Midterm 2 Flashcards
Descriptive statistics
- Helps us organize, summarize, and describe data (usually based on samples)
- Without distorting the info it provides about the world
Inferential statistics
-Helps us generalize from the sample to the population
Graphical representations
- Pie chart = categorical, nominal/ordinal
- Bar graph = categorical, nominal/ordinal
- Histogram = quantitative data
- Frequency polygon = quantitative, continuous data
Histogram
- Shows the frequency of occurrence of each score
- X-axis contains RANGES of scores
- Y-axis represents the frequency of occurrence
Percentile rank
-Percentile rank of a score value is the percent measurements in the distribution BELOW that value
Characteristics of frequency distributions
- Shape
- Central tendency
- Variability
Shape of frequency distributions
- Symmetric = two equal halves
- Positively skewed = has score values with low frequencies that trail off towards the positive end
- Negatively skewed = has score values that trail off towards the negative end
MODALITY
- Unimodal = one peak
- Bimodal = two peaks
- Multimodal = multiple peaks
- Uniform = does not have a well define MODE
Central tendency
- Central tendency of a distribution is the score of a value that corresponds to the center of that distribution
- A typical or representative score
- Summarizes a distribution
- Allows comparison to other distributions
- Used in inferential statistics procedures
What are the 3 main measures of central tendency?
- Mean
- Median
- Mode
Mean
-numerical average, obtained by summing all the data scores and then dividing by the number of scores
- Population mean (u) vs sample mean (M)
- A PARAMETER is the true value of a quantity in the population
- A STATISTIC is the value of the same quantity based on a sample
- a statistic (ex. M) is used to estimate a parameter (ex. u)
- M is an unbiased estimator of u
Limitations of mean as a central tendency measure
- sensitive to outliers
- poor measure of central tendency for highly skewed distributions
- NOT suitable for ordinal or nominal data
Median
- 50th percentile of a distribution
- The middle score with half the measurements above it and half the measurements below it
ADVANTAGES
- Robust against outliers
- A better summary of skewed data
- Can be used with ordinal data
LIMITATIONS
-Median is NOT an unbiased estimator of any population parameter
Mode
- The score with the highest frequency
- A distribution with two frequently occurring mode values is bimodal
ADVANTAGES
-Can be used with any type of data, including nominal
LIMITATIONS
- Ignores much of the data
- Is NOT an unbiased estimator of any population data
Which measure of central tendency is best to use?
Mean
- Preferred for interval and ratio data
- symmetric distribution
Median
- Use for skewed distribution
- Outliers
- Limits the applicability of statistical tests
Mode
- Categorical data
- Multimodal distributions
Variability
-Is the extent to which scores in a frequency distribution differ from one another
Two measures of variability:
- Range
- Variance