Statistics
Summarizes data → descriptive → cannot use to generalize
Analyze + draw conclusions → inferential → generalize to large population (random sample)
Common language
Measure of central tendency: mean, median, mode
Outlier when one or more data points are very different from the others
Leads to a skewed distribution
Median will be the best measure of central tendency to use
median > mean → negative skew
mean > median → positive skew
Measures of variation
Range = (largest number)-(lowest number)
Standard deviation: measure of how dispersed the data is in relation to the mean
How spread out the data points are
Normal distribution/curve (bell curve)
Symmetric (no skew)
Most data in the middle, less towards extremes
Median = mode = mean
68% → 1 SD
95% → 2 SD
99% → 3 SD
Inferential statistics: When can results be generalized?
Sample is representative of population being studied (random sampling)
More cases exist with those results (large sample size)
Variability of the data is low
Are the results due to differences in the IV or due to chance?
Statistical significance
Calculated using a variety of statistical tools (Chi-square, T-test)
How likely results are due to chance or differences in the IV
NOT how important the results are
Reported as a p-value
p-values of 0.05 or less → statistically significant, indicate results are not likely due to chance → can generalize to larger population
The results are unlikely to be obtained if there is no difference between the control and experimental groups
Summarizes data → descriptive → cannot use to generalize
Analyze + draw conclusions → inferential → generalize to large population (random sample)
Common language
Measure of central tendency: mean, median, mode
Outlier when one or more data points are very different from the others
Leads to a skewed distribution
Median will be the best measure of central tendency to use
median > mean → negative skew
mean > median → positive skew
Measures of variation
Range = (largest number)-(lowest number)
Standard deviation: measure of how dispersed the data is in relation to the mean
How spread out the data points are
Normal distribution/curve (bell curve)
Symmetric (no skew)
Most data in the middle, less towards extremes
Median = mode = mean
68% → 1 SD
95% → 2 SD
99% → 3 SD
Inferential statistics: When can results be generalized?
Sample is representative of population being studied (random sampling)
More cases exist with those results (large sample size)
Variability of the data is low
Are the results due to differences in the IV or due to chance?
Statistical significance
Calculated using a variety of statistical tools (Chi-square, T-test)
How likely results are due to chance or differences in the IV
NOT how important the results are
Reported as a p-value
p-values of 0.05 or less → statistically significant, indicate results are not likely due to chance → can generalize to larger population
The results are unlikely to be obtained if there is no difference between the control and experimental groups