Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Michael Wasdell, MA
Epidemiologist
Evaluation & Research Services
Michael.Wasdell@fraserhealth.ca
Director
Camille Viray
Dina Shafey
Magdalena Swanson
Michael Wasdell
Epidemiologist
2
http://research.fraserhealth.ca/
Objectives
Understand the relationship
What is Statistics?
The collecting, summarizing, and
analyzing of data.
The term also refers to raw numbers, or
stats, and to the summarization of data.
Why is a physician held in much higher esteem than a
statistician?
A physician makes an analysis of a complex illness
whereas a statistician makes you ill with a complex
analysis!
5
Types of Statistics
Descriptive Statistics: Describe research
findings
z
Tasty Statistics
1.
2.
3.
4.
5.
Everyone
Identify Overall
Research Goal
Describe
Associate
Predict
Compare
9
Describe
Case Study
an in-depth investigation of an individual, group, incident, or
community
Cross sectional
involve the collection of data from selected individuals in a
single time period.
Longitudinal
involve data collection at two or more times in order to
describe changes over time.
10
Associate
11
Predict
12
Compare
Interested in
z
13
manipulated/assigned by researcher
(assigned to a treatment, workshop etc.)
pre-existing characteristic, not under control
of researcher (sex, age, exposure or
treatment)
15
16
17
Continuous
z
18
z
z
19
Check Assumptions
About Data
20
Parametric Tests
1.
2.
3.
4.
5.
Statistical test
decision tools link
recipe components
with the required
statistic.
Results in successful
statistical planning and
analysis.
22
1. Identify overall
research goal.
2. Identify independent
and dependent variables.
3. Describe the level of
the data.
4. Identify the number
and pairing of groups.
5. Check assumptions
about data.
Continuous
Normal
Ordinal
Non-normal
Categorical
Describe one
group
Mean, SD
Median, interquartile
range
Proportion
Wilcoxon test
Chi-square
One-sample t test
Compare one
group to a
hypothetical value
Compare two
unpaired groups
Unpaired t test
Mann-Whitney test
Fisher's test
(chi-square for large
samples)
Compare two
paired groups
Paired t test
Wilcoxon test
McNemar's test
Kruskal-Wallis test
Chi-square test
Friedman test
Cochrane Q
Quantify
association
between two
variables
Pearson correlation
Spearman correlation
Contingency coefficients
Predict value
from another
measured
variable
Nonparametric
regression
Predict value
from several
measured or
binomial
variables
23
24
1.
2.
3.
4.
5.
25
27
if you have
excel Data
Analysis
28
29
Descriptive Statistics
Measures of central tendency (mean,
median, mode)
Variability (range, variance, standard
deviation)
Shape of Distribution (skewness, kurtosis)
Standard Error
Confidence Level
30
Tools
Data Analysis
Descriptive
Statistics
Input Range
Rows/Columns
Output Options
z
z
New worksheet
Summary statistics
31
Histogram
From http://www.microbiologybytes.com/maths/1011-17.html
32
Histogram Procedure
Tools
Data Analysis
Histogram
Input Range
Bin Range
Labels
Chart Output
33
Associate - Correlation
34
Correlation Procedure
Tools
Data Analysis
Correlation
Input Range
Rows/Columns
Output Options
36
37
Tools
Data Analysis
Regression
Input Y Range
(dependent variable)
Input X Range
(independent
variable)
Output Options
Compare T-Test
Independent Samples T-Test
Allows the comparison of the means of 2
non-paired groups.
Compares actual difference between two
means in relation to the variation in the
data (expressed as the standard deviation
of the difference between the means).
39
Tools
Data Analysis
T-test: Two Sample
Assuming Equal
Variances
Input 1 Range
(dependent variable for
group 1)
Input 2 Range
(dependent variable for
group 2)
Output Options
Compare T-Test
Paired Samples T-Test
Allows the comparison of the means of 2
41
Tools
Data Analysis
T-test: PairedTwo
Sample for Means
Input 1 Range
(dependent
variable at time 1)
Input 2 Range
(dependent
variable at time 2)
Output Options
43
Tools
Data Analysis
ANOVA: Single
Factor
Input 1 Range
(dependent
variable organized
with one column or
row of data per
group)
Output Options
Is there a difference in pre-surgical functioning between
the three major age groups ?
44
Type of Data
Goal
Continuous
Ordinal or Non
Normal
Categorical
Mean, SD
Median, interquartile
range
Proportion
One-sample t test
Wilcoxon test
Chi-square
or
Binomial test **
Compare two
unpaired groups
Unpaired t test
Mann-Whitney test
Fisher's test
(chi-square for large
samples)
Paired t test
Wilcoxon test
McNemar's test
Compare three or
more unmatched
groups
One-way ANOVA
Kruskal-Wallis test
Chi-square test
Compare three or
more matched
groups
Repeated-measures
ANOVA
Friedman test
Cochrane Q**
Quantify association
between two
variables
Pearson correlation
Spearman correlation
Contingency
coefficients**
Simple linear
regression
or
Nonlinear regression
Nonparametric
regression**
Simple logistic
regression*
Multiple linear
regression*
or
Multiple nonlinear
regression**
Multiple logistic
regression*
45
Resources
Choosing a statistical test
http://www.wadsworth.com/psychology_d/templa
tes/student_resources/workshops/stat_workshp/
chose_stat/chose_stat_01.html
http://www.whichtest.info/
46
47