Descriptive Statistics and Introduction to SPSS: Study Notes for Health Sciences

Applied Statistics for the Health Sciences

Course 1: Descriptive Statistics & Introduction to SPSS

This section introduces foundational concepts in statistics, focusing on descriptive statistics and practical data analysis using SPSS, tailored for health sciences students.

The 3 Research Components

Overview of Research Structure

• Variable Interaction: Understanding how different variables relate and affect each other in a study.

• Research Design: The plan or strategy for conducting research, including how data is collected and analyzed.

• Statistical Analysis: The process of applying statistical methods to interpret data and draw conclusions.

Statistical Analyses

Types of Statistical Analyses

• Descriptive Statistics: Summarize and describe the main features of a dataset.

• Inferential Statistics: Make predictions or inferences about a population based on sample data.

Example: Descriptive statistics might include calculating the average age of participants, while inferential statistics could involve testing whether a treatment has a significant effect.

Overview of Descriptive Statistics

Main Topics Covered

• Descriptive statistics

• Measures of central tendency

• Measures of variability

• Introduction to SPSS

Descriptive Statistics

Definition and Purpose

• Descriptive statistics are used to summarize and describe the characteristics of a dataset.

• They help to make sense of data by providing simple summaries about the sample and measures.

Types of Descriptive Statistics:

• Measures of central tendency

• Measures of variability

Measures of Central Tendency

Definition and Types

Measures of central tendency represent an indicator of the typical score in a dataset. The three main measures are:

• Mean

• Median

• Mode

Mean

• The mean is the most frequently used measure of central tendency.

• It is calculated by adding all the scores and dividing by the number of scores.

Formula:

$\text{Mean} = \frac{\sum x}{N}$

• Example: For scores 2, 3, 4, 5: $\text{Mean} = \frac{2+3+4+5}{4} = 3.5$

Problems with the Mean

• The mean is influenced by extreme scores (outliers).

• For example, in the set 1, 1, 1, 1, 20, the mean is 4.8, which does not represent the typical score.

Median

• The median is the middle score after all scores have been ordered.

• It is not influenced by extreme scores.

How to Find the Median:

• Order the scores from lowest to highest.

• If the number of scores is odd, the median is the middle score.

• If even, the median is the average of the two middle scores.

Example: For scores 1, 2, 3, 4, 5, the median is 3.

Formula:

$\text{Median} = \text{Middle value of ordered data}$

Mode

• The mode is the most frequently occurring score in a dataset.

• It is typically used with categorical data.

Example: For scores 1, 1, 2, 3, 4, the mode is 1.

Formula:

$\text{Mode} = \text{Most frequent value in the dataset}$

Measures of Variability

Definition and Importance

Measures of variability indicate the spread or dispersion of scores in a dataset. They help to understand how much the scores differ from each other.

• Range

• Interquartile range

• Standard deviation

Range

• The range is the difference between the highest and lowest scores in a sample.

Formula:

$\text{Range} = \text{Highest score} - \text{Lowest score}$

Example: For scores 1, 2, 3, 4, 5, the range is 5 - 1 = 4.

Interquartile Range (IQR)

• The IQR measures the spread of the middle 50% of scores.

• It is calculated by subtracting the first quartile (Q1) from the third quartile (Q3).

Formula:

$\text{IQR} = Q_3 - Q_1$

Example: For the dataset 1, 2, 3, 4, 5, 6, 7, 8, 9, Q1 = 3, Q3 = 7, so IQR = 7 - 3 = 4.

Standard Deviation

• Standard deviation measures how much the scores deviate from the mean.

• It is the square root of the variance.

Formula:

$s = \sqrt{\frac{\sum (x_i - \bar{x})^2}{N}}$

• Example: For scores 1, 2, 3, 4, 5, calculate the mean, subtract the mean from each score, square the result, sum the squares, divide by N, and take the square root.

Additional info: Standard deviation is widely used to assess the variability in health sciences data, such as blood pressure readings or test scores.

Introduction to SPSS

Why Learn SPSS?

• SPSS (Statistical Package for the Social Sciences) is a powerful software for statistical analysis.

• It is commonly used in health sciences for data management and analysis.

Steps for Downloading SPSS:

1. Download SPSS to your computer.

2. Open the downloaded file and install the SPSS database.

3. Double-click on the file to start SPSS.

Calculating Descriptive Statistics in SPSS

• Open the SPSS database.

• Go to Analyze > Descriptive Statistics > Descriptives.

• Select the variable of interest (e.g., Coping variable).

• Click on the blue arrow to move the variable to the analysis box.

• Click on the Options button and select desired statistics (mean, standard deviation, etc.).

• Click Continue and view the results in the SPSS output window.

Graphing Mean Scores in SPSS

• Go to Graphs > Chart Builder.

• Select Simple Bar chart.

• Add the variable to the Y-axis and the category to the X-axis.

• Click OK to generate the graph.

Data Cleaning in SPSS

• Always clean your data before analysis.

• Check for errors in data transcription.

• Assess the number of missing data points.

• Evaluate the distribution of scores (e.g., skewness, outliers).

Additional info: Proper data cleaning ensures the accuracy and reliability of statistical results, which is critical in health sciences research.

Summary Table: Measures of Central Tendency and Variability

Measure	Definition	Formula	Strengths	Limitations
Mean	Average of all scores	$\frac{\sum x}{N}$	Uses all data points	Affected by outliers
Median	Middle value in ordered data	-	Not affected by outliers	Does not use all data points
Mode	Most frequent value	-	Useful for categorical data	May not be unique
Range	Difference between highest and lowest scores	$\text{Highest} - \text{Lowest}$	Easy to calculate	Ignores distribution of scores
Interquartile Range	Spread of middle 50% of scores	$Q_3 - Q_1$	Not affected by outliers	Requires ordered data
Standard Deviation	Average deviation from the mean	$\sqrt{\frac{\sum (x_i - \bar{x})^2}{N}}$	Uses all data points	Complex to calculate