click below
click below
Normal Size Small Size show me how
Statistics
Introduction to Statistics
Question | Answer |
---|---|
Where did it come from? | Source |
A collection of observations. (Measurements,counts,survey) | Data |
Planning studies, obtaining data, organizing, summarizing, presenting, analyzing,interpreting ,drawing conclusions. | Statistics |
The complete collection of all individuals to be studied. | Population |
A subset of a population. | Sample |
A collection of data from all members of a population (Continuous study) | Census |
What is it? | Context |
How was it collected? | Sampling method |
Any measure if an entire population. | Parameter |
Any measure of a sample. | Statistic |
Measurement, Count | Quantitative |
Label | Qualitative |
Continuous-measurements Discrete-Counts | Quantitative |
Neither | Qualitative |
Nominal, Ordinal | Qualitative |
Interval, Ratio | Quantitative |
No order | Nominal |
Natural order | Ordinal |
Differences meaningful, ratios not | Interval |
Differences and ratios are meaningful | Ratio |
The respondents themselves decide whether to be included. | Voluntary response sample |
When subjects are asked for information and they give you their desired information, but not exact information. It's better if you did it yourself. | Reported Results |
Conclusions should not be based on samples that are too small. It's not representing as a whole. | Small Sample |
Not worded carefully, worded to elicit a desired response. | Worded, Loaded question |
100% of some quantity is not ALL of it, exceeding it is often not justified. | Percentages |
No treatment, observe a sample for characteristics. | Observational |
Treatment & observe its effects | Experimental |
People who don't report | Missing Data |
Someone either refuses to respond to a survey question or is unavailable. | Nonresponse |
Some parties with interests to promote will sponsor studies. | Self-Interest Study |
Percentage of | Take the percent divide it by 100 and multiply by "of" that number |
Fraction to percentage | Divide top into bottom |
Decimal to percentage | Multiply by 100 |
Percentage to decimal | Divide decimal by 100 |
"N" subjects is selected in such a way that every possible sample of the same size n has the same chance of being chosen. | Simple random sample |
selected in such a way that each individual member in the population has an equal chance of being selected. | Random sample |
We select some starting point and then select every kTH element in the population. | Systematic sampling |
Subdivide the population into at least two different subgroups so that subjects with the same subgroups share same characteristics, then draw a sample from each subgroup | Stratified sampling |
Divide the population area into sections, then randomly select some of those clusters, and then choose all the members from those selected clusters. | Cluster sampling |
Data are observed, measured,& collected at one point in time. | Cross-sectional study |
Data are collected from the past by going back in time. | Retrospective |
Data are collected in the future from groups sharing common factors. | Prospective |
Subjects are assigned to different groups through a process of random selection. Try to find a randomized way of choosing your sample. | Randomization |
subjects doesn't know whether he or she is receiving a treatment or a placebo. | Blinding |
Untreated, Unaffected. | Placebo |
Subjects didn't know and doctors didn't know either. | Double blinding |
when you are not able to distinguish among the effects of different factors. Usually unwanted. | Confounding |
Difference between a sample result and the true population result; such an error results from chance sample fluctuations. | Sampling error |
When the sample data are incorrectly collected, recorded or analyzed. | Nonsampling error |