Statistical analysis

• Quantitative data


  Type of data that deals in numbers (i.e. test scores)
• Qualitative data


  Descriptive data that is open-ended and investigative (i.e. age, gender, ethnicity)
• Descriptive statistics


  Statistics managing collected data (i.e. frequency charts or graphs)
• Inferential statistics


  Statistics used to predict how data will work on a larger population (generalizing it)
• Discrete data


  Data that can be counted (i.e. number of people in a room)
• Nominal scale


  Discrete data scale without structure or order (i.e. "short people" column and "tall people" column)
• Ordinal scale


  Discrete data scale that counts and orders but does not measure (i.e. "strongly disagree" to "strongly agree"
• Continuous data


  Data which can be measured (i.e. shoe size)
• Interval scale


  Continuous data scale that gives degrees of difference but no ratios (i.e. 1981-1983)
• Ratio scale


  Continuous data scale that processes a meaningful measurement with a zero value (weight, volume, distance)
• Dichotomy scale


  Scale with two categories when organizing data (male or female)
• Trichotomy scale


  Scale with three or more categories when organizing data
• Pie chart

  
• Frequency polygon chart

  
• Bar graph

  
• Histogram chart

  
• Central analysis


  Using the mean median and mode to summarize and find the value closest to the "middle"
• Mean


  Adding up all the numbers in a data set, then dividing it by the number of values to find the "middle" one (central tendency)
• Mean median and mode are used in central analysis
• Median


  Ordering all of the values in croissant/decroissant, then finding the one in the exact middle to get your central tendency
• Mode


  The value that appears the most times in a given set of values
• Standard deviation


  Allows researchers to understand the variation between data points (Variation)
• Range


  The difference between the lowest and highest value points in a set of values (variation)
• Range can only help researchers understand the difference between the highest and lowest score. It does not let them know what those scores mean in relation to the rest of the values
• Standard deviation allows researchers to see the average distance from the mean for a set of scores, which gives a lot more information that just range
• The higher the standard deviation, the less similar the score is to the mean
• Symmetrical distribution


  Also known as a bell curve
• Symmetrical distribution


  When the mean, median and mode are all set at the zero point after a large number of people have been surveyed
• Positive skew


  Occurs when the scores of a curve pull the mean towards the higher end of the range
• Negative skew


  Occurs when the scores of a bell curve pull the mean towards the lower end of the range
• Scatter plot


  A bunch of dots representing individual results from participants in a study whose relationship is used to determine whether or not there is a correlation between the independent and dependent variables
• Correlation coefficient


  Number between -1.0 and +1.0 used to show how closely correlated points on a scatter plot are
• Positive correlation


  When one variable increases, the other variable also increases
• Negative correlation


  When one variable increases, the other one decreases, and vice versa
• No correlation


  When there is no clear relationship between two variables when looking at points on a graph
• Null hypothesis


  The claim in statistical analysis that the effect being studied does not exist
• P value


  Probability that the null hypothesis is correct (i.e. percent chance that your study is wrong and there is no relationship) if it is less than 0.05 then your research is considered to be statistically significant, because there is less than a 5% chance you are completely wrong