SPM 573 RME slide set 01 SPM 573

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Introduction to Clinical Epidemiology • This discipline has changed much in the 20 th-Century • Last, J. M. 1988. What is “Clinical Epidemiology? ” Journal of Public Health Policy 9 (2): pp. 159 -163. • In the early 20 th-Century, so-called “epidemiology” was the study of epidemics, with an emphasis mainly on infectious diseases • 1918 Spanish flu epidemic: over a ten-month period between 25 -40 million people died world-wide…this flu originated as a swine-borne virus similar to today’s H 1 N 1 influenza virus • The 1930’s saw a shift in epidemiology toward the study of general risk of specific medical events (births, deaths) and disorders (diseases, injuries, etc. ) in populations

SPM 573 (RME): slide set 01 Clinical Epidemiology Continued • Infectious diseases - historical points & patterns of interest. . . • Pre-20 th Century: the major killers (besides accidents) were the infectious diseases (e. g. , influenza, diphtheria, smallpox, typhus, malaria, cholera, pneumonia, etc. ) • 1798: Edward Jenner tested his smallpox/cowpox vaccine • 1918: Spanish flu global epidemic (25 -40 million deaths) • 1920's: the first large-scale public health programs in vaccines and immunization begin • 1950's: polio controlled in the U. S. • 1970's: smallpox effectively eradicated world-wide • 1980 -1990's: emergence of public concern over major sexually-transmitted diseases (STD's), particularly AIDS

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Location, Time, Scale and Scope • Morbidity (more generally, medical disorder) and mortality are rarely distributed in any regular or uniform pattern, but this doesn’t mean we can’t find predictability in the patterns • More or less predictable clusters of disease, disorder and death over time and space can be found in epidemiology • But our reporting of disease, disorder and death can often be mistaken and prone to considerable error • One area of concern in the study of epidemiology is the role played by publicity and the mass-media…sometimes we find a big deal made out of “spectacular but trivial” conditions, while the more serious conditions get less attention • Case in point: Summer 2011 – deaths from Naeglaria fowleri

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Image from theguardian. com/ (viewed 4 -30 -2012) Image from nature. com/ (viewed 4 -30 -2012) Summer 2012: much more serious… Image from thepapercutnews. wordpress. com/ (viewed 4 -30 -2012)

SPM 573 (RME): slide set 01 2010 -2011 Cholera Outbreak in Haiti • 12 January 2010: 7. 0 Richter scale earthquake devastates Haiti • Butler, D. 2011. No quick fix for Haiti cholera. Nature 478 (20 October [7369]): pp. 295 -296. • Chin, C. -S. , J. Sorenson, J. B. Harris, W. P. Robins, R. C. Charles, R. R. Jean. Charles, J. Bullard, D. R. Webster, A. Kasarskis, P. Peluso, E. E. Paxinos, Y. Yamaichi, S. B. Calderwood, J. J. Mekalanos, E. E. Schadt, and M. K. Waldor. 2011. The origin of the Haitian cholera outbreak strain. New England Journal of Medicine 364 (1): pp. 33 -42. • Mumby, P. J. , R. Vitolo, and D. B. Stephenson. 2011. Temporal clustering of tropical cyclones and its ecosystem impacts. Proceedings of the National Academy of Sciences [PNAS] 108 (43): pp. 17626 -17630. • Rinaldo, A. , E. Bertuzzo, L. Mari, L. Righetto, M. Blokesch, M. Gatto, R. Casagrandi, M. Murray, S. M. Vesenbeckh, and I. Rodriguez-Iturbe. 2012. Reassessment of the 2010– 2011 Haiti cholera outbreak and rainfall-driven multiseason projections. Proceedings of the National Academy of Sciences [PNAS] 109 (17): pp. 6602 -6607.

SPM 573 (RME): slide set 01 2010 -2011 Cholera Outbreak in Haiti • Rinaldo et al. 2012: Pre-2010, cholera had never been reported in Haiti… • No experience among local health workers • No significant level of endemic immunity or resistance • By December 2010 (end of the first year)… • 170, 000 cases of cholera reported • 3, 600 deaths from cholera • The time and location couldn’t have been worse: the epicenter of the quake was near the densely packed and impoverished city of Port-Au-Prince with the rainy summer not far off • The culprit strain has been identified as one from halfway around the world, in Bangladesh (epidemics in 2002 and 2008)

SPM 573 (RME): slide set 01 Images from Rinaldo et al. , 2012 projected 12 January 2010 quake epicenter

SPM 573 (RME): slide set 01 Haiti’s 2010 cholera mortality rate was over 20 times higher than the global rate

SPM 573 (RME): slide set 01 2012 -2013 Avian H 7 N 9 Influenza

SPM 573 (RME): slide set 01 Hvistendahl, M. , D. Normile, and J. Cohen. 2013. Despite large research effort, H 7 N 9 continues to baffle. Science 340 (26 April [6131]): pp. 414 -415. • Mainly in China • Widespread in poultry • As of 26 April 2013: 108 cases reported, with 22 deaths (20% mortality) • Related to H 7 N 1 strain in Italy in 1999 • Are influenza outbreaks predictable?

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Image from: https: //www. antiviralintelistrat. com/1/viral_taxonomy (viewed 4 -21 -2014)

SPM 573 (RME): slide set 01 The Ebola Virus • Ebola virus (along with Marburg virus) is classified in the viral Family Filoviridae • The viruses form filaments of variable lengths • It carries a single-stranded RNA genome • The genome consists of seven genes, and comes in five strains, four of which cause disease • Ebola virus causes a form of haemorrhagic fever (EHF) with high and rapid lethality Image source: p. 4 in Baize et al. 2014 scale bar = 0. 1 m

SPM 573 (RME): slide set 01 Ebola Virus & Disease: Risk Factors • 1 st EHF diagnosed in 1976 • Ebola virus is vectored by some species of African primates and fruit bats • Animal-human transmission by way of physical contact with wastes or bodily fluids • Human-human transmission by physical contact with bodily fluids or wastes • At high risk: health-care workers (nosocomial), animal handlers, bat guano traders Image source: p. 4 in Baize et al. 2014 scale bar = 0. 1 m

SPM 573 (RME): slide set 01 Baize et al. 2014

SPM 573 (RME): slide set 01 Baize et al. 2014

SPM 573 (RME): slide set 01 Baize et al. 2014

SPM 573 (RME): slide set 01 Note: the WHO considers the Reston ebolavirus to be nondisease causing

SPM 573 (RME): slide set 01 Vogel, G. 2014. Are bats spreading Ebola across Sub-Saharan Africa? Science 344 (11 April [6180]): p. 140.

SPM 573 (RME): slide set 01 Feldmann, H. and T. W. Geisbert. 2011. Ebola haemorrhagic fever. Lancet 377 (9768): pp. 849 -862.

SPM 573 (RME): slide set 01 Feldmann, H. and T. W. Geisbert. 2011. Ebola haemorrhagic fever. Lancet 377 (9768): pp. 849 -862.

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 no reported cases

SPM 573 (RME): slide set 01 1976 -2012: 2, 351 cases 1, 576 deaths = 67. 03% mortality no reported cases

SPM 573 (RME): slide set 01 Ebola Cases 1976 -2014 GIS map by J. Montague, using ESRI Arc. View 9. 1 (2004) data sources: Baize et al. 2014, and http: //www. who. int/mediacentre /factsheets/fs 103/en/ (viewed 4 -21 -2014)

SPM 573 (RME): slide set 01 Kuehn, B. M. 2015. As ebola epidemic begins to slow, trials of drugs and vaccines speed up. Journal of the American Medical Association (JAMA) 313 (10): pp. 1000 -1002.

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Clinical Epidemiology Continued • Epidemic: specific events and/or conditions found in excessive prevalence • Endemic: specific events and/or conditions found in predictably regular prevalence • The challenge in clinical epidemiology is to statistically distinguish between “predictably regular” and “excessive” • Paul, J. R. 1938. President’s address: Clinical epidemiology. Journal of Clinical Investigation 17 (5): pp. 539 -41. • Clinical epidemiology is the “marriage between quantitative concepts used by epidemiologists to study diseases in populations and decision making in the individual case which is the daily fare of clinical medicine. ”

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Reardon, S. 2011. A world of chronic disease. Science 333(29 July [6042]): pp. 558 -559.

SPM 573 (RME): slide set 01 Reardon, S. 2011. A world of chronic disease. Science 333(29 July [6042]): pp. 558 -559.

SPM 573 (RME): slide set 01 Why Take a Population View? • Imagine you are seeing patients one day • A 30 -year old woman comes in complaining of abdominal pain and cramps, fever, and diarrhea-like distress, and she is anemic • She reports feeling OK up until the day before • You look further: There is a bloody discharge in her stool sample, and a blood test reveals a severe shortage of blood plateletes (thrombocytopenia) • You first suspect colitis (inflammation of the colon) • What could be happening? Ulcers? Crohn’s disease? Irritable bowel disorder? Food poisoning? • The next day, symptoms of kidney failure appear • Ah! Could it be an extremely rare enterohemorrhagic E. coli?

SPM 573 (RME): slide set 01 Example: 2011 E. coli Outbreak in Germany Source: www. npr. org (6 June 2011)

SPM 573 (RME): slide set 01 2011 E. coli Outbreak: Early Data • 19 May 2011: Germany’s Robert Koch Institute reported three cases of hemolytic uremic syndrome admitted on the same day in early May to a Hamburg hospital • Reports of new cases accumulated rapidly, the majority of these patients were adult women • The main symptoms included diarrhea and acute kidney failure • The culprit was soon identified as shiga-toxin-producing Escherichia coli bacteria mainly of the serotype O 104: H 4, often associated with farm animals (mainly ruminant cows), and transmitted mainly by handling of fecal-contaminated water • The World Health Organization (WHO) noted a similar outbreak in Japan in 1996

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 E. coli Outbreak Continued • Frank, C. , D. Werber, J. P. Cramer, M. Askar, M. Faber, M. a. d. Heiden, H. Bernard, A. Fruth, R. Prager, A. Spode, M. Wadl, A. Zoufaly, S. Jordan, K. Stark, and G. Krause. 2011. Epide-mic Profile of Shiga-Toxin-Producing Escherichia coli O 104: H 4 Outbreak in Germany - Preliminary Report. New England Journal of Medicine 364 [Electronic document available before print 10. 1056/nejmoa 1106483 nejm. org, June 2011 [viewed 7 -20 -2011]): pp. e 1 -e 11. • The outbreak centered mainly in northern Germany • The majority of cases developed between the first week of May and the first week of June, though the reporting of cases continued well into mid-July

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Note: the date for report of a case is NOT the same as the date for onset of the case

SPM 573 (RME): slide set 01 Epidemics Continued • Other recent examples of “epidemic outbreaks” in the public perception… • “Epidemic outbreak” of salmonella-infected chicken eggs [Neuman, W. 2010. Egg recall expanded after salmonella outbreak. New York Times Online (18 August): viewed 29 August]. • “Epidemic outbreak” of antibiotic-resistant strains of bacteria [Ferber, D. 2010. From pigs to people: The emergence of a new superbug [on MRSA: methicillin-resistant Staphylococcus aureus]. Science 329 (27 August [5995]): pp. 1010 -1011. ] • By and large, clinical epidemiology is a study of how risk is distributed in a population

SPM 573 (RME): slide set 01 Ferber, D. 2010. From pigs to people: The emergence of a new superbug [on MRSA: Methicillin-resistant Staphylococcus aureus]. Science 329 (27 August [5995]): pp. 1010 -1011.

SPM 573 (RME): slide set 01 Ferber, D. 2010. From pigs to people: The emergence of a new superbug [on MRSA: methicillin-resistant Staphylococcus aureus]. Science 329 (27 August [5995]): pp. 1010 -1011.

SPM 573 (RME): slide set 01 Analytical Studies:

SPM 573 (RME): slide set 01 Framingham Heart Study (FHS) – The First Major Prospective Study http: //www. nhlbi. nih. gov/about/framingham/ (viewed 8/14/2008)

SPM 573 (RME): slide set 01 Framingham Heart Study (FHS) • Cerebrovascular stroke is today one of the leading causes of death in the U. S. (roughly 500, 000 deaths per year) • 1940’s: deaths from strokes in older war veterans (from Spanish American War and WW-I) began to increase • Long-term care of aging veterans became a priority • Phase-1: 1948 -1964, study was initiated in 1948 by the U. S. Veterans Administration (VA) to identify cause(s) of stroke • 5, 200 healthy persons (“stroke-free”) were selected in 1948 to participate in a long-term (16 -year) prospective study • By 1964, hyperstension (high blood pressure) was identified as the leading risk factor for strokes …the Framingham Study continues today

SPM 573 (RME): slide set 01 Clinical Epidemiology Continued • Again, imagine you are seeing patients • In a sense, you are in the business of investigation • You are also in the business of profiling • Suppose a 65 year-old man, 5’ 7’’ and weighing 150 lbs. walks into the examination room - you form a certain first impression • But would your first impression be the same if the 65 -year old man is 5’ 7” and weighs 260 lbs. ? • Your expectations about the individual is guided by your understanding of population parameters • This is where clinical epidemiology begins

SPM 573 (RME): slide set 01 Probability and Sampling in Epidemiology • Based upon your understanding of statistical distributions you have certain expectations for your patient • Suppose our 65 year-old is: • 5’ 7”, 150 lb. (BMI = 23. 5, a common occurrence? ) Or instead: • 5’ 7”, 260 lb. (BMI = 40. 7, a rare occurrence? ) • Your approach depends both on your medical experience and your sense of probability • Probability: the mental processes used leading to belief that a particular event will occur (or has occurred)

SPM 573 (RME): slide set 01 Your Expectations for the 65 Year-Old Man • You have two sources of knowledge to tap: • Personal experience • Published clinical studies • How common are BMI = 23. 5 and BMI = 40. 7 among older men? • See: Paniagua, M. A. , J. E. Malphurs, and L. F. Samos. 2006. BMI and low bone mass in an elderly male nursing home population. Clinical Interventions in Aging 1 (3): pp. 283 -287. • For additional insight, see: Alley, D. E. , E. J. Metter, M. E. Griswold, T. B. Harris, E. M. Simonsick, D. L. Longo, and L. Ferrucci. 2010. Changes in weight at the end of life: Characterizing weight loss by time to death in a cohort study of older men. American Journal of Epidemiology 172 (5): pp. 558 -565.

SPM 573 (RME): slide set 01 Honolulu Heart Study (HHS) Program http: //www. nhlbi. nih. gov/resources/deca/descriptions/honolulu. htm (viewed 8/14/2008)

SPM 573 (RME): slide set 01 Honolulu Heart Study (HHS) Program • A prospective study initiated in 1965 in Honolulu, HI • National Institutes of Health (NIH), sub-unit of National Heart and Lung Institute • American men of Japanese ancestry born in 1900 -1919 and living on the island of Oahu in 1965 (most are now deceased) • “Notch babies: ” U. S. persons born between 1917 -1921 • Age at entry (1965): 46 to 65 years old • Initial sample size in 1965 = 8, 006 men (nearly 7, 700 were still alive and included in a subsequent 1972 study) • N = 100 randomly sampled men from the 1972 participants • We will use this sample in our first assigned Take-Home report

SPM 573 (RME): slide set 01 All 100 records are available in this Excel spreadsheet are posted on Blackboard

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 5’ 7” and 150 lbs, BMI = 23. 5 5’ 7” and 260 lbs, BMI = 40. 7

GMS 507: slide set 02 The Problem of Apples-to-Oranges • In any examination of a particular patient we look for patterns • Our patterns are built over the years, but they are often based on scattered and distinctly different studies • Question: Will our 65 -year old man selected at random be be underweight? Overweight? Obese? • We might look for clues at our 100 men in the HHS sample (1965), average = 53. 7 years • But we might also consider the sample of 57 elderly men sampled in 2000 in a Miami nursing home (see Paniagua et al. 2006), average = 72. 6 years • Our 65 -year old man, however, is not a member of either sample…which sample should be more relevant?

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 02

SPM 573 (RME): slide set 02

GMS 507: slide set 02 Comparing Apples to Oranges • The two samples of men come out of completely different sampling populations • Younger (HHS) vs. older (nursing home) • Geographically different (Honolulu vs. Miami) • Temporally different (1965 vs. 2000) • Ethnically different (Japanese ancestry vs. S. Florida) • Variable activities (HHS) vs. nursing home • Thus, apples-to-oranges: what accounts for the differences? • Place? Time? Culture? Genetics? Lifestyle? We are not certain, and this is typical of clinical epidemiology • First, we need some review of probability

SPM 573 (RME): slide set 01 Epidemiology and Biostatistics • Meaning of statistics depends on context: • Collections of recorded data (observations, events, etc. ) • Calculations performed on data records • Theoretical inferences concerning patterns in data • What do statisticians do? • Design experiments to maximize information and minimize bias • Analyze patterns in the data • Interpret patterns • Significant pattern: one resulting from factors other than chance alone

SPM 573 (RME): slide set 01 How do we Analyze Research Data? • Consider a study in which we collect a sample of observations • For simplicity today we’ll use our 100 HHS men • Hypothesis: prediction about the nature of our observations • Hypothesis: age and smoking status are unrelated • Our so-called “dependent variable” (response variable) smoking status (smoker vs. non-smoker) • Our so-called “independent variable” is age in years • Extraneous variable: one that is unknown or ignored • Random variable: value that varies according to chance alone

SPM 573 (RME): slide set 01 To be Randomly Sampled from 100 Men • What does it mean to be randomly picked out of a population? • Chance alone affects the selection • “Sampling error: ” “luck of the draw” • For two or more persons to be selected randomly from the same population: • Each person in the population has an equal chance of being selected first • 1 st person selected completely at random • All remaining persons are equally likely to be selected second • 2 nd person selected completely independent of the 1 st item • And so on…

SPM 573 (RME): slide set 01 Approaches to Biomedical Statistics • Descriptive statistics refers to the organization of data into tables, plots and histograms, and to the calculation of simple measures such as averages and standard deviations • In other words, this is what we do when we describe the pattern • Most people, even many scientists, believe this is what statistics is all about • Inferential statistics refers to methods which establish levels of certainty about the pattern • In other words, we use inferential statistics to help us decide whether or not the observed pattern is due to chance alone

SPM 573 (RME): slide set 01 Nominal Data • Value assigned according to non-numerical quality • “Either-or” variables, e. g. : smoker vs. non-smoker insured vs. uninsured male vs. female placebo treatment vs. experimental treatment • More than two categories, e. g. , blood type (A, B, AB, O) State of residence (FL, NY, WA, etc. ) • Consider our sample of 100 men from the HHS study • With nominal data we find no sensible scale of ranking of the categories along a scale

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Ordinal Data • Like nominal variables, ordinal variables are not scaled in any numerical context • But unlike nominal variables, ordinal variables do have a sensible order of rank • Examples: • Measure of patient’s day-to-day condition, e. g. , +1 = improved -1 = deteriorated 0 = unchanged • Educational status for our 100 HHS men (next slide) • The order (ranking) does make a difference on an ordinal scale

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Quantitative Data • Unlike nominal and ordinal data, quantitative scales of measure utilize numerical values • Interval-scales are those lacking a true zero-value • Negative values are possible on an interval scale, e. g. : • Degrees Celsius ( C)… 20 C is NOT “twice as warm” as 10 C • Economic accounting data (e. g. , profit-loss statements) • Ratio-scales contain true zero points • Negative values are not possible on a ratio-scale, e. g. : • Degrees Kelvin ( K)… 20 K is “twice as warm” as 10 K • Height in cm, weight in kg, etc.

SPM 573 (RME): slide set 01 • Farenheit scale (T F) invented in 1724 by the German phycicist Daniel Gabriel Fahrenheit (1686 -1736) • Metric celsius scale (T C) invented in 1742 by the Swedish phycicist Anders Celsius (1701 -1744) • Kelvin scale (T K) invented in 1848 by the English physicist William Thompson (a. k. a. , Lord Kelvin: 18241907) • T F and T C belong on an interval scale (no true zero point) • T K belongs on a ratio scale

SPM 573 (RME): slide set 01 Interval-Scale, Ratio-Scale Data • Discrete: can only take on whole integer values, e. g. , number of children per family • Continuous: can be measured with any degree of precision • Precision: closeness of repeated measurement of the same item • Accuracy: closeness of a measured value to the true value • We won’t be concerned here with the details of precision or accuracy

SPM 573 (RME): slide set 01 Distributions of Ratio Scale Data • Many (but not all) ratio-scale variables appear in a so-called “normal” (Gaussian) distribution • Gaussian distribution is roughly “bell-shaped: ” 1. Symmetrical about the mean 2. Width of the curve indicates variability 3. Tall, thin distributions (less variability with the population) vs. short, fat distributions (more variability within the population) • Example from our 100 HHS men…BMI (kg/m 2)

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Question: is there any difference in age between smokers and non-smokers?

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Which One is True?

SPM 573 (RME): slide set 01 Both! These are the Same Data!

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 H 0 = Null Hypothesis HA = Alternative Hypothesis H 0: observed pattern (smoking status and age) due to chance alone HA: observed pattern due to factors other than chance

SPM 573 (RME): slide set 01 H 0 = Null Hypothesis HA = Alternative Hypothesis H 0: no cause-effect relationship present HA: there is a cause-effect relationship present

SPM 573 (RME): slide set 01 H 0 = Null Hypothesis HA = Alternative Hypothesis H 0: no significant pattern present in the data HA: significant pattern is present in the data

SPM 573 (RME): slide set 01 Question Does the average smokers equal the average of non-smokers? H 0: smoker = non-smoker

SPM 573 (RME): slide set 01 Example from Clue Did Professor Plum commit the murder? H 0: Plum did it!

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Now, consider our null hypothesis about smoking and age H 0: smoker = non-smoker Is it true?

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01 Excel Pivot Tables • Use the Pivot. Table feature to summarize data in a worksheet, then list and display that data in a table format • The interactive quality of a Pivot. Table allows you to freely rearrange, or “pivot, ” parts of the table structure around the data • Summarize data values within the table • A Pivot. Table’s summary function controls what type of calculation is applied to the table data • Unless you specify otherwise, Excel applies the SUM function to numeric data and the COUNT function to data fields containing text • You can easily change the SUM function to different summary function

SPM 573 (RME): slide set 01 Steps in Creating the Pivot Table • Use the following guidelines to create a Pivot. Table: • Review the source data • Determine the purpose of the Pivot. Table and write down the names of the fields you want to include • Determine which field contains the data you want to summarize and which summary function you want to use • Decide how you want to arrange the data • Determine the location of the Pivot. Table

SPM 573 (RME): slide set 01

SPM 573 (RME): slide set 01