Data Analysis.pptx
- 2. BASICTERMINOLOGY Statistics,Biostatistics,Variable, Measurement Scale,Data, Medical Data, type of data, Data Analysis
- 3. VARIABLE,SCALE,DATA • Variable isa characteristics whichvaries and • Scale is a device on which observations are taken. • Data is set of observations/measurements taken from experiment/survey or external source of a specific variable using some appropriate measurement scale
- 4. What is Statistics?... A science of: • Collecting numerical information (data) • Evaluating the numerical information (classify, summarize, organize, analyze) •Drawing conclusions based on evaluation
- 5. Statisticsand Bio-statistics Statistics is generally understood as the subject dealing with number and data, more broadly it involves activities suchas collection of data from survey or experiment, summarization or management of data, presentation of results in a convincing format, analysis of data or drawing valid inferencesfrom findings. Whereas Bio-Statistics is science which helps us in managing medical data with application of statistical methods/techniques/tools or a collection of statistical procedures particularly well-suited to the analysis of healthcare-related data
- 6. What ismedicaldata? Thedata whichisrelated to patient careor numerical information regarding patient’sclinical characteristics, mortality rate survival rate, diseasedistribution, prevalenceof disease,efficacy of treatment,and other suchinformation iscalledmedical data.
- 7. NATUREOF DATA • Data is the value you get from observing (measuring, counting, assessing etc.) from experiment or survey. • Data iseither categorical or metric. • Categorical data is further divided into Nominal and ordinal, • Whereas metric into discrete and continuous (quantitative)data.
- 9. Types of Data Qualitative Data Quantitative Data Nominal Ordinal Discret e Continuous
- 10. Types of Data… Quantitative Data: There is a natural numeric scale (can be subdivided into interval and ratio data) Example:- age, height, weight Qualitative Data: Measuring a characteristic for which there is no natural numeric scale (can be subdivided into nominal and ordinal data) Example:- Gender, Eye color
- 11. Quantitative data... Discrete Data : When data is taken from some counting process, Values are distinct and separate. Values are invariably whole numbers. Example: Number of children in a family, number of patients in different wards, number of nurses, number of hospitals in different cities. Continuous Data : When data is taken from some measuring process Those which have uninterrupted range of values. Can assume either integral or fractional values. Example : Height, Weight, Age
- 12. Qualitative Data… Nominal data : To classify characteristics of people, objects or events into categories. No meaningful order of classes. Example: Gender (Male / Female). Ordinal data (Ranking scale) : Characteristics can be put into ordered categories. Example: Socio-economic status (Low/ Medium/ High).
- 13. Primary Scalesof Measurement Scale Basic Characteristics Common Examples Examples Permissible Statistics Descriptive Inferential Nominal Numbers identify &classifyobjects Social Security nos., numbering of football players Brandnos., store types Percentages, mode Chi-square, binomial test Ordinal Nos.indicate the relativepositions of objectsbutnot the magnitudeof differences between them Quality rankings, rankingsof teams in a tournament Preference rankings, market position, social class Percentile, median Rank-order correlation , Friedman ANOVA Interval Differences between objects Temperature (Fahrenheit) Attitudes, opinions, index Range, mean, standard Product- moment Ratio Zeropointis fixed, ratios of scale values can be compared Length, weight Age, sales, income, costs Geometric mean,harmonic mean Coefficient of variation
- 14. Nominal Scale Thenumbersserve only aslabels or tags for identifying and classifying objects. When usedfor identification, there isa strict one-to-one correspondence between the numbersand the objects. Thenumbersdo not reflect the amountof the characteristic possessedby the objects. Theonly permissible operation onthe numbersin a nominal scale is counting. Social security number,hockey players number, brands, attributes, stores and other objects
- 15. ORDINAL SCALE • A ranking scale in which numbers are assigned to objects to indicate therelative extentto whichtheobjectspossess somecharacteristic. • Can determine whether an object has more or less of a characteristic thansomeotherobject, but nothow muchmoreor less. • Any series of numbers can be assigned that preserves the ordered relationshipsbetween theobjects. • So relative position of objects not the magnitude of difference between the objects. • In addition to the counting operation allowable for nominal scale data, ordinal scales permit the use of statistics based on percentile, quartile, median.Possessdescriptionand order, notdistanceor origin
- 16. INTERVALSCALE • Numerically equal distances on the scale represent equal values in the characteristic being measured. • It permits comparisonof the differences between objects. • Thedifference between 1 & 2 issameas between 2 & 3 • Thelocation of the zero point isnot fixed. • Both the zero point and the units of measurement are arbitrary. • Everyday temperature scale. Attitudinal data obtained on rating scales.Donot possessorigin characteristics (zero and exact measurement)
- 17. RATIOSCALE • Thehighest scale that allows to identify objects, rank order of objects, and compare intervals or differences. It is also meaningfulto computeratios of scale values • Possess all the properties of the nominal, ordinal, and interval scales. • It hasanabsolutezero point. • Height, weight, age, money. Sales, costs, market share and numberof customersare variables measuredona ratio scale • All statisticaltechniquescanbe applied to ratio data.
- 18. • After collecting the accurate and reliable data successfully by using the appropriate method from the source, the next step is how to extract the pertinent and usefulinformation buried inthe data for further manipulationand interpretation. • Theprocessof performing certain calculations and evaluation in order to extract relevant information fromdata iscalled data analysis. Data Analysis
- 19. • The data analysis may take several steps to reach certain conclusions. Simple data can be organized very easily, while the complex data requires proper processing. • The word “processing” means the recasting and dealing with data makingready for analysis. Cont……
- 20. •Questionnaire checking/Data preparation •Coding •Cleaning data •Applying mostappropriate tools for analysis Stepsin data analysis
- 21. QUESTIONNAIRECHECKING A questionnaire returned from the field may be unacceptable for several reasons. Partsof the questionnaire maybe incomplete. Thepattern of responsesmayindicate that therespondent did not understand or follow the instructions. Theresponsesshowlittle variance. One or morepages are missing. Thequestionnaire isreceived after the pre-established cutoff date. Thequestionnaire isanswered by someonewho doesnot qualify for participation.
- 22. DATAPREPARATION Preparation of datafile It isimportant toconvertraw data intoa usabledata for analysis (codingwhere it needed), simply transform information fromquestionnairetocomputer database Theanalysis andresultswill surelydependonthequality of data Thereare possibilitiesof errorsin handling instruments, raw data, transcribing, data entry,assigningcodes,values, value labels Data needtobecleanedtofulfill theanalysis conditions
- 23. CODING Coding means assigning a code, usually a number, to each possible response to each question.
- 24. •One of the first stepsin analyzing data isto “clean” it of any obviousdata entry errors: Outliers? (really high or low numbers) Example: Age = 110 (really 10 or 11?) •Value entered that doesn’t exist for variable? Example:2 entered where 1=male, 0=female •Missing values? Did the person not give an answer?Was answer accidentally not entered into the database? Data cleaning
- 25. •May be able to setdefined limits whenentering data Preventsentering a 2 whenonly 1, 0, or missingare acceptable values •Univariate data analysis isa usefulway to check the quality of the data Cont……
- 26. Data analysis
- 27. Statistical Applications... Descriptive Statistics Summarizes or describes the data set at hand. Evaluate the data set for patterns and reduce information to a convenient form. Inferential Statistics Use sample data to study associations, or to compare differences or predictions about a larger set of data.
- 28. Descriptive Statistics… Measures of central tendency are statistics that summarize a distribution of scores by reporting the most typical or representative value of the distribution. Measures of dispersion are statistics that indicate the amount of variety or heterogeneity in a distribution of scores.
- 29. Descriptive Statistics… oMeasures of Central Tendency oMean oMedian oMode oMeasures of Dispersion oRange oVariance oStandard Deviation
- 30. Data Analysis May Be Descriptive Or Inferential Descriptive Contains Mean, Median , Mode, Standard Deviation, Frequency, Percentage, Range, Percentile On The Other Hand Confidence Interval, Testing Of Hypothesis, P-value, ANOVA etc. Related To Inferential
- 31. UNI-VARIATEDESCRIPTIVEANALYSIS Graphical Method For nominal& ordinal data weuseBar or pie chart Forcontinuousdata weuse histogram Numerical method For nominal& ordinal data weuseFrequency/proportions Forcontinuousdata weuseMean,Standarddeviation
- 32. Summary Guide Scale Nominal Ordinal Displaying data Histogram Box-plot Bar chart, Pie chart Bar chart, Pie chart Summarizing data Mean, Median, SD Frequency table, Percentage s, Proportion Frequency table, Percentage s, Proportion
- 33. Summary Guide for appropriate analysis for two variable Type of variables Graphical display Relationship Categorical- categorical Multiple bar Contingency table Categorical- Scale Box-plot Descriptive statistics for each group Scale-scale Scatter plot Correlation
- 34. MedicalData Analysis Graphs,Bar,PieCharts Descriptive Analysis Frequency(f), Percentage (%), Proportion Categorical Data Chi-square (χ2) test Inferential Analysis Z-test Univariate Histogram Descriptive Analysis Mean± S.D ContinuousData Z-test (n>30) Inferential Analysis t-test (n<30) Multivariate Categorical Data DescriptiveAnalysis Multiple Bar Charts ContigencyTable InferentialAnalysis Association χ2, OR, RR Prediction,Logistic Regression ScatterPlot, Box Plot Descriptive Analysis Relationship, Regression, Correlation ContinuousData t-test Inferential Analysis ANOVA, Multiple Regression