Guo's first lecture Flashcards
Evidence Based Medicine
The integration of best research evidence, clinical expertise, and patient values
Evidence Based Pharmacotherapy
the integration of best research evidence, clinical PHARMACY expertise, and patient values
Statistics
- acquisition of knowledge through the process of observation
- allow the researcher to summarize data & to distinguish b/w chance & systematic effects
Descriptive Statistics
- Describe data that we collect or observe (empirical data)
- concerned with the presentation, organization, and summarization of data
- ex: pie charts, bar graphs, etc
Inferential Statistics
- a range of procedures/statistical tests (ex. t-test, analysis of variance, or chi-square test, multiple regression analysis)
- allow us to generalize from our sample of data to a larger group of subjects
Discrete Variable (Data)
- characterized by gaps or interruptions
- aka “Qualitative” data
- can only be whole numbers; limited set of values
- Ex: sex, marital status, blood type
- NO HERMAPHRODITES
Continuous Variable (Data)
- no gaps or interruptions & may take any value within defined range
- aka “Quantitative” data
- Ex: height, weight, BP, blood glucose
- Hermaphrodites are okay
Dependent Variable (Y)
- the outcome of interest, which should change in response to some interventions
- the variable you want to measure
- ex: final exam scores, blood glucose level, bioavailability
Independent Variables (Xi)
- the intervention or what is being manipulated. A variable keeps changing it’s value. It allows us to control some of the research environment
- predictor variables
- Ex: temp, drug therapy, institutional vs community pharmacy
Nominal Scale
- lowest level of measurement
- Named categories with no implied order among the categories
Ordinal Scale
- same as nominal plus ordered categories; where the difference b/w categories cannot be considered to be equal
Interval Scale
- same as ordinal plus equal intervals; Data has equal distances b/w scores, but the zero point is arbitrary
Ratio Scale
- highest scale of measurement
- Data has equal intervals b/w scores and a meaningful zero point
Random Sampling
- Equal chance of being included in the sample (everyone has a chance of getting in )
- Use of random numbers table
Selective Sampling
- Not random sampling; convenient sampling
Systematic Sampling
- systematically select subjects as sample
- Ex: it can be a systematic random sample in which every Xth is selected for a study
Stratified Sampling
- Population is divided into subgroups (strata) with similar characteristics, then randomly select samples from each subgroup (stratum)
Cluster Sampling
- also called multistage sampling
- many individual “primary” units that are clustered together in “secondary” units for further division (units can be sub-sampled)
Mode
The value with the greatest frequency of occurence
Median
The score that divides the distribution into the lower and upper 50 percent of the observations
Mean
The center of gravity of distribution; or average score