Data Analysis Flashcards
What are the steps for analyzing qualitative data?
1) converting responses into some numerical system or categorical organization
2) tabulation
3) summarize data using descriptive statistics
What is the main technique for analyzing qualitative data?
.
What are some data analysis strategies?
.
Frequencies
The number of times each value of a variable occurs,
Most appropriate for nominal or ordinal variables
Measures of central tendency:
mean
mode
median
Measures of variability (the spread)
range quartile deviation variance standard deviation the normal curve skewed distributions
Measures of relative position
percentile ranks standard scores (z scores, t scores, and stanines)
Measures of relationship:
correlation
correlation coefficient
What are the two main methods for calculating correlation coefficient?
The Spearman Rho coefficient (for ranked data)
The Pearson r coefficient (for interval and ratio data)
The Spearman Rho coefficient (for ranked data)
For correlating ranked data
mean
Arithmetic average of all the scores
Mode
Most commonly attained score
Median
Midpoint in a distribution
range
Difference between the highest and lowest score in a distribution
quartile deviation
One-half of the difference between the upper quartile (the 75th percentile) and the lower quartile (25th percentile)
standard deviation
The square root of the variance (amount of spread between scores)
A measure of variability that is stable and takes into account every score in a distribution.
The most frequently used statistical index of variability.
The normal curve
The bell shape formed when a normal distribution is plotted as a frequency graph
skewed distribution
Non-symmetric distribution in which there are more extreme scores at on end of the distribution than at the other
percentile ranks
Measures of relative position indicating the percentage of scores that fall at or below a certain score.
standard scores (z scores, t scores, and stanines)
A derived score that expresses how far a given raw score is from some reference point, typically the mean, in terms of standard deviation units
What factors determine the choice of statistical procedures?
Scale of measurement Method of participant selection # of groups being compared # of independent variables
What are two assumptions for using a t-test and ANOVA?
The standard deviations (SD) of the populations for all groups are equal (homogeneity of variance)
The samples are randomly selected from the population.
What is the purpose of t-test?
Used to determine whether two groups of scores are significantly different at a selected probability level
What is the purpose of ANOVA?
Analysis of variance
Used to determine whether scores from two or more groups are significantly different at a selected probability level.
What is the difference between t-test and ANOVA?
t-test is appropriate for two groups
ANOVA is appropriate for multiple groups
What is the purpose of factor analysis?
It is used to identify relations among variables in a correlation matrix.
What is the purpose of chi square?
It used to compare frequencies, percentages, or proportions occurring in different patterns or groups.
Excellent analytical tool for nominal data.
How is chi square different from t-test and ANOVA?
Chi square can be used to analyze nominal data,
t-scores and ANOVA cannot.
What is the function of multiple regression?
It determines not only whether variables are related, but also the degree to which they are related.
What is the purpose of analysis of covariance (ANCOVA)?
Analysis of co-variance is a form of ANOVA that accounts for the different ways in which the independent variables are measured,taking into account the design of the study.
What is standard error?
Expected, chance error among means.
What are one-tailed tests?
Assumes that a difference can only occur in one direction.
Stanine
Standard scores that divide a distribution into nine parts
T score (Z score)
A standardized score derived from a z score by multiplying the z score by 10 and adding 50
z score
The most basic and most used standard score,
Raw score - mean, divided by the SD
expresses how far a score is from a mean in terms of standard deviation units
Allows scores from different tests to be compared across individuals
Variance
Amount of spread between scores
Small variance
The Pearson r coefficient (for interval and ratio data)
Most appropriate measure when variables to be correlated are either interval or ratio
Takes into account every score in both distributions
Most stable measure of correlation
Assumes relationship between variables is linear
What are two-tailed tests?
Assumes the results can occur in either direction
What is a major advantage to one-tailed tests?
It’s statistically “easier” to obtain a significant difference when using a one-tailed test.