01_Research&Assessment_STATISTICS Flashcards
What is Regression Analysis?
A statistic that provides an estimate of one variable based upon other variables
How do you calculate what the population size is predicted to be in 6 months?
Data:
Current population = 3000
Monthly births = 400
Monthly deaths = 150
- Calculate birth rate (400/3000 = 0.13333)
- Calculate death rate (150/3000 = 0.05)
- Calculate the overall rate of change by subtracting the death rate from the birth rate (0.13333-0.05 = 0.083)
- Calculate the change in population over time
~(3,000 *1.0833 = 3,249.9) Month 1
~(3,249.9 *1.0833 = 3520.6) Month 2
~(3520.6 *1.0833 = 3813.9) Month 3
~(3813.9 *1.0833 = 4131.6) Month 4
~(4131.6 *1.0833 = 4475.7) Month 5
~(4475.7 *1.0833 = 4848.6 ) Month 6 - Round up to 5000
What is Regression Analysis?
Analysis of the relationship between two variables
What is the difference between the lowest and highest score on an exam?
Range
What is the Coefficient of Correlation?
Measures the degree to which two variables are related
What is the Cohort Survival Projection Method?
-method for forecasting future population based upon the survival of the existing population and the births that will occur.
-typically it involves five-year increments
What is correlation?
-strength of a “linear” relationship
-very similar (but not identical) to the slope of a regression between the two variables
-“strong” correlation would be a value close to either +1 or -1
-“weak” correlation would be a value close to 0.
Between 1960 and 2010, nationally marriage rates have
Declined from 72 percent to 51 percent
What is the Cohort Survival Projection Method?
-method for forecasting future population based upon the survival of the existing population and the births that will occur.
-typically it involves five-year increments
In data analysis, what is oversampling?
-Overrepresenting certain historically underrepresented populations in data collection
-Goal: achieving representative results.
What is the primacy effect?
-tendency to choose earlier answers in a list of elaborated options
(When provided with a list of responses in a closed-ended survey question, respondents are more likely to choose earlier options)
What is Recall Bias?
-occurs when interviewees present incorrect accounts or inaccurate data due to shortcomings of their own memory.
-could easily happen in an interview setting
What is Survivorship Bias?
when a visible successful subgroup is mistaken as the entire group.
What is Loss Aversion?
cognitive bias that describes why the pain of losing is psychologically twice as powerful as the pleasure of gaining
What is Selection Bias?
occurs when individuals or groups in a study differ systematically from the population of interest
What is stratified random sampling?
-division of a population into smaller subgroups known as strata.
-strata are formed based on members’ shared attributes or characteristics, such as income or educational attainment
What is cluster sampling?
-Probability sampling method
-Divide a population into clusters, such as districts or schools
-Then randomly select some of these clusters as your sample.
(clusters should each be mini-representations of the population as a whole)
What is systematic random sampling?
-probability sampling method
-random sample, with a fixed periodic interval, is selected from a larger population
-e.g. every third person is sampled
What is Symptomatic Population Estimating?
using local data such as utility connections or building permits to estimate the current population.
What is Translational Research?
aims to make findings from basic science useful for practical applications
If you had information on the age distribution of the population over time, which population projection method should you use?
Cohort Survival
Why should you select a random sample from a large population?
To provide an approximation of the characteristics of the population
An analysis of the relationship between one or more variables to determine if the factors impact the dependent variable is called:
Regression analysis
What are the top five U.S. Census Bureau household surveys?
American Community Survey
American Household Survey
Current Population Survey
National Health Interview Survey
National Crime Victimization Survey
Why is a random sample from a population desirable?
they get close to the characteristics of a population at a minimum cost.
The range is a proper summary of the spread in the distribution of {blank} data and {blank} data
interval; ratio
Scenario
The City is considering several different interventions to prevent foreclosures.
-They want to understand the degree to which a combination of one-time grants to homeowners to catch up on mortgage payments, placing a temporary three year freeze on property taxes, and homeowner counseling are working and whether they are reducing the foreclosure rate among those they are helping.
*Which of the following is the best statistical technique to understand this relationship?
Regression Analysis would help to understand the degree of influence of these programs.
A {blank} has the population divided into {blank} according to variables that are thought to be related to the variables of interest. Then a sample is taken from every {blank}.
stratified sample; strata; stratum
ACS data are {blank}; the Coefficient of Variation must not exceed {blank} percent
estimates; 15
Qualitative research is not appropriate for understanding {blank}
generalized trends
What is another name for nominal data?
Categories
A median is a proper summary of the central tendency of what types of data?
-ordinal
-interval
-ratio
What two data categories are qualitative?
Nominal (categories) and ordinal (ordered categories)
What two data categories are quantitative?
Interval (differences between measurements, no true zero) and ratio (differences between measurements, true zero)
What is a multiplier analysis?
-used to project the number of jobs created or lost.
If an industry had a multiplier 1.5 and 100 jobs were lost directly in the industry another {blank} would be lost in the rest of the economy.
50
Qualitative research typically involves a {blank} written report, not a {blank} one.
flexible; structured
What is a t-test?
test on the difference in means between two subgroups
(null hypothesis would be that the mean scores for the two groups are the same)
By 2045, what percentage of the population in the United States will be made up of minorities?
over half
{blank} are about rejecting the null hypothesis, never proving it.
Inferential statistics
