Portfolio Task 7 - Data Analysis

Portfolio Task 7 - Data Analysis

1. Exploratory data analysis

   • Coding open-ended questions
     • Used in postal questionnaires and interviews
     • Used when the researcher has no clear hypotheses regarding answers, which will be numerous and varied
     • Best way is to code the information in terms of ideas and themes
       • To reduce the large number of individual responses to a few general categories of answers that can be assigned a numerical code
     • In order to analyse open-ended questionaires
       • 1. Place all similar answers in a general category and assign them with a code
         • 2. Divide them into 2-4 sub-categories and assign them a code
           • 3. Chose the method of analysis which you think is suitable for your data
             • Descriptive method
             • Inferential method

2. Recording the information

   • Recording Scheme
   • Production coding
   • First column of the data summary form
     • Designated for the respondent's number
   • The rest of the columns
     • Coded answers to the questions in the questionaire
   • Can be applied to open-ended questions as well to closed-ended questions
   • After recording the information the field of statistics can be applied to the raw data
     • Descriptive statistics method
     • Inferential statistics method

3. The descriptive statistics method

   • Frequency distribution
     • When summarising large amounts of raw data it is often useful to distribute the data into categories or classes
       • To determine the number of individuals or cases belonging to each category
         • This is called 'Category Frequency'
           • Tabulation
             • The simplest way to show the frequency of observations of each response to each variable under investigation
           • Bar chart
             • Horizontal or vertical bar charts can be used with the frequency distribution table or as an alternative method of presentation in the dissertation
           • Pie chart
             • Represents the proportion of the respondents and is presented as percentages
           • Graph
   • Measurement of central tendency
     • Used when you have a group of data and you wish to find the most typical value for the group or the score which all other scores are evenly clustered around
       • Mean
         • Average of all values in a set of data
       • Mode
         • The value which occurs with the greatest frequency within a set of numbers
           • The most common value
           • May not exist when every number is unique
           • May contain more than one mode
       • Median
         • The middle value
   • Measurement of dispersion
     • Shows you degree by which numerical data tend to spread about an average value
       • Known as variation or dispersion
       • Represented by the formula of Mean Deviation
       • Methods include Standard Deviation and Normal Distribution

4. Inferential statistics method

   • Comparison of results for different parts of the sample
   • Statistical significance test of the difference between the proportions
   • Step 1: Formulate the research hypothesis in terms of the predicted result
     • 2: State the null hypothesis
       • 3. Decide which test to use
         • 4.Calculate and obtain the test statistics
           • 5.Decide whether result is significant
             • Judge whether results are significant or are due to chance
               • P<0.05
                 • Reject null hypothesis
                   • Results are significant
               • P<0.05
                 • Accept null hypothesis
                   • Results are insignificant
   • Parametric test (the t-test)
     • Used to compare the difference between the mean scores of two samples
   • Non-parametric test (the chi-square test)
     • A test of association between two sets of data
       • Used only when the data is nominal or ordinal
         • Predicts how many subjects in each group will fall into certain categories
   • Spearman rank correlation coefficicent
     • A non-parametric test for measuring the difference in ranking between two groups of respondent's scoring a number of issues, attributes or factors
     • Applied when the question is...
       • Requesting a ranking value
       • Requesting a scoring value
       • Requesting rating values
   • Pearson product moment correlation coefficient
     • Used when you have two sets of scores and you want to calculate whether there is a strong relationship between them

Imágenes y archivos del mapa