Theme 9 Flashcards
what is EBHC
“the conscientious, explicit and judicious use of the current best evidence in making decisions about the care of individual patients”
what does EBHC take into consideration (4)
- contextual factors
- health worker’s expertise acquired through clinical practice and experience
- current best evidence obtained from clinically relevant research
- patient values
Importance of synthesizing evidence (5)
- Need to qualify outcomes
- Many effective tx(alternatives)
- Costs
- Info overload/ need for synthesis
- Changing patient-physician relationship
aim of reviews (4)
Readable summary of all evidence
Unbiased reporting of evidence
Transparency
Up-to-date
Narrative Review
- Qualitative, narrative summary of evidence on a given topic
- Written by expert in field (generally)
- Typically involve informal and subjective methods to collect and interpret info
(think of what we did in our pharm project)
Systematic review definition
Summary of literature that uses explicit and reproducible methods to systematically search, critically appraise, and synthesize on a specific issue. It synthesizes the results of multiple primary studies related to each other by using strategies that reduce biases and random errors””
Need for systematic review
- efficient way to access the body of research ( saves time , critical appraisal, interpretation of results)
- explore dif btwn studies
- reliable basis for decision making
- clearly stated objectives and question
- pre-defined eligibility criteria
- comprehensive systematic review
- explicit, reproducible methods
- assessment of validity of included studies
Types of bias minimized by a systematic review
publication / language/ indexing/file-drawer
Application of meta-analysis (3)
Intervention – estimate efficacies and risk of TX
Diagnostic tests – provide more reliable estimates of diagnostic accuracy of test
Epidemiology – to provide more reliable estimate of risks
what is statistics (definition)
“Statistics is the science of collecting, summarizing, presenting and interpreting data, and of using data to estimate the magnitude of associations and test hypotheses.”
types of statistics
- Descriptive statistics
2. Analytic statistics
Descriptive statistics
Methods to summarise and present data
Analytic statistics
Methods to test associations and draw inferences from the sample to a population
Why we need statistics (3)
- Statistics is a way of handling variability.
- It allows us to separate out the real effect from that which could have happened due to chance variability (random error).
- It allows us to make inferences about a larger population from a smaller sample
types of variables ( 2 main types and 5 subtypes)
Categorical variables
a. Nominal
b. Ordinal
c. Binary
Numerical / Quantitative variables
a. Discrete
b. Continuous
Nominal variables
Categorical variable
Categories in no order, are identified by name
e.g. gender, marital status, ethnic group
Ordinal variables
Categorical variable
There is some order and can be recorded in categories
e.g. socio-economic status, severity of a disease
Binary variables
Categorical variable
Binary (or dichotomous)-
Variables that have only two possible categories
e.g. alive or dead, smoking status
Discrete variables
Numerical / Quantitative variable
Can only take on certain values - value is counted not measured
e.g. count of events, count of people
Continuous variables
Numerical / Quantitative variable
Can take on any value - value is measured not counted
e.g. height, blood pressure, CD4 count
Rates/ proportions vs ratios
Rates or proportions relate the number of cases to the size of the population at risk
Ratios used to compare two rates or proportions
Percentage of each response sometimes shown as a proportion- Proportion ranges from 0 to 1
Summarising and presenting Categorical Data
5 ways
- Frequency table (Count the number of observations in each category)
- 2 by 2 tables (show associations between two categorical variables)
- Measures of the strength of association
- risk ratio
- odds ratio
Measures of the strength of association
often 2 X 2 table
- Many epidemiological studies set out to investigate the association between an exposure and an outcome (usually disease)
- binary variables (yes or no)
Relative risk/Risk ratio
- Compares the risk of outcome in two groups
- Groups can be differentiated by demographic factors or by exposure to a suspected risk factor or treatment intervention
- Used in cohort studies and cross sectional studies
interpretation of risk ratio results
- RR = 1 (risk among exposed group = risk among non-exposed i.e. no association)
- RR > 1 (exposure is a risk factor)
- RR < 1 (exposure is protective)
Odds ratio
- The odds of an event calculated from the probability of occurrence
- Used in case control studies and cohort studies
interpretation of odds ratio results
Calculate the probability of exposure amongst the diseased (cases) vs. the non-diseased (controls)
•Odds ratio = 1 (odds are similar)
•OR > 1 (exposure is a risk factor)
•OR < 1 (exposure is protective)
graphing Categorical Data (3 ways)
- bar chart
- cluster bar chart
- pie chart
Simple bar graph
- Used to display data from one variable table
- Each value or category is represented by a bar
- The length of the bar is proportional to the number of events in that category
- Makes it easy to compare the relative size of the different categories
- Bars can be presented either horizontally or vertically
Cluster bar graph
show association between two categorical variables
Pie chart
- For categorical variables with more than 2 categories
- Where total percentage adds up to 100%
- Not very scientific
what graphical display of numerical data detects (4)
- Strange values
- Patterns
- Relationships
- Whether intended statistical analyses are appropriate
what we use for graphical display of numerical data
Symmetry of data detected in:
•histograms
•Box plots
Relationships detected through:
•Bivariate (or scatter plots)
Scatter plot
- Used to plot two continuous numerical variables against one another (e.g. height and weight)
- Used to explore the relationship between variables
- Compact pattern indicates high correlation
- Drawing the scatter plot should precede a statistical analysis
- Plot one variable on the X-axis and plot the other on the Y-axis
Measures of central tendency in Summarising numerical data
- In symmetrical distributions- Mean
- in asymmetrical distributions-Median+ Geometric mean
- Mode
Mean
- Arithmetic mean or average
* Useful in symmetrical distributions of data because sensitive to extreme values
Median
- The median represents the middle of the set (i.e. half the observations above and half the observations below)
- Not sensitive to extreme values -Useful in asymmetrical distributions of data
Mode
- The value that occurs most frequently
- Useful if we are interested in knowing which values are most popular or to assess whether a measuring instrument has a preference for a certain value
- Every set of data has one mean and one median, but could have one mode, no mode, or multiple modes
Comparison of mean and median in different distributions
- In normal distribution, mean and median are similar
* In asymmetrical distributions, they are different
Measures of variability in Summarising numerical data (3)
- Range
- Standard deviation
- Interquartile range
Range
•The largest minus the smallest value or denoted by indicating the smallest and largest value separately
Standard deviation
- Gives the average distance from the mean
* Used with symmetrical data
Interquartile range
- Used to summarise asymmetrical data (i.e. where there are outliers)
- Therefore used with the median
- Calculation –75thpercentile minus the 25thpercentile
- Gives the range of values between which 50% of the data in the sample lie
