C2 LAB

• Data Collection Procedure
• Questionnaire:

  • Series of questions designed to collect information
  • Most common type of instrument used
  • Typically filled out by participants
• Types of Questions:

  • Open ended questions
  • Closed ended questions
  • Closed ended questions can elicit more detailed responses
  • Responses require more effort to encode for data analysis
  • Easy to administer
  • Uniform and pre-coded
  • Can be encoded and analysed in a short time
• Interview:

  • Verbal communication between the researcher and the participant, during which information is collected
• Types of Interview:

  • Unstructured
  • Structured
  • Structured interviews allow flexibility in questioning
  • Order of questions are designed prior to the interview
• Sampling in interview:

  • Random sampling
  • Non-representative sampling
  • Non-representative sampling includes:
  • Key informants: one-on-one interview with a point person
  • Focus group discussion: small group of people interviewed at the same time to informally discuss specific topics under the guidance of a moderator
• Review of records:

  • Collection of data from existing records using an abstraction form
  • Common in case control studies
• Observation:

  • Behaviors that can be observed and measured using observation checklists or rating scales
  • Requirements:
  • Develop standard protocol for data collection
  • Blinding
  • Train observers
  • Calibrate equipment
• Data Processing
• Data Processing:

  • Systematic procedure to ensure that the information/data gathered are complete, consistent and suitable for data analysis
• Data Coding:

  • Transforming collected information/observation into numbers (cohesive categories) which can be more easily encoded, counted and tabulated
  • Purpose of Data Coding:
  • Allows rapid storage of data
  • Minimizes errors in encoding data
  • Guidelines for Data Coding:
  • Number of codes must be kept to a minimum (preferably <8)
  • It should be exhaustive and mutually exclusive
  • Adopt coding convention for questions with similar answers
• Data Encoding:

  • Entering of data in a spreadsheet
  • Use computer programs for encoding
  • Examples of software for encoding: SPSS, MS Excel, MS Access
• Data Editing:

  • Inspection and correction of any errors or inconsistencies in the information collected
  • Purpose of Data Editing:
  • To make changes/corrections as early as possible
  • To ensure completeness, consistency and legibility of data entries
  • To prepare the data for analysis
• Data Analysis
• Data Analysis:

  • The process of evaluating data using analytical and statistical tools to discover useful information
• Considerations in Choosing a Statistical Test:

  • Objective of Analysis
  • Level of Measurement of the Variable
  • Study Design
• Data Presentation
• Data Presentation:

  • The method of summarizing, organizing and communicating information using a variety of tools
• Methods of Data Presentation:

  • Tabular Method & Graphical Method
• Tabular Presentation:

  • Compact way of presenting data in columns and rows
• Parts of a Table:

  • Table number
  • Title
  • Boxhead
  • Stub
  • Body
  • Footnotes
  • Source
• Guidelines in Table Construction:

  • It should appear immediately after the text where it is first cited
  • All tables should have a uniform style
  • Categories must be mutually exclusive
  • The unit of measurement
• • Class interval: width of class distribution
  • Frequency: records the number of times a result appears in class interval
  • Cumulative frequency: adds the frequency of the previous row to the frequency of the current row
  • Percentage: lists the percentage of the frequency in each class interval
  • Cumulative percentage: adds the percentage of the previous row to the percentage of the current row
• Types of Tables:

  • Dummy Table:
  • Skeleton tables that give a preview of expected table outputs from the study
  • Purpose: help clarify instrument, assist protocol reviewer, aid computer programmer
  • Master Table:
  • Shows distribution of observations across several variables of interest in a study
  • Presents detailed statistical data and facilitates generation of smaller tables
  • Frequency Distribution Table:
  • Shows actual number of observations falling in each range or the percentage of observations
  • Parts of a Frequency distribution table:
• • Each bar shows how a whole is made up of its component parts
  • Histogram:
  • Represents quantitative data in terms of frequencies of continuous quantitative variable
  • The area of rectangle is proportional to both the frequency and the width
  • Frequency polygon:
  • Displays the frequency of continuous quantitative variable
  • Frequencies are plotted against the corresponding midpoints of the classes
  • Advantageous if ≥ 2 distributions are being depicted in a single graph
  • Line graph/Diagram:
  • Intended to show trends or changes in the variable with time
• Graphical Presentation:

  • Pie graph:
  • Describes how a whole is divided into parts
  • Shows the percentage of total observations falling into each category of a qualitative variable
  • Bar graph:
  • Presents data in terms of frequencies per category
  • Used in comparing numerical measurements of qualitative variable or discrete quantitative variable
  • Height of the bar is proportional to their values
  • Bars should be of equal width and separated by gaps
  • Component Bar Diagram:
  • Used for comparing the compositions of two or more different groups
• • Also known as Time series charts
  • Scatterplot:
  • Graph in which the values of two variables are plotted along two axes
  • Used to show relationship between two quantitative variables
  • Box plot:
  • Shows skewness of data by comparing the mean and median
  • Useful for showing description of large quantitative data including range, quartiles, spread, shape, tail lengths, and outliers
• Data Editor:

  • Views of the Data Editor:
  • Data editor: spreadsheet-like method for creating and editing data files
  • Two views: Data view, Variable view
  • Data View:
  • Rows represent a case or an observation
  • Columns represent a variable or characteristic being measured
  • Cells contain data values only; single value for each cell; cannot contain formulas
  • No "empty" cells within the boundaries of the data file; blank cells are converted to system missing values
  • Variable View:
  • Contains descriptions of the attributes of each variable in the data file
• • Other attributes: Number of digits, Number of decimal places, Column width
• • To define variable attributes:
  • Variable name: must be unique, cannot contain spaces, reserved keywords cannot be used as variable names
  • Data type: assumed to be numeric, can be defined in the Variable Type dialog box
  • Variable labels: descriptive labels, can contain spaces and reserved characters not allowed in variable names
  • Value labels: allows creation of a list of value labels
  • Missing values: defines specified data values as user-missing
  • Measurement level: Nominal, Ordinal, Scale
• Managing the Data Editor:

  • Entering Data:
  • Data values are not recorded until you press Enter or select another cell
  • To enter anything other than simple numeric data, you must define the variable type first
  • Editing Data:
  • Modifying data values such as changing, cutting, copying, pasting data values, adding and deleting cases, adding and deleting variables, changing the order of variables
  • Replacing or modifying data values: double click the cell, edit the value directly in the cell, press Enter
  • Data Editor Display Options:
• • The View menu provides display options for the Data Editor:
  • Fonts: controls the font characteristics of the data display
  • Grid Lines: toggles the display of grid lines
  • Value Labels: toggles between the display of actual data values and user-defined descriptive value labels; available only in Data View
  • Data Editor Printing:
  • A data file is printed as it appears on the screen, grid lines are printed if currently displayed, value labels are printed in Data View if currently displayed, otherwise, actual data values are printed
• • To print data editor contents: File > Print