Statistics - assessment 1

Thesis question

The potential effect or relationship of two variables on each other. Written in the form of is there a relationship between variable x and variable y? _

Hypothesis

As the ________-increases, the __________

Independent variable

x - Is not dependent on y

Dependent variable

y - is dependent on the result of x

Sample

Wo the data was actually collected from

Population

Who the data was meant to reflect

Census

When the sample is the population (everyone is surveyed)

Cross sectional study

The data is gathered once from the sample and then analyzed.

Longitudinal study

the data is collected regularly from the same sample and trends appear when analyzed.

Types of variables (4)

Discrete Numerical

Continuous numerical 

Ordinal Categorical 

Non-Ordinal categorical

Discrete Numerical

A finite number of values are possible. Values cannot be subdivided. Often but not always in whole numbers example grades on a test, shoe size.

Continuous numerical 

 infinite number of values are possible. Continuous numerical data can be measured and then broken down into smaller parts and still have meaning. Example shoe size in millimetres or grade displayed on a report card.

Ordinal Categorical 

Data is not measurable, but appears in some sort of logical order. Example dislike, somewhat dislike, no opinion, somewhat like, like. 

• Ordinal data can be changed to discrete when each option is converted to a numerical grade.

Non-Ordinal categorical

this data is not measurable and does not have a logical order for example, favourite color, food, movie, etc.

Potential random sampling techniques

1. Simple random sampling

2. Systematic random sampling

3. Stratified random sampling

4. Cluster random sampling

5. Multi stage random sampling

Random sampling (concept)

The process of selecting random members of a population to survey. The best samples will reflect all of your population, and to give every member of the population and equal chance to be surveyed.

Simple random sampling

-the population is written as a list i.e. by alphabetical, birthdate, random, etc.

- random number generator will select from the list until the sample size is full.

Systematic random sampling

The population is written as a list. 

-randomly select a starting location

• To find every nth member divide the population size by the sample size.

-select every nth member from the list

Stratified random sampling

a proportional number of sub groups are surveyed

1. The population is divided into sub groups called Stratas. Each group is written as a list.

2. The sample size is divided by the population size this determines your proportion

3. Multiply the proportion by the size of each strata to get a strata sample size.

Cluster random sampling

1. The population is subdivided into Stratas

2. Write stratas as a list

3. Randomly select stratas to survey

4. Conduct a census of each strata.

Multi stage random sampling

1. The population is subdivided into Stratas

2. using technique one (simple, random sampling) or technique two (systematic random sampling) decide which strata is to survey

3. Using technique one or two select who is being surveyed from each strata.

Types of data

primary data and secondary data

Primary data

data that you or your team collect yourself

Secondary data

data that is collected elsewhere and presented or analyzed by your team.

Types of questions when obtaining data (2)

Open questions and closed questions

Closed questions

questions that force the responder into a specific types of answers.

Open questions

questions that allow for a responder to elaborate and explain their answers.

Types of closed questions

1. Information questions

2. Checklist questions

3. Ranking questions

4. Rating questions

Information questions

Questions that deal with giving a particular piece of

Checklist questions

questions that have you select one or more possible response. note not multiple choice

Ranking questions

questions to ask you to put the options in some sort of order

Rating questions

questions that ask you to write your feelings towards a subject

Types of bias

1. Sampling bias

2. Measurement bias

3. Response bias

4. Non-response bias

Bias

when the data collected or displayed does not accurately represent the population (intentionally or unintentionally)

Sampling bias

when the data becomes over/under represented due to the sample selected. This could be because the sample was collected with the wrong proportions, the incorrect group of people or didn't represent the intended population.

Measurement bias

When certain results become over/underrepresented because of the sampling technique, phrasing of the question, or situation.

Response bias

when data is over/under represented because the surveyee needs to misrepresent themselves due to sampling technique. Example a survey that asks what is your favourite subject, math science or physics.

Non-response bias

when the results become over/underrepresented because there is an optional component example a an optional survey about a teacher's performance.