
nominal
ordinal
dichotomous
Continuous variables
Can be measured along a continuum:
internal
ratio
Nominal variable
no intrinsic order.
Ex. Description of shirt
Ordinal variables
Have order, but not necessarily at equal intervals
Ex. Rating of tofu
Dichotomous
Only 2 values
Ex. Male/ Female
Interval
numberical value and is measured
Ex. Height, age, # years as nurse
Ratio
Numeric, measured value with a 0
Ex. height, years as nurse
Range
highest value to lowest value
Interquartile range
75th percentile - 25th percentile
SEM
Standard error of mean- measures the accuracy for which the sample represents the population

Null hypothesis
there is no difference between the things being tested
T-test
t = (Mean1 – Mean2) / √(SEM12 + SEM22)
chance error
Random variations. T-test will tell us if the results were caused by chance
Bigger sample size fixes this error.
Bias
Systematic variation
- selection bias
- measurement bias
- analysis bias
Confounding
An underlying variable that affects the variable that you are testing for
Ex. Testing for avg height of SRNA students at a military CRNA school. Military is more likely to be male, males are more likely to be taller
DOE
Disease Oriented Evidence
blood pressure, cholesterol, glucose
POEM
Patient Oriented Evidence that Matters
mortality and morbidity
Clinical trial
Experimental study where exposure is decided by investigator
Randomized controlled trial
“double blind” clinical trial
Cohort Study
People with a variable (e.g. Hypertension) and people without are identified and followed for a long time
Case-Control Study
Identified subjects with certain variable and a control group without and looks back in time (chart review)
Works well for rare diseases.
Cross-Sectional Study
Identifies presence or absence of a disease and an exposure at the same time.
Ex. Asking a random group of people a bunch of questions at a fair. You don’t get any answers, just more questions.
Case Report
Reports about a single part or series of pets with certain disease. Usually offers a hypothesis but does not test hypothesis b/c there is no comparison group.
Incidence
number of new diagnoses or events
Prevalence
of persons in populations affected by a disease at a specific time divided by the number of persons in the population at the time
Relative risk
ratio of the incidence of disease in exposed group/incidence of disease in unexposed group

Sensitivity
Ability of the test to identify correctly those who have the disease
number of subjects with positive test who have the disease divided by all subjects who have the disease
Specificity
The ability of the test to correctly identify those without the disease
of subjects with negative test and no disease divided by the # of subjects with no disease.
Positive predictive value
Probability of disease in a patient with a positive test.

Negative predictive value
probability of not having the disease if he has a negative test result

Odds ratio
odds of exposure in the group with disease / the odds of exposure in the control group

exact number
can be reproducibly determined by counting or is defined
*have infinite precision and significan figures
*are NOT obtained using measuring devices
density
m/v
specific gravity
density of substance/density of water