Introduction to epidemiology

Slides:



Advertisements
Similar presentations
Introduction to Summary Statistics
Advertisements

Introduction to statistics in medicine – Part 1 Arier Lee.
Insert name of presentation on Master Slide Epidemiology Toolkit for Outbreak Investigation Meirion Evans Communicable Disease Surveillance Centre.
QUANTITATIVE DATA ANALYSIS
DESCRIBING DATA: 2. Numerical summaries of data using measures of central tendency and dispersion.
B a c kn e x t h o m e Parameters and Statistics statistic A statistic is a descriptive measure computed from a sample of data. parameter A parameter is.
Measures of Dispersion CJ 526 Statistical Analysis in Criminal Justice.
Statistical Analysis SC504/HS927 Spring Term 2008 Week 17 (25th January 2008): Analysing data.
Describing distributions with numbers
@ 2012 Wadsworth, Cengage Learning Chapter 5 Description of Behavior Through Numerical 2012 Wadsworth, Cengage Learning.
Think of a topic to study Review the previous literature and research Develop research questions and hypotheses Specify how to measure the variables in.
APPENDIX B Data Preparation and Univariate Statistics How are computer used in data collection and analysis? How are collected data prepared for statistical.
6.1 What is Statistics? Definition: Statistics – science of collecting, analyzing, and interpreting data in such a way that the conclusions can be objectively.
Methods for Describing Sets of Data
PTP 560 Research Methods Week 8 Thomas Ruediger, PT.
Biostatistics: Measures of Central Tendency and Variance in Medical Laboratory Settings Module 5 1.
Statistics for Infection Control Practitioners Presented By: Shana O’Heron, MPH, CIC Infection Prevention and Management Associates.
Measures of Central Tendency and Dispersion Preferred measures of central location & dispersion DispersionCentral locationType of Distribution SDMeanNormal.
1 1 Slide Descriptive Statistics: Numerical Measures Location and Variability Chapter 3 BA 201.
1 PUAF 610 TA Session 2. 2 Today Class Review- summary statistics STATA Introduction Reminder: HW this week.
Measures of central tendency are statistics that express the most typical or average scores in a distribution These measures are: The Mode The Median.
FREQUANCY DISTRIBUTION 8, 24, 18, 5, 6, 12, 4, 3, 3, 2, 3, 23, 9, 18, 16, 1, 2, 3, 5, 11, 13, 15, 9, 11, 11, 7, 10, 6, 5, 16, 20, 4, 3, 3, 3, 10, 3, 2,
Basic Statistical Terms: Statistics: refers to the sample A means by which a set of data may be described and interpreted in a meaningful way. A method.
1 1 Slide IS 310 – Business Statistics IS 310 Business Statistics CSU Long Beach.
1 1 Slide © 2006 Thomson/South-Western Slides Prepared by JOHN S. LOUCKS St. Edward’s University Slides Prepared by JOHN S. LOUCKS St. Edward’s University.
Relative Values. Statistical Terms n Mean:  the average of the data  sensitive to outlying data n Median:  the middle of the data  not sensitive to.
Chapter 3, Part A Descriptive Statistics: Numerical Measures n Measures of Location n Measures of Variability.
Descriptive & Inferential Statistics Adopted from ;Merryellen Towey Schulz, Ph.D. College of Saint Mary EDU 496.
1 1 Slide © 2008 Thomson South-Western. All Rights Reserved Slides by JOHN LOUCKS St. Edward’s University.
Chapter Eight: Using Statistics to Answer Questions.
Unit 3: Averages and Variations Week 6 Ms. Sanchez.
Organization of statistical research. The role of Biostatisticians Biostatisticians play essential roles in designing studies, analyzing data and.
LIS 570 Summarising and presenting data - Univariate analysis.
Descriptive Statistics(Summary and Variability measures)
Chapter 6: Descriptive Statistics. Learning Objectives Describe statistical measures used in descriptive statistics Compute measures of central tendency.
Descriptive Statistics Dr.Ladish Krishnan Sr.Lecturer of Community Medicine AIMST.
NURS 306, Nursing Research Lisa Broughton, MSN, RN, CCRN RESEARCH STATISTICS.
1 1 Slide © 2008 Thomson South-Western. All Rights Reserved Slides by JOHN LOUCKS St. Edward’s University.
Data analysis and basic statistics KSU Fellowship in Clinical Pathology Clinical Biochemistry Unit
Lecture 8 Data Analysis: Univariate Analysis and Data Description Research Methods and Statistics 1.
MGT-491 QUANTITATIVE ANALYSIS AND RESEARCH FOR MANAGEMENT OSMAN BIN SAIF Session 18.
Outline Sampling Measurement Descriptive Statistics:
A QUANTITATIVE RESEARCH PROJECT -
EPIDEMIOLOGICAL INVESTIGATIONS
Methods for Describing Sets of Data
MATH-138 Elementary Statistics
Analysis and Empirical Results
Descriptive measures Capture the main 4 basic Ch.Ch. of the sample distribution: Central tendency Variability (variance) Skewness kurtosis.
Relative Values.
Central Tendency and Variability
CHAPTER 2: PSYCHOLOGICAL RESEARCH METHODS AND STATISTICS
Descriptive Statistics
Description of Data (Summary and Variability measures)
STATS DAY First a few review questions.
Numerical Descriptive Measures
Georgi Iskrov, MBA, MPH, PhD Department of Social Medicine
Descriptive Statistics: Numerical Methods
Central tendency and spread
Introduction to Statistics
Basic Statistical Terms
Descriptive and inferential statistics. Confidence interval
Numerical Descriptive Measures
Data analysis and basic statistics
Statistics: The Interpretation of Data
Univariate Statistics
Chapter Nine: Using Statistics to Answer Questions
Math 341 January 24, 2007.
Introductory Statistics
Presentation transcript:

Introduction to epidemiology HCAI Information for Action 2009 Introduction to epidemiology Meirion Evans Communicable Disease Surveillance Centre Oct 2009

What is epidemiology? The study of the distribution and determinants of health-related states or events in specified populations and the application of this study to control health problems. (JM Last. Dictionary of Epidemiology)

Epidemiology & clinical medicine “You’ve got whatever it is that’s going around”

Epidemiology & clinical medicine Populations Studies Prevention Evaluation Planning Individuals Diagnosis Treatment Curing Caring

The uses of epidemiology Describe characteristics of disease Help define and classify disease Understand natural history of disease Define health care needs & plan services Analyse causes of disease Determine aetiology & quantify individual risk Identify opportunities for prevention Evaluate prevention, treatment and care Assess effectiveness and efficiency

Five essential questions

Methods Surveillance Outbreak investigations Observational studies HCAI Information for Action 2009 Methods Surveillance Outbreak investigations Observational studies Case series Case-control studies Cohort studies Experimental studies RCTs

Purpose DESCRIBE SUMMARISE COMPARE INFER HCAI Information for Action 2009 Purpose DESCRIBE Time, Place, Person (When, Where, Who) SUMMARISE Mean & SD COMPARE Odds ratios & Relative risks INFER Confidence intervals Hypothesis testing

DESCRIBE - Time WHEN does the disease occur? HCAI Information for Action 2009 DESCRIBE - Time WHEN does the disease occur? Secular trends (long term) Point epidemics (short term) Cyclical change Seasonal variation

Time - the epidemic curve HCAI Information for Action 2009 Time - the epidemic curve Figure 1. Cases of gastroenteritis (n=45) in Hospital X, Wales by date of onset, January and February 2009 1 patient case 1 staff case

Time - patterns of spread cases cases Persistent source Point source days days cases cases Person to person transmission Propagated source weeks days

Time - estimating time of exposure A community outbreak of hepatitis A 15 50 days one case 30 days Number of cases 10 5 15 days 2 8 14 20 26 2 8 14 20 26 1 7 Exposure Date of onset

Time trends MRSA cases before and after handwashing intervention D Pittet, et al. Lancet 2000;356:1307-1312.

DESCRIBE - Place WHERE does the disease occur? HCAI Information for Action 2009 DESCRIBE - Place WHERE does the disease occur? In the community Place of residence Place of work In hospital Floor Ward or unit Operating theatre Outpatient departments

The one-variabletable Table 1. Cases of MRSA in Area X, 2009, by area of residence HCAI Information for Action 2009 The one-variabletable

HCAI Information for Action 2009 The spot map Figure 1. Cases of MRSA in Area X, 2009 by place of residence. 1 dot = 1 case

HCAI Information for Action 2009 The area map Figure 2. Incidence rate (per 100,000) of MRSA in Area X, 2009 by area of residence.

Plan view of intensive therapy unit Shading indicates location of MRSA cases Source: J Hosp Infect 1996;32:207-11.

DESCRIBE - Person WHO is getting the disease? HCAI Information for Action 2009 DESCRIBE - Person WHO is getting the disease? Sex and age group Ethnicity Pre-existing conditions Medication Invasive procedures Surgical treatment

The two-variable table HCAI Information for Action 2009 The two-variable table Area X, 2008

HCAI Information for Action 2009 Grouped bar chart Area X, 2008

HCAI Information for Action 2009 Stacked bar chart Area X, 2008

HCAI Information for Action 2009 Component bar chart Area X, 2008

Source: DH Third prevalence survey of HCAI in England Grouped bar chart Figure. HCAI prevalence by age group and gender, England 2006 Source: DH Third prevalence survey of HCAI in England

SUMMARISING data Measures of centrality Mean Median Mode HCAI Information for Action 2009 SUMMARISING data Measures of centrality Mean sum of the data divided by no. of observations Median middle value (half above, half below) Mode most frequently observed value

Normal distribution curve 12 13 14 15 16 17 18 19 20 21 22 Score or measure Total number of scores 9 8 7 6 5 4 3 2 1

Skewed distributions Positive or Right Skew Distribution mean median mode Positive or Right Skew Distribution mean median mode Negative or Left Skew Distribution

Skewed distributions Ratio of ICNs to total number of beds in NHS Trusts Source: NAO report, 2004

SUMMARISING data Measures of variability (dispersion) HCAI Information for Action 2009 SUMMARISING data Measures of variability (dispersion) Range (percentiles, interquartile range) difference between largest and smallest value Variance how far each value differs from the mean (square ea. difference, add results together, divide by no. of measurements minus one) Standard deviation (SD) square root of the variance

Different distributions Small Standard Deviation Large Standard Deviation Different Means Different Standard Deviations Same Standard Deviations Same Means

Range – percentiles Incidence of SSI by category of surgical procedure, 1997-2003 Source: NAO report, 2004

COMPARING data Comparing exposures in case and non-cases HCAI Information for Action 2009 COMPARING data Comparing exposures in case and non-cases What are the risk factors for disease? Cross-sectional studies Cohort studies Case-control studies

COMPARING data Relative risk (RR) cross-sectional and cohort studies HCAI Information for Action 2009 COMPARING data Measures of association: Relative risk (RR) cross-sectional and cohort studies Odds ratio (OR) case-control studies

The 2x2 table for a cohort study HCAI Information for Action 2009 The 2x2 table for a cohort study Incidence ill not ill exposed 49 49 98 50 % not exposed 40 % 4 6 10 Risk difference 50% - 40% = 10% Relative risk 50% / 40% = 1.25

The 2x2 table for a case-control study HCAI Information for Action 2009 The 2x2 table for a case-control study ill not ill exposed 49 49 98 not exposed 4 6 10 Odds 49/4 49/6 12.3 8.2 Odds ratio 12.3 / 8.2 = 1.5

Table from a case control study Risk factors for MRSA bacteraemia HCAI Information for Action 2009 Table from a case control study Risk factors for MRSA bacteraemia Exposure Cases n=42 Controls n=90 Odds Ratio On admission Indwelling catheter on admission 5 3 3.9 Prior admission 35 66 1.8 On or during admission Bed sore 1 12.0 Skin ulcer 2.3 During admission Central line during admission 17 60.5 Urinary catheter during admission 22 2 48.4 Blood transfusion 15 7 6.6

Making INFERENCES Estimation Hypothesis testing HCAI Information for Action 2009 Making INFERENCES Estimation To describe population parameters using information obtained from samples Point estimate e.g. sample mean Interval estimate e.g. confidence interval Hypothesis testing To reject or accept a hypothesis by testing whether observed data is consistent with it

Description vs Inference Graphical Data tables Bar graphs & pie charts Numerical Percentages Averages Range Relationships Correlation coefficient Regression analysis Inference Confidence interval Compare means of two samples Pre/post scores t test Compare frequency in two groups Risk factors RR and OR

I am 95% confident that μ is between 40 & 60 HCAI Information for Action 2009 Making INFERENCES Population Random Sample I am 95% confident that μ is between 40 & 60 Mean x = 50 Mean μ is unknown Sample

Interval estimation using a sample to estimate the population mean Population distribution Parameter B A Sample distribution Sample distribution Interval estimate

Confidence Intervals +/- 1 SD +/- 2 SD +/- 3 SD 68% Samples HCAI Information for Action 2009 Confidence Intervals +/- 1 SD 68% Samples +/- 2 SD 95% Samples +/- 3 SD 99.7% Samples

Interval estimation Estimate popn mean from sample mean HCAI Information for Action 2009 Interval estimation Estimate popn mean from sample mean Confidence interval the range of values within which the true population mean (μ) will lie 95%CI = x +/- (1.96 x SEM) x = sample mean SEM = standard error of mean = SD/√n SD = standard deviation, n = no. in sample

Prevalence of HCAI by infection type Source: DH Third prevalence survey of HCAI in England

Prevalence of HCAI by infection type Source: DH Third prevalence survey of HCAI in England