Statistics is a fundamental tool for architects in Kenya who must analyze data from site surveys, material tests, and user feedback to make informed design decisions. This chapter equips architecture students with the ability to identify, collect, organize, and present data effectively, enabling evidence-based planning and communication with stakeholders. Mastery of statistical methods enhances precision in estimating costs, understanding environmental impacts, and optimizing spatial layouts in architectural projects. The focus is on practical application of statistical techniques relevant to architectural contexts.

5.1 Data Identification, Collection and Organization Assessment

In architectural practice, correctly identifying, collecting, and organizing data ensures that design decisions are based on accurate and relevant information. Data can range from measurements of building materials to user occupancy patterns or environmental conditions at a site. This topic covers methods to systematically gather and structure such data for analysis, crucial in preparation for project design, evaluation, and reporting.

5.1.1 Methods of Identifying Data

Data identification involves recognizing what type of data is needed for a specific architectural task. This includes distinguishing between qualitative and quantitative data, and understanding their sources in architectural projects such as site conditions, building codes, and client requirements.

The fundamental formula for classification of data types is not numerical but conceptual:

• Quantitative data: measurable, numerical values such as dimensions, costs, or temperature.
• Qualitative data: descriptive attributes such as material type, user satisfaction, or architectural style.

Worked Examples

Example 1:
Given: An architect needs to collect data on the number of windows in a building and the type of glazing used.
Identify the data types.

• Number of windows = quantitative data (countable number)
• Type of glazing = qualitative data (categorical description)

Example 2:
Given: Data collected on daily temperature and humidity levels at a construction site.
Identify data types.

• Temperature (°C) = quantitative (continuous)
• Humidity (%) = quantitative (continuous)

Example 3:
Given: Survey responses on user satisfaction with lighting quality in a hospital.
Identify data types.

• User satisfaction rating (scale 1–5) = quantitative (ordinal)
• Comments on lighting = qualitative (textual)

5.1.2 Techniques of Data Collection

Data collection in architecture involves gathering measurements, observations, or survey responses. Common techniques include direct measurement, questionnaires, interviews, and environmental monitoring.

The process can be summarized by the following steps:

1. Define the objectives of data collection clearly to focus on relevant parameters.
2. Choose appropriate data collection methods depending on the data type and project needs.
3. Prepare data collection instruments such as measuring tapes, forms, or digital sensors.
4. Conduct data gathering systematically to maintain consistency and accuracy.
5. Record data precisely and organize it for analysis.
6. Validate data to check for completeness and errors.

Worked Examples

Example 1:
Given: A survey to measure wall thickness in a new hospital wing.
Steps: Use a calibrated tape measure to record thickness at 10 different points.

• Objective: Measure wall thickness
• Method: Direct measurement with tape measure
• Data: Thickness values in mm

Example 2:
Given: Collecting user feedback on seating comfort in a university lecture hall using questionnaires with rating scales.
Steps: Distribute questionnaires, collect responses, and tabulate scores.

Example 3:
Given: Measuring noise levels at a retail business construction site using a sound level meter at different times.
Steps: Set sound level meter, record readings every hour, organize data by time.

5.1.3 Organizing Data for Analysis

Organizing data means structuring raw data into formats suitable for analysis such as lists, tables, or spreadsheets. This process includes classification, coding, and summarizing data points.

The organization formula can be represented as:

$$ \text{Organized Data} = f(\text{Raw Data, Classification, Coding, Summarization}) $$

Where \(f\) is the process of structuring.

Steps for data organization:

1. Sort data according to categories or measurement scales.
2. Assign codes for qualitative data to enable quantification.
3. Enter data into tables or spreadsheets systematically.
4. Check for missing or inconsistent entries.
5. Summarize data using counts, totals, or averages.
6. Prepare data for visualization or statistical analysis.

Worked Examples

Example 1:
Given: Raw data of window counts and glazing types from a hospital project.
Organize data into a table:

Example 2:
Given: User satisfaction ratings (1 to 5) collected from a hotel survey.
Organize data by frequency counts of each rating.

Example 3:
Given: Temperature readings from a county government building site over a week.
Organize data by date and time in a spreadsheet.

Chapter Summary

This chapter explored the process of data identification, collection, and organization, emphasizing effective methods to gather relevant information for analysis. It then covered various techniques for data presentation, including tables, bar charts, histograms, pie charts, and line graphs, to visually communicate statistical findings. Measures of central tendency such as mean, median, mode, and range were introduced and calculated to summarize data sets. The chapter also examined measures of dispersion, focusing on range, variance, and standard deviation to describe data variability. Fundamental probability laws were explained, including conditional probability, to understand the likelihood of events. Different probability distributions were studied, highlighting the normal, binomial, and Poisson distributions and their applications. Sampling methods and the concept of sampling distributions were discussed to support inference about populations. The chapter concluded with techniques for determining confidence intervals, performing hypothesis testing for various sample sizes, and analyzing relationships between variables through correlation coefficients and simple linear regression analysis.