Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
93 Cards in this Set
- Front
- Back
Statistical test used when:
Variable 1 (Factor): Nominal (eg. treatment groups) Variable 2 (Outcome): Ordinal (eg. categories of wellness) |
Chi-square test
|
|
Statistical test used when:
Variable 1 (factor): Nominal (two levels, dichotomous) Variable 2 (outcome): Continuous (eg. Blood Press) |
T-test
|
|
Statistical test used when:
Variable 1 (factor): Nominal (3 or more levels) Variable 2 (outcome): Continuous |
ANOVA
|
|
Error that occurs when you mistakenly reject the Null:
|
Type I (alpha)
|
|
Error that occurs when you mistakenly accept the null:
|
Type II (beta)
|
|
Requirements of a Pearson Correlation:
|
Random selection of sample
Normality of traits measured At least interval level measurement Similar variation between X and Y Linear relation between X and Y |
|
What type of test to ordinal data require?
|
Nonparametric test
|
|
You could use this test when you have ordinal data that is not normal in the population in question:
|
Spearman Rank Correlation
(Spearman r) |
|
Requirements of a Spearman correlation:
|
Random selection of sample
Both distributions of scores are in ordinal form Linear relation between sets of scores |
|
Chi-square test requirements:
|
Randomly selected samples
nominal level of measurement independent cell entries no expected cell frequency below 5 |
|
Degrees of freedom (chi-square)=
|
(rows-1)(columns-1)
|
|
4 variables specified in order to determine sample size:
|
Significance level, alpha (usually .05)
The desired power (80-95%) Variability of the populations (SD's) The amount of change from the null that we realistically want to detect |
|
What would happen to the required sample size if alpha is decreased?
|
it would increase
|
|
What would happen to the required sample size if power is decreased?
|
it would decrease
|
|
What would happen to the required sample size if standard deviations were larger?
|
it would increase
|
|
What would happen to the required sample size if we decrease the differences we want to detect?
|
it would increase
|
|
What would happen to the required sample size if increase the differences we want to detect?
|
it would decrease
|
|
Random sample:
|
external valitidy to ensure that it is representation of the population
|
|
The presence of a microbe in a host to benefit the microorganism. Generally used to denote the possibility of causing disease:
|
Infection
|
|
Presence of microbes in a host which does not result in clinical disease and may be needed for health:
|
Colonization
|
|
GI tract flora are an example of a _____________ in the human body.
|
Colonization
|
|
The persistence of a microbe in a host with possibility of disease in the future without shedding of the organism in the interval:
|
Latent infection
|
|
Shingles from Varicella zoster is an example of a:
|
Latent infection
|
|
An infection can be ________ (like cholera or the flu) or __________ (like Hep B).
|
Acute; chronic
|
|
Two types of non-clinical infection (inapparent) for which transmission may still occur:
|
Preclinical; subclinical
|
|
Are you capable of spreading a virus in a latent infection prior to the onset of symptoms?
|
No
|
|
What percentage of typhoid infections are in people who are only carriers?
|
2-5%
|
|
The ability of the microbe to cause infection (enter, survive, multiply in host) but not necessarily cause symptoms:
|
Infectivity
|
|
Attack rate is equal to:
|
# infected/# exposed
|
|
The ability of the microbe to cause disease: (severity doesn't matter)
|
Pathogenicity
|
|
Attack rate for pathogenicity is equal to:
|
# of clinical cases/# infected
|
|
Degree of severity of the disease produced:
|
Virulence
|
|
Virulence and ____________ are often used interchangably, incorrectly.
|
Pathogenicity
|
|
Case fatality rate =
|
# fatalities/ # diagnosed cases
|
|
A sudden increase in the frequency of infection in a particular region:
|
Epidemic
|
|
An epidemic on a global scale (such as HIV, AIDS):
|
Pandemic
|
|
Why does HIV/AIDS occur more commonly in men?
|
Male-male sexual contact is primary source of transmission
|
|
Why is the prevalence of HIV increasing when incidence has been steady since the 1990s?
|
Duration is increasing due to better treatments
|
|
An infection that occurs regularly at a stable rate in a particular region:
|
Endemic
|
|
Malaria is ______ to sub-Saharan Africa
|
Endemic
|
|
A water-borne infection that is resistant to chlorine, other purifiers, and is hard to detect in epidemiological sense:
|
Cryptosporidiosis (fecal-oral tramsission)
|
|
Thousands have been infected with this from recreational water exposure
|
cryptosporidiosis
|
|
Residua of droplets which have evaporated to less than 5 microns
|
droplet nuclei
|
|
Two sites of infection from airborne vectors
|
upper respiratory infection or lung alveoli
|
|
Talking produces about ___ particles, coughing, ____, sneezing, ________>
|
100; 1000; >500000
|
|
Malaria, dengue, and yellow fever are examples of
|
Vector borne infecitons
|
|
Other living organisms which harbor microbe and transmit to susceptible host:
|
Vector
|
|
Inanimate objects which are contaminated and spread infection:
|
Fomites
|
|
An infection normally present in vertebrate animals but which can rarely spread and cause disease in humans; may be mild and require extensive exposure:
|
Zoonosis
|
|
An infection acquired in a hospital; chances much greater with presence of invasive devices or tubes such as catheters:
|
Nosocomial infection
|
|
Where do nosocomial infecitons occure the most?
|
The ICU
|
|
Requirements of an ANOVA:
|
Random selection of samples
Normality of traits in populaiton Homogeneity of variance At least one independent var. with three or more leves One dependent var. |
|
What is used to define an ANOVA?
|
the number of independent variables
|
|
ANOVA with multiple dependent variables:
|
Multivariate (MANOVA)
|
|
ANOVA where the dependent variable is 'corrected' for possible confounders:
|
Analysis of Covariance (ANCOVA)
|
|
An ANOVA is just a ______ with more than two levels of independent variables
|
t-test
|
|
An ANOVA is an _______, or an overall test.
|
omnibus
|
|
An ANOVA tells whether there is a difference between any groups, but not which groups that difference is in. What test must be done to find further information?
|
a post-hoc test
|
|
The proportion of diabetics in a group is pi where pi =:
|
# of diabetics in a group/# of people in the group
|
|
In many settings, this means the same thing as proportion:
|
probability
|
|
4 essential components of surveillance:
|
Case reporting
Data analysis Communication of results Application of findings |
|
Systematic ongoing colleciton, collation, and analysis of data and the timely dissemination of information to those who need to know so that action can be taken:
|
Surveillance
|
|
3 types of surveillance:
|
Passive, active, and stimulated
|
|
Surveillance in which Physician, ICP, or lab reports cases as prescribed by state law without prompting
|
Passive surveillance
|
|
Surveillance in which regular examination and prompting done to ascertain presence or absence of cases:
|
Active surveillance
|
|
Surveillance in which intermittent prompting increases passive reporting:
|
Stimulated surveillance
|
|
Who publishes a list of diseases that should be reported?
|
Council of State and Territorial Epidemiologists (CSTE) and CDC
|
|
International health regulations require the mandatory declaration of what three diseases only?
|
Cholera, the plague, and yellow fever
|
|
Restriction of activities on the basis of exposure:
|
quarantine
|
|
Restriction of activities on the basis of infection until the infectious period has passed:
|
Isolation
|
|
Damage to an individual due to an energy exchange, or due to an acute disruption in the normal body energy process.
|
An injury
|
|
Five types of energy disruption in an injury:
|
Mechanical
Electrical Chemical Thermal Radiation |
|
What 3 types of death make up the injury portion of Years of potential life lost?
|
Unintentional injury, suicide, and homicide
|
|
What are the two biggest contributors to unintentional injury deaths?
|
Motor vehicle accidents, unintentional poisoning
|
|
"The story of the people"
|
Demography
|
|
The scientific study of the determinants and consequences of population trends (mortality, fertility, migration):
|
Demography
|
|
Reasons for measuring health/ill-health
|
Disease/injury prevention
Health promotion Health services planning Program evaluation |
|
Which sex is more robust?
|
Female
|
|
Hypothesis a priori?
|
Before they collected the data
|
|
What is most directly associated with the accuracy of an estimate?
Standard deviation variance Standard error Median Range |
Standard Error
|
|
When we accept the null, what is the probability of a type I error?
|
zero
|
|
What is the most effective method for reducing confounding in a study design?
|
Randomization
|
|
What effect does increasing alpha have on the chance of a type I error?
|
Increases the chance.
|
|
Only ____________ can help us determine if a result is 'significant' or suggests clinical significance.
|
effect sizes
|
|
Formula for Cohen's d:
|
(mean1 - mean2)/SD
|
|
Carrier status for typhoid fever is more common in which sex?
|
Females
|
|
Tuberculosis, measels, varicella, and possibly influenza can all be transmitted through:
|
Droplet nuclei
|
|
What percentage of ATV deaths are to passengers?
|
12
|
|
Type of bias which states that people receiving treatment are systematically different than the general population:
|
Berkson's bias
|
|
This bias is also known as prevalence-incidence bias; people with serious, more detrimental forms of a disease are less likely to show up in a point prevalence (not so much a problem with incidence)
|
Neyman's bias
|
|
Only study people who are homogenous for a known confounder:
|
restriction
|
|
Production of individuals improved solely because they were being watched:
|
Hawthorne effect
|
|
Mistaken belief that something is more likely to occur because it hasn't occured in a period of time:
|
Gambler's fallacy
|