Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
54 Cards in this Set
- Front
- Back
Data Analysis |
Describing the dataset by by computing a small number of statistics that characterize various aspects of the data. |
|
4 purposes of statistical analysis? |
1. Summarize data 2. Help us to understand 3. Show patterns 4. Interpret patterns |
|
5 types of statistical anaylsis |
1. Descriptive 2. Inferential 3. Differences 4. Associative 5. Predicted
(Progressively more complex and usually combined when used) |
|
Descriptive analysis |
Ex. Mean, median, mode, standard deviation, and range.
Portrays the "typical" respondent to reveal a general pattern of responses. Summary.
Used early and become the foundation for subsequent analysis. |
|
Inference analysis |
Ex. Standard error and null hypothesis.
Determines population parameters, test hypothesis, and estimates population values.
Generalize results of the target population. |
|
Difference analysis |
Ex. t-test of differences and analysis of differences.
Determines differences between two percentages or two or more means for groups in the sample.
|
|
Association analysis |
Ex. Correlation and cross tabulation
Determines simple relationships, if they are related in a statistical way, and by how much. |
|
Predictive analysis |
Ex. Multiple regression
Finds complex relationships for variables, forecast future events, and determines how several independent variables influence a key dependent variable.
|
|
2 sets of measures used to describe information used in a sample |
Central tendency- typical response, single piece of into.
Variability- measures describing how similar or dissimilar responses are from typical ones, set of values.
|
|
2 key questions while using descriptive measures |
1. What one number best represents the variable? 2. How well does that one number represent the variable in question? |
|
3 measures of central tendency and define |
Mode- value that occurs most often.
Median- value whose occurrence lies in the middle of an ordered set of values; halfway point.
Mean- average, must be computed. |
|
3 measures included in variability |
1. Frequency distribution 2. Range 3. Standard deviation
(tells how close or apart measures are) |
|
Frequency (percentage) distribution |
Number or percentage of times a different value appears in a particular set of values (occurrence).
|
|
Range |
Max and min values in a set of numbers. Does not tell us how often these values occur. |
|
Standard deviation |
Degree of variation or diversity in the values. (normal or bell shaped curve)
xi each individual observation x_ mean |
|
With a bell shaped distribution _________% of the value lies within ____________ times the standard deviation away from the mean. |
95% +- 1.96 |
|
Why is the squaring operation in the standard deviation formual used? |
To avoid the cancellation effect. |
|
Variance |
Standard deviation squared. |
|
With the bell shaped curve, how will the curve look with a small standard deviation vs a large standard deviation? |
Small- greatly compressed or high peak Large- flat because it is stretched out. |
|
Nominal scale |
"What is your gender?"
Mode
Frequency/percentage distribution |
|
Ordinal scale |
"Rank from 1st to 5th choice"
Median
Cumulative percentage distribution |
|
Interval scale |
"On a scale of 1 to 5, how much..."
Mean
Standard deviation/range |
|
Ratio scale |
"How many times did you..."
Mean
Standard deviation/range |
|
Average in descriptive measure |
Include. Place in column close to variable descriptions and arrange in an order. |
|
Median, mode in descriptive measure |
Don't include.
|
|
Standard deviation in descriptive measure |
Typically include, if they are mostly equal don't include. |
|
Minimum, maximum in descriptive measure |
Include if data set has several diff variables, don't report if they are the same. |
|
Frequencies in descriptive measure |
Include if researcher wants to note something about the sample (very small with great affect).
Very close to variables. |
|
Percent in descriptive measures |
Include, very close to variables. |
|
Mode in descriptive measure |
Highlight, but if obvious do not report. Largest percentage group i usually readily apparent. |
|
Statistics |
Values computed from a sample. (p) |
|
Parameters |
Values computed from a complete census that are considered to be precise and valid measures of the population. (pie sign) |
|
Inference |
Form of logic in which you make a general statement about an entire class based on what you have observed about a small set of members of that class. |
|
Statistical inference |
Sample size and statistic are used to make an estimate of the corresponding population parameter (large samples are more accurate than small ones). |
|
Statistical inference is based on what to determine what? |
Based on sample size and variability to determine the amount of sampling error. |
|
2 types of statistical inferences |
Parameter estimation and hypothesis testing. |
|
Parameter estimate |
Used to approximate the population value (parameter) through the use of confidence intervals. |
|
Hypothesis testing |
Used to compare the sample statistic with what is believed (hypothesized) to be the population value prior to undertaking the survey.
Used to accept or reject hypothesis based on sample evidence. |
|
Parameter estimation |
Using sample info to compute an interval that describes the range of a parameter such as the population mean or percentage. |
|
3 values that parameter estimation uses |
1. Population mean/percentage 2. Standard error of the statistic 3. Desired level of confidence |
|
Standard error |
Measure of the variability in a sampling distribution based on what is believed to occur were we to take a multitude of independent samples from the same population. |
|
Does the formula for mean standard error differ from a percentage standard error? |
Yes. |
|
The standard error will be ___________with larger sample sizes and ___________ with smaller sample sizes. |
Smaller Larger |
|
2 things the standard error takes into account |
Sample size and variability in sample. |
|
50-50 split |
Great variability.
Has a larger standard error than 90-10 split when sample size is the same. |
|
Population parameters are estimated with the use of _______________________. |
Confidence intervals |
|
Confidence intervals |
Degree of accuracy desired by the researcher and stipulated as a level of confidence in the form of a range with a lower and upper boundary. |
|
Most commonly used level of confidence |
95%, 1.96 |
|
A 99% confidence interval is always ___________ than 95% confidence interval if all other factors are equal. |
Wider |
|
A sample statistic is usually a ____________ or a _____________. |
Mean Percentage |
|
Hypothesis |
Expectation |
|
Hypothesized population parameter |
Value can be determined using either a percentage or a mean. |
|
Sampling distribution concept |
Our sample is one of many contributing to the bell shaped curve.
**Crux of statistical hypothesis testing. |
|
2 tests of a hypothesized population parameter value |
1. Test of a hypothesis about a percentage 2. Test of a hypothesis about a mean |