1. Sampling

2. Sampling Theory Concepts
 Population
 Target Population
 Accessible Population
 Elements of a Population
 Sampling Criteria

3. Sampling Criteria
 Characteristics essential for
inclusion or exclusion of
members in the target
population
 Between the Ages of 18 & 45
 Ability to speak English
 Dx of diabetes within last month,
or
 No Hx of chronic illness

4. Sampling Theory Concepts
 Sampling Plans or
Methods
 Sampling Error
 Random Variation
 Systematic Variation

5. Sampling Error
 Random Variation
 The expected difference in values that
occurs when different subjects from
the same sample are examined.
 Difference is random because some
values will be higher and others lower
than the average population values.

6. Sampling Error
 Systematic Variation (Bias)
 Consequence of selecting
subjects whose measurement
values differ in some specific
way from those of the
population.
 These values do not vary
randomly around the
population mean

7. Sampling Error
Sampling Error
Population
Sample
Population
Mean
Sample
Mean

8. Sampling Theory Concepts
 Sample Mortality
 Subject Acceptance Rate:
 Percentage of individuals
consenting to be subjects
 Representativeness

9. Representativeness
 Needs to evaluate:
 setting
 characteristics of the subjects:
age, gender, ethnicity, income,
education
 distribution of values
measured in the study

10. Probability (Random)
Sampling Methods
 Simple Random Sampling
 Stratified Random Sampling
 Cluster Sampling
 Systematic Sampling

11. Nonprobability (Nonrandom)
Sampling
 Convenience (Accidental)
Sampling
 Quota Sampling
 Purposive Sampling
 Network Sampling

12. Sample Size
 Factors influencing sample size
 Effect size
 Type of study conducted
 Number of variables studied
 Measurement sensitivity
 Data analysis techniques

13. Power Analysis
 Standard Power of 0.8
 Level of Significance
 alpha = .05, .01, .001
 Effect Size
 .2 Small; .5 Medium; .8 Large
 Sample Size

14. Example Sample
 A convenient sample of 55 adults
scheduled for first time elective CABG
surgery without cardiac
catheterization, who had not had
other major surgery within the
previous year, and who were not
health professionals met the study
criteria and were randomly assigned
to one of two instruction conditions...

15. Example Sample
 Based on a formulation of 80% power, a
medium critical effect size of 0.40 for each of
the dependent variables, and a significance
level of .05 for one-tailed t-tests means, a
sample size of 40 was deemed sufficient to
test the study hypotheses...

16. Example Sample
 The study included a convenience
sample of 32 post-op Lung Cancer
patients. A power analysis was
conducted to determine size. A
minimum of 27 subjects was necessary
to achieve the statistical power of 0.8
and a medium (0.5) effect size at the
0.05 level of significance....The
subjects were 25 men and 7 women
with an age range from 18-58 years
(mean = 32.74)....

17. Critiquing the Sample
 Were the sample criteria
identified?
 Was the sampling method
identified?
 Were the characteristics of
the sample described?

18. Critiquing the Sample
 Was the sample size identified?
 Was the percent of subjects
consenting to participate
indicated?
 Was the sample mortality
identified?
 Was the sample size adequate?

19. Concepts of
Measurement

20. Measurement Theory
Concepts
 Directness of Measurement
 Direct measurement
 Oxygen saturation,
Temperature, weight
 Indirect measurement
 Pain, depression, coping, selfcare, self-esteem

21. Measurement Theory
Concepts
 Measurement Error

Scoreobs = Scoretrue +
Scoreerr
 Systematic error
 Random error
 Levels of Measurement

22. Levels of Measurement
 Nominal
 data categorized, but no order or zero (ex- gender
numbers)
 Ordinal
 categories with order, but intervals not necessarily
equal and no zero (ex – pain)
 Interval
 equal intervals, but no true zero (ex- temp scales)
 Ratio
 equal intervals with a true zero. These are real
numbers, for things such as weight, volume, length.

23. Gender
 1 = Male
 2 = Female
 (Nominal Data)

24. Likert Scale
 How often do you feel in control of
your life?
 (1) Never
 (2) Seldom
 (3) Often
 (4) Almost always

25. Age
 How old are you?
 25-34
 35-44
 45-54
 55 or older

26. Income
 1 = under Rs-35,000/ 2 = Rs-35-50,000/ 3 = Rs-50 - 100,000/-

27. What is reliability?
 Reliability - is concerned
with how consistently the
measurement technique
measures the concept of
interest.

28. Types of Reliability
 Stability -- is
concerned with the
consistency of
repeated measures or
test-retest reliability

29. Types of Reliability
 Equivalence -- is focused
on comparing two versions
of the same instrument
(alternate forms reliability)
or two observers (interrater
reliability) measuring the
same event.

30. Types of Reliability
 Homogeneity -- addresses the
correlation of various items
within the instrument or
internal consistency;
determined by split-half
reliability or Cronbach’s alpha
coefficient.

31. Inter-rater reliability
 Consistency in raters
 % = # behaviors
performed/total # of
behaviors
 Values below 0.8 are a
problem

32. What is validity?
 The extent to which an
instrument reflects the
concept being examined.

33. Measurement
Strategies

34. Physiologic Measures
 Physical Measurement
Methods
 EKG, BP
 SVO2, Pulse Oximetry

35. Physiologic Measures
 Chemical/biochemical
 Blood glucose
 SMA-24
 PKU

36. Physiologic Measures
 Microbiological
 Smears
 Cultures
 Sensitivities

37. Observational Measurement
 Unstructured Observations
 Structured Observations
 Category Systems
 Checklists
 Rating Scales

38. Interviews
 Unstructured Interviews
 Structured Interviews
 Describing interview questions
 Pretesting the interview protocol
 Training interviewers
 Preparing for an interview
 Probing
 Recording interview data

39. Unstructured or Open ended:
 Tell me about…..
 What has been your experience
with....
 What was it like to hear you
have cancer?

40. Closed ended:
 Structured
 Response alternatives fixed
 Which would you rather
do, x or y?

41. Measurement Strategies
 Questionnaires
 Scales
 Diaries

42. Questionnaires
 Administration
 In person/on phone
 Self administered
 Mail

43. Scales
 Rating Scales
 Likert Scales
 Semantic Differentials
 Visual Analog Scales

44. Introduction
to Statistical
Analysis

45. Normal Curve
Mean
Median
Mode
68.3%
95.5%
-3
-3
-2
-1
-2
-1
-2.58 -1.96
99.7%
0
0
1
1
2
2
1.96
3
3
2.58

46. Tailedness
Significantly different
from mean
Significantly different
from mean
0.025
0.025
Tail
Tail
Two-Tailed Test- .05 Level of Significance
0.05
Significantly different
from mean
One-Tailed Test- .05 Level of Significance

47. Process for Quantitative Data
Analysis
• Preparation of the Data for Analysis
• Description of the Sample
• Testing the Reliability of the Instruments
for the Present Sample
• Testing Comparability of Design Groups
• Exploratory Analysis of Data
• Confirmatory Analyses Guided by
Objectives, Questions, or Hypotheses
• Post Hoc Analyses

48. Cleaning Data
 Examine data
Cross-check every piece of data with the
original data
 If file too large, randomly check for
accuracy
 Correct all errors
 Search for values outside the appropriate
range of values for that variable.


49. Missing Data
 Identify all missing data points
 Obtain missing data if at all possible
 Determine number of subjects with data
missing on a particular variable
 Make judgement - are there enough
subjects with data on the variable to
warrant using it in statistical analyses?

50. Transforming Data
 Transforming skewed data so that it is linear
(required by many statistics).
 Squaring each value
 calculating the square root of each
value

51. Calculating Variables
 Involves using values from two or
more variables in your data set to
calculate values for a new variable
to add to the data set.
 Summing scale values to obtain
a total score
 Calculating weight by height
values to get a value for Body
Mass Index

52. Statistical Tools
 Used to allow easy calculation of statistics
 Computer-based tools allow rapid analysis but
sometimes too easy
 Must still know what each type of test is for and how to
use them
 Don’t fall into the trap of using a test just because it is
easy to do now
 Many papers appearing with questionable tests just
because a computer program allows the calculation

53. Statistics Exercises
 Stat Trek
 http://stattrek.com/
 Tutorial for exercises
 Understand rationale for the selection of each test type.
 Be prepared to utilize test if asked, and know major advantages
of each main test.
 Miller Text (Chapter 21, Fifth Edition, pgs 753-792)
 Material very thorough.
 Many little-used tests described.
 Read for idea of why other tests are available

Don’t get bogged down in the details

54. Descriptive Statistics
 Describes basic features of a data group.
 Basis of almost all quantitative data analysis
 Does not try to reach conclusions (inferences), only
describe.
 Provide us with an easier way to see and quickly interpret
data

55. Descriptive Statistics
 Data Types
 Based on types of measurement
 Measurement scales can show magnitude, intervals, zero point, and
direction
 Equal intervals are necessary if one plans any statistical analysis of
data
 Interval scales possess equal intervals and a magnitude
 Ratio scales show equal intervals, magnitude and a zero point
 Ordinal scales show only magnitude, not equal intervals or a zero
point
 Nominal data in non-numeric (not orderable) whereas
ordinal data is numeric and can be ordered but not based
on continuous scale of equal intervals

56. Descriptive Statistics
 Goal of use is to be able to summarize the data in a way
that is easy to understand
 May be described numerically or graphically
 Describe features of the distribution
 Examples include distribution shape (skewed, normal
(bell-shaped), modal, etc), scale, order, location

57. Descriptive Statistics
 Location Statistics
 How the data “falls”
 Examples would be statistics of central tendency
 Mean



Median



Average of numerical data
Σx/n
Midpoint of data values
Value of data where 50% of data values is above and 50% below (if
number of data points is even, then the middle two values are averaged)
Mode


Most frequent data value
May be multi-modal if there is an identical number of max data values

58. Descriptive Statistics
 Location Statistics
 Data outliers may need to be accounted for and possibly
eliminated

This can be done by trimming or weighting the mean to
effectively eliminate the effect from outliers

59. Descriptive Statistics
 Count Statistics
 One of the simplest means of expressing an idea
 Works for ordinal and nominal data

60. Descriptive Statistics
 Statistics of Scale
 Measures how much dispersal there is in a data set
(variability)
 Example statistics include sample range, variance,
standard deviation (the square root of the variance), SEM
(SD/sq root of N)
 Outliers can influence variance and standard deviation
greatly, so try to avoid their use if there are lots of outliers
that can not be weighted out

61. Descriptive Statistics
 Distribution Shape Statistics
 Determines how far from “normal” the distribution of data
is based on normal distribution shapes (Gaussian)
 Skewness measures how “tailed” the data distribution is
(positive to right, negative to left)
 Kurtosis measures whether the “tail” is heavy or light

62. Inferential Statistics
 Attempts to come to conclusions about a data set that are
not exactly stated by the data (inferred)
 Many tests use probability to help determine if data
points to a likely conclusion.
 Often used to compare two groups of data to see if they
are ‘statistically different’
 Often used to decide whether or not a conclusion one is
trying to reach from the data set is reliable (within
statistical probability)

63. Inferential Statistics
 Simplest form is the comparison of average data between
two data sets to see if they are different
 Students t-test is often used to compare differences
between 2 groups
 Usually one control group and one experimental
 Should be only one altered variable in experimental
group

64. Inferential Statistics
 Most common inferential statistical tests belong to the
General Linear Model family
 Data is based on an equation in which a wide variety of
research outcomes can be described
 Problems with these types of analysis tools usually comes
from the wrong choice of the equation used
 Errors in the wrong equation used can result in the data
conclusions being biased one way or the other, leading to
accepting or rejecting the null hypothesis wrongly

65. Inferential Statistics
 Common Linear Model tests include:
 Students t-test
 Analysis of variance (ANOVA)
 Analysis of covariance (ANCOVA)
 Regression analysis
 Multivariate factor analysis

66. Inferential Statistics
 Type of research design used also determines the
type of testing which can be done:
 Experimental analysis
 Usually involves comparison of one or more groups against a
control, and thus t-test or ANOVA tests are the most commonly
used
 Quasi-experimental analysis
 Typically lack a control group, and thus the random analysis that is
usually used to assign individuals to groups
 These types of analysis are much more complex to compensate for
the random assignments