Presentation on theme: "Frequency distributions and graphing data:"— Presentation transcript:
1Frequency distributions and graphing data: Levels of MeasurementFrequency distributionsGraphing data
2Stages in scientific investigation: Obtain your data:Usually get data from a sample, taken from a population.Descriptive statistics:Reveal the information that's lurking in your data.Inferential statistics:Use data from a sample to reveal characteristics of the population from which the sample data were presumably selected.
3Levels of measurement: 1. Nominal (categorical or frequency data):When numbers are used as names.e.g. street numbers, footballers' numbers.All you can do with nominal data is count how often each number occurs (i.e. get frequencies of categories).
42. Ordinal:When numbers are used as ranks.e.g. order of finishing in a race: the first three finishers are "1", "2" and "3", but the difference between "1" and "2" is unlikely to be the same as between "2" and "3".Many measurements in psychology are ordinal data - e.g., attitude scales.
5Many measurements in psychology are interval data - e.g., IQ scores. When measurements are made on a scale with equal intervals between points on the scale, but the scale has no true zero point.e.g. temperature on Celsius scale: 100 is water's boiling point; 0 is an arbitrary zero-point (when water freezes), not a true absence of temperature. Equal intervals represent equal amounts, but ratio statements are meaningless - e.g., 60 deg C is not twice as hot as 30 deg!Many measurements in psychology are interval data - e.g., IQ scores.
64. Ratio:When measurements are made on a scale with equal intervals between points on the scale, and the scale has a true zero point.e.g. height, weight, time, distance.Measurements in psychology which are ratio data include reaction times, number correct, error scores.
7What kind of measurement is a Likert scale? Likert scales are often used to measure attitudes and opinions:How attractive is Simon Cowell?(1 = “highly unattractive”, 7 = “highly attractive”)1234567Is this scale interval?1234567Or ordinal?1234567Strictly speaking, these are ordinal data – but commonly treated as interval measurements.
8Nominal data masquerading as scale measurements: SPSS uses numbers as codes for nominal data.Here “1” = “male” and “2” = “female. These are names, not numbers!
9Frequency distributions: 50 scores on a statistics exam (max = 100):
10Score Freq Score Freq Score Freq Score Freq Raw (ungrouped) Frequency Distribution:Score Freq Score Freq Score Freq Score Freq
11Grouped Frequency Distributions: Class interval width = 3ScoreFrequency94-96191-9388-90685-871082-8479-8176-7873-75270-72567-6964-6661-63Class interval width = 5ScoreFrequency95-99190-94285-891580-841075-79970-74665-69560-64
15Relative Frequency Distributions: Useful for comparing groups with different totals.Group A: N = 50ScoreRaw Freq.96-100391-95486-901181-851576-80871-7566-70261-65Total:50Rel. Freq.6 %8 %22 %30 %16 %4 %100 %Group B: N = 80ScoreRaw Freq.96-100391-95486-901881-852476-801171-75966-70561-656Total:80Rel. Freq.3.75 %5.00 %22.50 %30.00 %13.75 %11.25 %6.25 %7.50 %100 %Relative frequency = (cell total/overall total) x 100
16Raw Frequency and Relative Frequency Distributions: Only the scale of the graph changes - not the pattern of frequencies.