0% found this document useful (0 votes)
22 views57 pages

Introduction to Statistical Analysis

This document provides an overview of statistical analysis and experimental study designs. It discusses different types of experimental studies including clinical trials, laboratory trials, and community trials. It also describes various study designs like completely randomized designs, randomized block designs, Latin square designs, and factorial designs. The document outlines some common pitfalls in research protocols and discusses important statistical concepts like sampling, randomization, and hypothesis testing. It provides guidance on writing up results, discussions, and conclusions sections of a research study.

Uploaded by

Rajeev Sharma
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
22 views57 pages

Introduction to Statistical Analysis

This document provides an overview of statistical analysis and experimental study designs. It discusses different types of experimental studies including clinical trials, laboratory trials, and community trials. It also describes various study designs like completely randomized designs, randomized block designs, Latin square designs, and factorial designs. The document outlines some common pitfalls in research protocols and discusses important statistical concepts like sampling, randomization, and hypothesis testing. It provides guidance on writing up results, discussions, and conclusions sections of a research study.

Uploaded by

Rajeev Sharma
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

Statistical Analysis An

Overview Introduction

Dr. AJIT SAHAI


Faculty- Consultant (Research)
Ex Director – Professor Biometrics
JIPMER, Pondicherry
Experimental studies

 Clinical trials
 Laboratory trials
 Community trials
(a) Clinical trials
1. Controlled trials
parallel or concurrent controls
 a. randomized
 b. non-randomized
sequential controls
a. self-control
b. cross-over
external controls ( including
historical )

[Link] trials
B. Laboratory/experimental designs

Completely randomized
Randomized block
Latin square
Lattice
 Cubic
 Rectangular
Split plot
Factorial
Common Pitfalls in Research Protocols
Statistical Methods

Dr. AJIT SAHAI


PhD, FIAPSM, FIPHA, FSMS, FRSS

Faculty-Consultant (Research/Biostatistics)
KGMU, Lucknow.

Formerly-Professor & Head,


Dept of Medical Biometrics, JIPMER, Pondicherry.
A few generalized aspects
 Title
 Research Question(s)
 Hypothesis(es)
 Aims Objectives(Primary/Secondary)
 Tools; Techniques & Methods:
Case definition (Controls)
Eligibility for recruitments
Methodology Aspects
 Study design
 Standardizations of tools; techniques of
measurements
 Scoring & grading systems

 Sampling & Sample


 Random selections & allocations
 Statistical tests proposed
Results-Discussions-Conclusions
and Recommendation Aspects

 Tables; Graphs/Charts and Write-ups


 Reveal the facts –Scientific Strengths
 Never Censor the weaknesses (- ves)
 Never discuss and conclude without
evidence or beyond study results
 Never construct recommendations
beyond the study domain or scope
WHY? Sampling
 A study of entire population is
impossible in most of the situations

 Sometimes, the study process


destroys (animal sacrifice) or depletes
the item being studied
 In such situations the only alternative
is sample study
Advantages
Sample results are often more
accurate;

Apart from being


quick and less expensive
Generalization strength -
Validity of Results

Target population
A common sense judgment is required to
make inferences from the sampled to the
target population

Sampled population
Random sampling is required to make
statistical inferences from the sample
to the sampled population.

Sample
Sampling Error (E)

Sampling Error
(E)

Sample size (n)


Sample-Size Vs. Sampling-Error

 The sample size may have to be


directly proportional to the
heterogeneity in the population,

 Whereas, the sampling error is


always inversely proportional to
the sample size.
Non-sampling error

 Non-response
 Response

 Non-coverage

 Measurement
Probability Sampling
The techniques of sampling may be
classified as;

“Probability sampling” such as;


- Simple random sampling,
- Stratified, cluster, systematic,
- Multi-stage and multi-phase
sampling; whereas,
Sample Size - Methods Vs Studies

Exploratory studies Confirmatory studies

Experimental studies Observational studies

Clinical studies Population studies

Cross-sectional studies Longitudinal studies

Prospective studies Retrospective studies

Cohort studies Case-referent studies


GENRALIZATION
 If samples are properly selected,
probability methods can be used
to estimate the error in the
resulting statistics

 It is this aspect of sampling that


permits investigators to make
probability statements about the
observations in a study
Power of a Study
It is not only the sampling method but
the sample-size also equally responsible
for the power of a study

 For this reason, investigators must plan


the sample size appropriate for their
study prior to beginning research
Sampling methods
 Random sampling
 Simple Random Sampling (SRS)
 Stratified Random Sampling
 Systematic random sampling

 Ratio/Regression methods
 Systematic sampling
 Cluster sampling
 Multi-stage sampling
 Multi-phase sampling
Deficiencies in published papers

 no detail on sample size 89%


 no confidence intervals 86%
 inadequate detail on randomisation 60%
 no details of concealment 77%
Moher, D. CONSORT: an evolving tool to help improve the quality of reports of RCTs.
JAMA, 1998, 279: 1489-91

 defects in 18-68% of abstracts


Pitkin, RM et al, JAMA 1999, 281: 1110-1

 errors in 4-67% (median 36%) of citations


Wager, E & Middleton, P: PIRATES abstract submitted to
Peer Review Congress, Barcelona, Sept 2001
Common Errors When Reporting
RESULTS
Errors of Omission:

 Not accounting for all study subjects


 Not naming which statistical tests were
used for specific analyses
 Not presenting the results in a clinically
relevant units
Errors in the Analysis

 Lack of power
 Failure to adjust for multiple comparisons
 Analysis by treatment received and not by
intention to treat

Errors in Interpretation
 Not recognizing the limits/meaning of p
Data Analyses/Syntheses Process
 Screening /Verification/Cleaning up
 Organization
 Compilation /Collation &

 Classification (Nominal/Ordinal/Numerical)
 Grouped Frequency Distribution

 Tabulation
 Graphical representations
Summary Statistics
 Rates, Ratios and Proportions

 Incidence & Prevalence (Point /Period)

 Numerator and Denominator

 Per – Cent / Thousand / Lakh / Million


Summary Statistics
Measures of
 Central Tendency – averages

 Dispersion/Deviation
/Scatter/Variation/ Spread

 Location –percentiles /quintiles


The role of Central Tendency
and Deviation

-3s -2s +2s +3s


Mean
95.5%

99.7%
Biological Observations
 Though this universe is full of
uncertainty and variability,
a large set of experimental /
biological observations always
tend towards a
 Normal distribution.
Inferential Statistics

 This unique behavior of


data
is the key to entire
inferential statistics.
Population Probability
Distributions
such as;

Normal
Binomial
Poisson
Rectangular
Sampling Distributions
Like;

Chi-square ‘X2’
Student’s
‘t’
and ‘F’
Population & Sampling
Distributions
 frequently used for
probability calculations and
also for
 testing the hypotheses
through various tests of
significance
Possible Conditions of Null
Hypothesis
H0 is TRUE H1 is TRUE

REJECT H0 TYPE I Correct


error decision
ACCEPT H0 Correct TYPE II
decision error
Probability (P) - Error types
 The size of type I error is the probability
that the sample point will fall in the critical
region when H0 is true (α)

 The size of the type II error is the


probability that the sample point will fall in
the non-critical region when H1is true (β)
Guidelines for Writing Results -
The Study as it was Conducted
 Specify the dates of the study
 Provide a schematic summary
 Describe the characteristics of each group
 Indicate if the sample is representative
 Indicate if randomization was successful
 Describe duration and nature of follow up
 For observations based on judgment,
provide assessment of consistency
Guidelines for Writing Results:
The Study Outcomes
 Present the results for all primary endpoints
 Report 95% CI
 Report actual p values for all primary analyses
 Report the main findings in figures or tables
 Report statistical findings in detail
 Report confounders
Guidelines for Writing Results:
The Study Outcomes

 Indicate compliance and deviations from


the protocol
 Report treatment related SE/AE
 Describe the treatment of outliers
 Account for all observations; explain
missing data
 Report anecdotal evidence or
observations that might influence
interpretation
Good publication practice
 Read “Guidelines on good publication practice”
from the Committee on Publication Ethics
(COPE)

 Available free at [Link] [Link]


COPE guidelines on good
publication practice cover
 Study design and ethical approval
 Data analysis
 Authorship
 Conflicts of interest
 Peer review
 Redundant publication
 Plagiarism
 Duties of editors
 Media relations
 Advertising
 Dealing with misconduct, including sanctions
Why publish?
 Because you have something important to say
 To change practice
 To promote thought or debate
 To allow examination of your work
 “Fame and the love of beautiful women”
 Money
 Career advancement
 To entertain/divert/amuse
 To educate
 To console
What do editors want?
 Excitement/ “wow”
 Importance
 Originality
 Relevance to the audience
 True
 Clearly written
 Engagingly written
Utility of information

 Utility = relevance x validity x interactivity


work to access
The basics of writing a paper
1. Before you begin

 What do I have to say?


 Is it worth saying?
 What is the right format for the message?
 What is the audience for the message?
 Where should I publish the message?
 How can I best use paper and the web?
The basics of writing a paper
2. The importance of structure

 Structure is everything.
The basics of writing a paper
3. Possible structures
 Beginning, middle, end (AA beginning, a muddle, and an end.@
Philip Larkin)

 Tell people what you are going to say, say it, tell them what
you=ve said

 Rudyard Kipling: (AI keep six honest serving me, (They taught
me all I knew), Their names are What and Why and When, And
How and Where and Who?)
The basics of writing a paper
3. Possible structures continued
 News story: (Story in the title; story in the first line; expand
slightly on the story in the first paragraph; give the evidence for
the story; give the counter view)

 ImraD (Introduction, methods, results, and discussion)

 Stream of consciousness

 Chronology: diary, autobiography


The basics of writing a paper
3. Possible structures continued

 A list

 Something very formal: for example, sonnet, limerick, haiku

 Ulysses
The basics of writing a paper
4. Still structure

 Make sure that readers know where


they are, where they are going, and
why.
The basics of writing a paper
5. IMRaD
 Introduction--Why did I do it?
 Methods--What did I do?
 Results--What did I find?
 Discussion-- What might it mean? What is our overall finding? What
are the strengths and weaknesses of the study in relation to other studies?
Why might we have got different results? What might the study mean,
particularly for clinicians or policy makers? What questions remain
unanswered and what next?
The basics of writing a paper
5. IMRaD (Introduction)
 Why did we start?
 What has gone before - ? A systematic review
 Why was this study needed?
 Be sure that readers understand the importance of the
study-but don=t overdo it short
 Don=t try to show readers that you have read
everything
 Short, short, short
The basics of writing a paper
5. IMRaD (Methods)
 Like a recipe
 For informed readers this is the most important section
 Describe how subjects were selected and excluded
 Don=t describe standard methods in detail - use references
 Statistics
 Ethics
 Remember that you can put more detailed methods on the web--
for example, questionnaire
The basics of writing a paper
5. IMRaD (Results)
 Stick to what is relevant
 Be sure to include basic descriptive data
 The text should tell the story
 The tables give the evidence
 The figures illustrate the highlights
 Don=t include just percentages or p values
 Include confidence intervals
 Think about absolute risk, number needed to treat, etc
 Avoid beginning to discuss the implications or strengths and weaknesses of your
study
The basics of writing a paper
5. IMRaD (Discussion)

 Statement of principal findings


 Strengths and weaknesses of the study
 Strengths and weaknesses in relation to other studies, discussing
particularly any differences in results
 Meaning of the study: possible mechanisms and implications for
clinicians or policymakers
 Unanswered questions and future research
 Go easy on the last two
The basics of writing a paper
Topping and tailing
 Title: Include design; Don=t try to be clever
 Abstract: Must be structured; Include some
numbers, not all
 References: Keep to the essentials
 Covering letter: Something very crisp
 Authorship, acknowledgements, competing
interests

You might also like