Manipulating and using Data

Manipulating and using Data

1. Primary Data

   • Data that has been gathered through original research done by the organisation or individual
   • More up to date
   • More Reliable
   • More Relevant

2. Secondary Data

   • Data that has been gathered by someone other than the user of the data
   • It is much quicker to obtain
   • It isn’t subject to the organisation/individuals’s bias
   • Should always come from a trustworthy source

3. Data must be reliable to be useful

   • Data must be reliable to be useful

4. Data Collection Methods

   • Questionairres
     • Involve a set of questions, normally in a closed question format, used to gain information for statistical analysis, or personal information from respondents
     • Every respondent answers the exact same questions. This helps to remove bias from our findings and improves the consistency of our data.
     • It can be difficult to get in-depth answers as most questions are closed and followup questions cannot be asked based on responses
   • Focus Groups
     • Involve a group of people being asked questions on a particular topic
     • Respondents are able to build on each others answers. This helps to improve the depth and detail of the responses, and so the quality of the data
     • The data produced from focus groups is qualitative, it is all descriptive and not numerical. This type of data is more difficult to analyse, especially by a computer
   • Interviews
     • Are a one-to-one meeting where an interviewer asks questions to a single respondent in order to gather information
     • Very good for drawing out detailed responses through followup questions. This can also be used to provide greater clarity and ensure questions are fully understood
     • Interviews take a long time to gather information from a wide range of people. This means it isn’t cost effective where a large number of responses are required

5. Ensuring Data accuracy

   • It is extremely important to ensure data accuracy as computers don’t have the common sense to spot errors and so if bad data is entered bad results are outputted (GIGO)
   • We can help ensure data accuracy through the use of validation and verification
   • Validation is a check to ensure data is sensible and reasonable. E.g. a length check or type check
   • Verification is a check to ensure data matches the original source. E.g. a proof reading check or double entry check

6. Data Collection User Interfaces

   • An easy to use interface must have clear navigation, good labelling and simplified input methods
   • An accessible interface should consider the individual needs of users with disabilities. Such as using a clear and simple interface, high contrast colour schemes and support changing of sizes
   • Error reduction in a user interface can be achieved through validation/verification checks, input masks and warning messages
   • An intuitive interface is easy to use even with little training. This can be achieved through making it easy to use and keeping the interface similar to paper forms or previous systems
   • Functionality in a user interface is about allowing users to be able to perform the required tasks they need from the system.
   • The performance of a user interface can be improved by ensuring that tasks can be completed in few steps, it’s easy to navigate and reducing the likelihood of errors arising
   • Compatibility affects the user interface. A highly compatible interface will allow data to be inputted to and from different IT systems