Chapter 3

• Research question:

  • A question that outlines a specific scope for investigation related to the topic.
  • Often used where little research exists or the relationships between the variables are uncertain.
  • Inquisitive in nature.
  • Many possible conclusions may be formed at the end of the investigation.
• Hypothesis:

  • A measurable statement consisting of one or two variables.
  • Often used when a large body of research on the topic is available and relationships between the variables are quite certain.
  • Predictive in nature.
  • A definite conclusion is formed at the end of the investigation.
• Primary data:

  • Data that are collected first-hand.

  Examples

  • Photographs and sketches taken by fieldwork researchers.
  • Responses from closed-ended questionnaire surveys administered by fieldwork researchers.
• Secondary data:

  • Data that are collected by someone else.

  Example:

  • Books, newspaper articles, journals and maps produced by other authors.
• Quantitative data:

  • Data that can be quantified and measured.

  Example:

  • Responses from closed-ended questionnaire surveys.
• Qualitative data:

  • Data that are not easily measurable and are subjective in nature.

  Example:

  • Responses to open-ended questions in semi-structured interviews.
• Quantitative data followed by qualitative data:

  • Firstly, quantitative data are collected to identify patterns and trends.
  • Subsequently, qualitative data are collected to examine the patterns and trends observed.
• Qualitative data followed by quantitative data:

  • Firstly, qualitative data are collected to make observations.
  • Subsequently, quantitative data are collected to verify the observations.
• Limitations to consider in fieldwork:

  1. Data to be collected
  2. Time available
  3. Access to places
  4. Availability of equipment
  5. Manpower
• Risk: Falls, cuts and minor injuries

  • Students are to wear proper footwear and clothing.
  • Students are to take note of potential hazards such as uneven surfaces, steep steps and jagged rocks
• Risk: Traffic accidents

  • Students are to take note of local traffic hazards and road crossing procedures.
  • Students are to avoid collecting data on the road or in the path of cyclists.
• Probability sampling:

  • Used to select a more representative sample.
  • Samples are randomly selected, without the researcher's conscious decision.
  • This can be done by using a random number generator or die.
  • This removes bias that may come from the choices made by the researcher.
  • Has a greater chance of creating a representative sample.

  Example: Simple random sampling and Stratified random sampling
• Non-probability sampling:

  • Samples are non-randomly selected, often using the researcher's conscious decision.
  • This means that the researcher subjectively selects samples, such as family or close friends.
  • This selection may be biased.
  • Samples are unlikely to be representative as they are subjectively selected, making it hard to make generalisations about the population.
  • Used when it is impractical to select representative sample or when there is a lack of time

  Example: Convenience sampling and quota sampling
• Simple random sampling:

  • Every member of the population is given a number.
  • A random number generator is used to generate random numbers to select the samples.
• Stratified random sampling:

  • Select a sample that has a proportionate makeup to the population based on age and sex or other categories
  • Probability sampling such as random sampling is used to select the sample.
  • If random sampling is not used, it becomes quota sampling.
• Quota sampling:

  • Select a sample that has a proportionate makeup to the population based on age and sex or other categories
  • Non-probability sampling such as convenience sampling is used to select the sample, instead of random sampling.
• Convenience sampling:

  • Samples are selected because they are convenient sources of data, such as friends and people walking down a street
• Predefined response in questionary survey:

  • The predefined responses in the questionnaire survey could be short phrases, or a single word arranged in a series, or numbers.
  • Alternatively, the actual value can be recorded.

  Advantage:

  • Use of predefined responses guides participants, thus it is easier for them to answer.
  • Researchers may find predefined responses easier to analyse and interpret since they are put into fixed categories.
  • Useful for quantitative data analysis to examine patterns and trends.
• Using rating scales in the questionnaire survey.

  • Rating scales include a set of predefined responses.
  • Often used to guide survey participants to respond to questions on their opinions with a wide range of responses.
• Likert scales:

  • Present a range of responses anchored by two extreme opposing positions.
  • Can have predefined responses based on a scale of agreement (e.g. agree/disagree) or quality (e.g. excellent/extremely poor).
• Frequency scales:

  • Present a range of responses based on the number of occurrences.
• Ranking scales:

  • Used to get participants to compare items with one another.
  • Should have less than ten items to produce reliable data as when large ranking scales are used, participants would not have strong opinions about items ranked in the middle
• Mental map:

  • Used to collect data on how people experience and think visually and spatially about their environment and the dynamic interrelationships people have with their environment.
  • Participants might be given blank paper to draw features in a map form or a base map and asked to add details by labelling or annotating their perceptions of places on the map.
• Mental maps part 2:

  • Depending on the research question or hypothesis, participants may be given different base maps, instructions and tools to create their mental maps.
  • Free-form mental maps are more representative of participants view of the space around them
  • However, free-form mental maps are not easily georeferenced and mapped onto Geographical Information Systems.
  • Using drawn mental maps as discussion points, semi-structured interviews with open-ended questions can be conducted thereafter to find out more about the mapper's perceptions of the places.
• Measures of frequency: Counts

  • Total number of times something happens
• Measurements of frequency: Percentage

  • A proportion of something, expressed as a fraction out of 100.
• Mean:

  • Sum of all the values in the data set divided by the number of values in the data set.
  • Advantage: It includes every value in the data set and no data is left out to show its central location.
  • Disadvantage: It is subjected to the infuence of outliers, which can skew it, and thus not provide the central location.
• Median:

  • Middle value for a set of data that has been arranged in ascending order.
  • Advantage: It is less affected by outliers.
  • Disadvantage: However, it is not as sensitive as mean in showing the central location in a data set.
• Mode:

  • The most frequent value in a data set.
  • Advantages: Useful for categorical data like the different modes of transport le.g. car is the most frequent mode of transport) and it is not affected by outliers.
  • Disadvantage: Not very useful for continuous data (e.g. temperature over the course of the day) because there may be two or more values that share the highest frequency.
• Processing of mental map: Centering and borders

  • Features drawn at the centre capture attention, and might signal greater importance to the mapper compared with those drawn at the borders.
  • However, this may not represent reality. The positions of the different features drawn may not match reality.
• Processing of mental map: Scale of map elements

  • Comparing the scale of different map features within the map and with reality can provide insights into a mapper's familiarity and activity within the space.
  • Larger features could indicate greater familiarity and more frequent activity done there.
  • However these may not represent reality. Larger features drawn by the mapper may be smaller than other features in reality.
• Processing metal maps: Labelling

  • Labelled and annotated places indicate mappers' familiarity.
  • The content and choice of words, positive or negative, used in labelling provide information on the mappers' knowledge and emotions of the places experienced.
• Processing metal maps: Colours, legends and symbols

  • Colours used in maps can differentiate places and convey emotions, like red representing anger.
  • A legend may be included to explain the symbols that the mapper uses.
  • Symbols like hearts and stars convey personal experiences or information about places, such as a favourite or an important location to the mapper.
• Processing of metal maps: Perspective and orientation

  • Mental maps may present different perspectives:
  • Street view captures a small area with greater detail
  • Aerial view captures a large area with less details.
  • How places are positioned or oriented in relation to the surroundings reveals the mapper's experiences.
  • A place that is important to the mapper could be depicted on the map as closer to their home.
• Processing of metal maps: Other features

  • Paths, nodes, or intersections, may be added to mental maps to show the mapper's personal history with the place such as a route they have taken to go somewhere
• Interpreting mental maps:

  • We can compare actual maps with participants' mental maps to analyse the differences or inaccuracies portrayed.
  • Drawn map features can appear as distortions, mislabellings and mislocations. They are key in understanding the factors that influence the mapper's perceived space.
  • Further verification can be made with the mapper through open-ended questions asked during the semi-structured interview.
  • During the interview, the mapper may also be asked why some spaces are prominent while others are absent or ignored.
• Relationships and patterns from scatter plots and best-fit lines:

  • To determine if there is a relationship between two variables
  • If there is a positive correlation between the two variables, a positive best-fit line can be drawn through most of the data on the scatter plot.
  • Outlier may be present where it cannot be incorporated into the best fit line
  • There is no relationship if a best fit line cannot be drawn
• Recognisable geometric shapes, clusters and repetitions.

  • Patterns and relationships can appear as recognisable geometric shapes, clusters and repetitions, and analysing differences and similarities between them.
  • A common approach is finding what is common among participants
  • Repetitions or clusters of labellings, geometric shapes or drawn features found in a mental map may indicate popularity and prominence of the places.
  • Their absence could indicate unfamiliarity and a lack of interaction within the space.
• Presenting findings on maps:

  • Maps are visual representations of real-world spatial information using
  • Most map symbols are essentially variations of dots, lines and polygons.
  • It is common to find all three symbols on a single map
  • Maps consist of essential elements such as title, date, orientation, scale, legend, author and source(s)
• Presenting data using bar graph:

  • Shows total values by categories using rectangular bars.
  • Used to represent data with distinct categories or to compare data between different categories