Scribd Logo
Upload

Welcome to Scribd!

  • 19 views

    QCA2Sampling and Units of Analysis

    Uploaded by

    fikru terfa
    This document discusses important considerations for determining sampling and units of analysis in content analysis projects. It explains that sampling may be necessary when the data source is too large or scattered, and that both presence and absence of content must be analyzed. The appropriate balance of data needs and feasibility must be found. Sampling is recommended when data extends over long periods of time or contains too much information, or when focusing on particular aspects. Sampling is not needed when the data set is limited, complete, or unique, or when qualitative analysis will be used. The document outlines strategies for sampling and developing codes, and provides guidance on determining appropriate units of analysis based on the phenomenon of interest and natural divisions in the data.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd

    QCA2Sampling and Units of Analysis

    Uploaded by

    fikru terfa
    19 views11 pages
    This document discusses important considerations for determining sampling and units of analysis in content analysis projects. It explains that sampling may be necessary when the data source is too large or scattered, and that both presence and absence of content must be analyzed. The appropriate balance of data needs and feasibility must be found. Sampling is recommended when data extends over long periods of time or contains too much information, or when focusing on particular aspects. Sampling is not needed when the data set is limited, complete, or unique, or when qualitative analysis will be used. The document outlines strategies for sampling and developing codes, and provides guidance on determining appropriate units of analysis based on the phenomenon of interest and natural divisions in the data.

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses important considerations for determining sampling and units of analysis in content analysis projects. It explains that sampling may be necessary when the data source is too large or scattered, and that both presence and absence of content must be analyzed. The appropriate balance of data needs and feasibility must be found. Sampling is recommended when data extends over long periods of time or contains too much information, or when focusing on particular aspects. Sampling is not needed when the data set is limited, complete, or unique, or when qualitative analysis will be used. The document outlines strategies for sampling and developing codes, and provides guidance on determining appropriate units of analysis based on the phenomenon of interest and natural divisions in the data.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    19 views11 pages

    QCA2Sampling and Units of Analysis

    Uploaded by

    fikru terfa
    This document discusses important considerations for determining sampling and units of analysis in content analysis projects. It explains that sampling may be necessary when the data source is too large or scattered, and that both presence and absence of content must be analyzed. The appropriate balance of data needs and feasibility must be found. Sampling is recommended when data extends over long periods of time or contains too much information, or when focusing on particular aspects. Sampling is not needed when the data set is limited, complete, or unique, or when qualitative analysis will be used. The document outlines strategies for sampling and developing codes, and provides guidance on determining appropriate units of analysis based on the phenomenon of interest and natural divisions in the data.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    You are on page 1of 11

    Sampling and Units of

    Analysis
    Making the Basic Decisions for
    a Content Analysis Project
    Basic Considerations
     Content analysis requires sufficient data
     desired content may be scattered thinly
     analysis may require large volume of data
     Absence is as important as presence
     need to compare presence with absence
     need to understand context of presence
     Finding the right balance
     how much data the research requires
     what is feasible for one person to do
    When and Why to Sample

     each unit of data source is fairly small

     data source extends over a long time

     data source contains way too much

     you are interested in particular aspects

     you need material from multiple sources


    When Not to Sample
     you have only a limited amount of data
     the data source is complete in itself
     you need the entire set to make the case
     there is sufficient internal variability
     the data set is unique or has special properties
     you will do primarily qualitative analysis
     it is feasible to include the entire set
    Two Content Analysis Strategies
     Traditional procedure (hypothesis testing)
     develop codes on a sample
     throw out that sample
     apply fixed codes to the rest of the data
     Contemporary approach (exploratory)
     start with small sample for familiarity
     expand gradually but use all the material
     develop codes and analysis iteratively
     Usually need to begin with exploratory
     Usually not testing a clear hypothesis
    Get Started with a Test Sample
     purpose is to become familiar with data
     find out what is POSSIBLE
     what content does it contain?
     what questions could you answer with it?
     how can you extract relevant content?
     how much effort does it take?
     to plan a feasible research project
     start with a few cases of the text data
    Sampling Unit vs. Unit of Analysis
     Sample the form the data source provides
     Unit of Analysis can be smaller
     sampling texts, using sentence or paragraph
     sampling films, using scenes
     sampling events, using phases, relations, etc.
     sampling interactions, using exchanges
     Unit of analysis CONTAINS what you want
     Unit of analysis defines N or denominator
    Determining Units of Analysis
     Level of the phenomenon of interest
     how does it appear in the material?
     what context is needed to interpret it?
     Are there already natural units to the data
     does it come in small pieces already?
     are there clear internal divisions?
     are larger units appropriate to the task?
     Will the volume of data be appropriate
     will you have enough “cases” to analyze?
     can you manage that much coding?
    Multiple and Nested Units
     Counting incidence
     can count every incident and sum for unit
     can count presence/absence in larger unit
     Flexible units such as time periods
     code in individual data units
     can combine units later to clarify patterns
     Comparison between sets of data
     code units for two or more sets of data
     combine data by set for analysis
    Unit of Analysis vs Coding Unit
     Unit of Analysis
     what you code WITHIN
     what you compare in the analysis
     you can combine but not divide units later
     Coding Units
     what you actually code for each unit of analysis
     level at which something is described
     you can combine but not divide codes later
     Scale of these two determines coding time
    Three Basic Principles
     Make units only as small as necessary
     for the type of coding you will do
     for the type of analysis you will do
     Code everything you need for every case
     code characteristics of the units as context
     code at the level you can see in the data
     You can combine later but you cannot divide
     Units of analysis can be combined easily
     Codes can also be combined easily
     Dividing requires going back and starting over

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy