data analysis psych exam

• Between group designs


  Compare different groups. For example, we might compare stress levels in psychology students versus engineering students.
• Within-group design


  focus on the same group of individuals but under different conditions or over time. For example, measuring a student's anxiety level before and after a stress management workshop. This design helps in understanding how interventions or time impact the same group.
• Variables


  what we study
• Variables can be categorical. What types?

  Categorical (Discrete) or continuous
• categorical variable


  have specific categories, like a student's major (psychology, engineering, etc.).

  represent data that can be divided into distinct categories or groups.
• Continuous variable 


  can take any value within a range, like hours of sleep per night.
• What are the four scales of measurement?


  Nominal, ordinal, interval, ratio.
• Nominal


  categorizes thing without any orders (EX:types of therapy)

  
  

  Metaphor: Think of nominal scales like sorting objects into different colored bins. Each bin represents a category, but there's no specific order to the colors. For example, sorting fruits into bins labeled "apples," "oranges," and "bananas.
• Ordinal


  Ranks data into ordered categories (ex:mild, moderate, severe anxiety)

  
  

  Metaphor: Imagine ranking your favorite ice cream flavors from 1 to 5, where 1 is your most favorite and 5 is your least favorite. While there's an order to the rankings, the difference in preference between each rank may vary.
• Interval


  measure data with equal intervals but no true zero (IQ scores)

  
  

  Metaphor: Consider measuring temperature using the Celsius scale. The difference between 20°C and 25°C is the same as the difference between 25°C and 30°C. However, 0°C doesn't represent an absence of temperature but rather a specific point on the scale.
• ratio scales


  have a true zero point (number of therapy sessions attended)

  
  

  Metaphor: Think of ratio scales like measuring lengths with a ruler. Each unit on the ruler represents an equal interval, and the zero point signifies the absence of length. For example, if one object is twice as long as another, it's a meaningful comparison because of the true zero point.
• Central tendency:


  Important for figuring out what values are typical or average in a group of data. This helps psychologists understand how groups of people behave.
• What are three measures of central tendency?

  Mean, Median, and mode
• Mean:


  The average score, calculated by adding all scores and dividing by their number. Educational psychologists use this to assess program effectiveness, like evaluating average improvements in student test scores after a new teaching method is introduced
• Median:


  The middle score when all scores are lined up. Crucial when data is skewed.
• Mode:


  The most frequent score, highlighting common behaviors or responses. Clinical psychologists may use mode to determine the most common symptoms reported by patients with a specific mental health disorder, guiding treatment approaches
• Spread and variability


  help us understand how different or similar the information in psychological data is. It's important for both doing research and applying what we learn in real-life situations.
• Range:


  It's the difference between the highest and lowest scores. Imagine it as the distance between the tallest and shortest people in a group photo.

  shows the span between the highest and lowest scores. Forensic psychologists utilize range to understand the variability in behavior patterns among different offenders,aiding in criminal profiling
• Variance


  The average of squared differences from the mean. Sports psychologists might use variance to assess the consistency of an athlete’s performance over time, crucial for developing tailored training programs.

  This tells us how much the scores differ from the mean. It's like measuring how spread out the dots are on a scatterplot.
• Standard Deviation (SD)


  It shows how much the scores vary around the mean. If scores are tightly packed around the mean, the SD is small; if they're spread out, the SD is larger. Think of it as a measure of how spread out or bunched up the data points are on a graph.

  
  

  Indicates the spread of scores around the mean. SD is particularly useful in community psychology to understand the range of responses to community-based interventions, helping to tailor programs to diverse groups.
• Sum of squares


  A 'behind-the-scenes' statistical concept, it's fundamental for calculating variance and SD. Industrial-organizational psychologists might not report this measure directly but use it to understand the spread of employee engagement scores across large organizations.

  
  

  This is a technical term used to calculate variance and SD. It's like the foundation of a building – you don't see it directly, but it's essential for the structure's stability.
• Normal Distribution


  A bell shaped curve. l. Most people in a population are like the folks living in the middle of this hill, with average characteristics. Only a few are like the ones at the very top or bottom, with exceptional traits. This pattern is common in things like IQ scores, where most people cluster around the average intelligence level.
• Skewed Distribution


  Occurs when data is not evenly distributed. In clinical psychology, certain mental health disorders may show a skewed distribution. For example, major depressive disorder might be more prevalent in certain age groups, resulting in a distribution that is not evenly spread out.
• Frequency Distributions in SPSS


  Commonly seen in SPSS outputs, frequency distributions show how often each value occurs in a dataset. While frequently used in data analysis, they're rarely included in research articles.
• For discrete (categorical) or continuous (quantitative) what are the types of graphs used?


  Discrete: bar graph, pie chart

  Continuous: histogram, line graph

  
  

  Line graphs, Bar charts, Histograms
• Discrete variable


  have specific, distinct values that are separate from each other and often represent counts or categories. They typically have a finite number of possible values or a countable number of values. Discrete variables cannot take on values between the distinct points or categories; there are gaps between the values.

  Examples of discrete variables include the number of siblings a person has, the number of pets in a household, or the outcome of rolling a six-sided die. These values cannot be divided into smaller parts.
• What are differences between continuous and discrete variables?

  • Continuous variables are measurable and can take on any value within a range of numbers. They can include fractions or decimals, and there are infinitely many possible values within their range.
  • Discrete variables are also measurable, but they can only take on specific, distinct values. These values are often counted, and there are typically gaps between the values since they cannot have values between the distinct points or categories.
• Line graphs


  Suitable for continuous data over time. Developmental psychologists use line graphs to depict cognitive development across different ages.

  • good for showing how something changes over time, like a person's height or test scores as they get older. Imagine plotting points on a graph and connecting them with lines to see the overall trend.
• Bar charts


  Best for discrete data. A social psychologist might use a bar chart to display the occurrence of various social behaviors in different demographic groups.

  • great for comparing different groups or categories, like the number of students in each grade level or the favorite colors of people in different age groups. Picture bars of different heights representing the amount of something in each category.
• Histograms


  Ideal for showing the distribution of continuous data. Clinical psychologists use histograms to illustrate the frequency of different levels of symptom severity among patients.

  • used to see how data is spread out, especially for things that can have many different values, like test scores or symptom severity. It's like dividing the data into buckets or bins and counting how many fall into each one, then showing that with bars on a graph.
• Z score

  help make data comparable across different situations and allow us to test hypotheses effectively using the Z-test. They standardize information, making it easier to understand and analyze results from various studies or cases.
• what are 2 types of Mean and Standard deviation


  Population Parameters and Sample Statistics
• Population Parameters (μ (mu), σ (sigma))


  These define the true mean (μ) and standard deviation (σ) of the entire group under study. Given the impracticality of surveying entire populations, these values are often theoretical.

  These are the average (mean) and spread (standard deviation) of the entire group you're studying. They're like the true characteristics of a big group, but since it's hard to study everyone, we estimate these from smaller samples.
• Sample Statistics (x, s)


  Derived from a select subset of the population, these statistics (x for mean, s for standard deviation) serve as practical estimations for a population.

  These are estimates of the population parameters based on a smaller group (sample) from the population. They're like snapshots of the big group, helping us understand its characteristics.
• Z scores


  measure how many standard deviations an individual data point is from the mean of its distribution.
• How is Z score calculated?


  z = (x-μ)/σ, where x is the raw score, μ is the population mean, and σ is the population standard deviation.

  • make it easier to compare different sets of data, especially in psychology where we often want to compare individual scores to a larger group.
• What do Z scores do for psychologists?

  Standardize data

  • help compare individual test scores to average data. A Z-score of 0 means the score is average. +1 or -1 indicates a score is one standard deviation above or below average. This helps understand how test results compare to a standard group.
• 68-95-99.7 Rule:


  This rule tells us that most scores (about 68%) fall within one standard deviation of the average, and the majority (about 95%) fall within two standard deviations.
• Percentiles and Probabilities


  Percentiles help us understand where someone's score ranks compared to others, with positive Z-scores indicating above-average scores and negative Z-scores indicating below-average scores.

  
  

  show where a score ranks compared to others. A Z-score of +1 means the score is higher than about 84% of people. A Z-score of -1 means the score is lower than about 16% of people. This helps understand how someone's performance compares to others.
• Central Limit Theorem


  This theorem says that if you take lots of samples from a population and calculate the means, those means will form a normal distribution, no matter the shape of the original population.