Data Classification & Collection Methods

• Module 4A presents data classification, organization, and different forms of data presentation.

Data Fundamentals

• Data consists of factual information recorded for analysis, serving as the raw material for statistics.
• Raw/ungrouped data includes data collected in an investigation that isn't systematically organized.
• Grouped data is raw data presented in a frequency distribution.

Purposes of Data Gathering

• Data gathering serves several purposes including characterization, assessment, evaluation, control, prediction and improvement.

Data Collection Methods

• Direct/Interview Method involves person-to-person interaction for data collection.
• Indirect/Questionnaire Method uses written responses from questionnaires.
• Registration Method is enforced by organizations to record data.
• Observation Method determines cause-and-effect relationships.
• Experimentation is a scientific method using all senses to measure outcomes.

Qualitative Data

• Deals with descriptive categories or attributes relating to words and language.
• Examples include eye or hair color, ethnicity, or brand of ice cream.

Quantitative Data

• Numerical and countable, able to be given a numerical value.
• Examples include weight, age, distance, or number of newborns.

Discrete Quantitative Data

• Can only take specific numerical values, obtained through counting, cannot be expressed in fractions.
• Examples include pregnancies, hospitalizations, or number of countries.

Continuous Quantitative Data

• Takes any value within an interval, obtained by measuring, and expressed in fractions.
• Examples include body mass, height, blood pressure, weight, and age.

Nominal Qualitative Data

• Classifies data into categories with the lowest level of measurement that describe a name, label, or category without natural order.
• Examples include college courses, gender, ethnicity, or brand of toothpaste.

Ordinal Qualitative Data

• Ranks qualitative data, arranging it in order and examples include level of anxiety, academic rank, or winners in a competition.

Interval Quantitative Data

• Ranks data with meaningful differences, has equal intervals.
• Lacks a true zero point as exemplified by Celsius or Fahrenheit temperature scales & IQ test results as well as age measured in years

Ratio Quantitative Data

• Includes interval characteristics and starts at a true zero value, representing the highest level of measurement.
• Examples include weight, height, temperature in Kelvin and earned income

Population and Sample

• Population (N) is a finite or infinite set of objects, events, or individuals and the capital "N" denotes population size.
• Sample (n) is a limited collection selected from a population, with "n" denoting sample size.

Random Sampling Techniques

• Lottery/Fishbowl Sampling involves writing names/numbers on paper, placing them in a container.
• Systematic Sampling takes every kth element from an arranged population.
• Stratified Random Sampling partitions the population into subgroups.
• Multistage/Multiple Sampling uses several stages to obtain a sample, still done at random.

Non-Random Sampling Techniques

• Judgment/Purposive Sampling selects based on population characteristics and study objectives.
• Quota Sampling is quick and convenient, with researchers choosing elements at their convenience.
• Cluster Sampling, or area sampling groups the population into clusters.
• Incident Sampling uses readily available samples.
• Convenience Sampling draws the sample from a readily available part of the population
• This method is useful for pilot testing.

Data Presentation Forms

• Textual combines text with numerical facts.
• Tabular presents numerical facts concisely in statistical tables.
• Graphical uses figures for clear data relationships.

Types of Graphs and Charts

• Bar graphs use equal-width bars or rectangles to show data and illustrate frequencies
• Circle/pie graphs show the relationship of components to a total.
• Histograms use vertical bars to represent frequency of a range of values.
• Line graphs show relationships between two sets of quantities using plotted points and line segments.
• Picture graphs/pictographs use symbols to represent quantities.
• Map graphs/cartograms present geographical data with legends.
• Scatter plots display the relationship between two quantitative variables.
• Stem-and-leaf plots divide data into "stem" and "leaf".
• Box-and-whisker plots graphically represent quantitative data, including the minimum, median, maximum, and quartiles.
• Frequency distribution tables arrange raw data into class intervals with frequency.

Descriptive Measures in Module 4B

• Descriptive measures are numbers that summarize sets of data.
• They include measures of central tendency and dispersion/variation.

Central Tendency Measures

• Indicate the center or typical value of a data set and include the mean, median and mode.
• Mean is the sum of all values divided by the number of observations
• Median is the middle position in an array of values and for ungrouped data, it is the middle number if there is an add number of items
• If there is an even number of items, the the mean of the two middle values provides the median
• Mode is the most frequent score.

Measures of Dispersion

• A single value describing the spread of distribution, including range, interquartile range, variance and standard deviation.
• Range is the difference between highest and lowest values.
• Interquartile range is the length of the middle 50%.
• Variance measures the spread between numbers in a data set.
• Standard deviation is the square root of the variance

Correlation Analysis in Module 4C

• Correlation analysis studies the relationship between independent and dependent variables.
• The correlation coefficient (r) determines the linear relationship between two variables.

Scatter Plots

• Scatter plots are visual representations of the relationship between two variables.

Types of Correlations

• Pearson correlation
• Spearman correlation
• Kendall Rank Correlation
• Point-Biserial Correlation

Pearson's Moment Correlation Coefficient

• Measures the statistical relationship between two continuous variables based on covariance.
• Provides information on the magnitude and direction of the relationship.

Simple Linear Regression Analysis

• Differs slightly from correlation analysis, aiming to predict future values of a dependent variable, depending on an independent variable.
• It approximates the relationship between the two variables with a straight line.

Simple Linear Regression

• Uses the coefficient of determination to determine the percent of variation.
• The regression or prediction line is drawn on a scatter plot.