What are the five stages of the statistical enquiry cycle, in order?

In order, the five stages are: Hypothesis & Planning Collecting Data Processing & Representing Data Interpreting Results Evaluating

True or False? 'Has the average age of brides increased since 2003?' is a suitable hypothesis for a statistical investigation.

False. A hypothesis has to be a statement that data can be tested against, not a question. A suitable version would be 'The average age of brides has increased since 2003'.

Why is the statistical enquiry process a cycle rather than a list of steps?

Because it is iterative : the stages are repeated, with improvements made each time. Once an investigation has been evaluated you go back to the planning stage and run it again, so there is no fixed beginning or end.

In the statistical enquiry cycle, what is the difference between the Interpreting Results stage and the Evaluating stage?

Interpreting Results is about what the data means: you explain the statistics and diagrams in context, draw conclusions about the hypothesis, and comment on how reliable the findings are. Evaluating is about the investigation itself: you identify weaknesses in how the data was collected or represented, and suggest improvements.

An investigation would give the best results with a sample of 5000 people, but there is only enough money for 200. Which constraint is this, and what should the plan do about it?

This is a cost constraint. You cannot always run the best possible investigation, so the plan should aim for the best investigation that can be afforded.

In planning an investigation, what is a proactive strategy, and name one problem worth planning for.

A proactive strategy is one decided at the planning stage, ahead of a problem appearing, rather than reacting once it has already happened. Problems worth planning for include difficulty identifying the population, people not answering some or all of the questions, and outcomes that were not expected.

What is the difference between quantitative data and qualitative data?

Quantitative data can be recorded as a number , such as a height, a length of time or a number of people. Qualitative data cannot be recorded as a number, such as a colour, a flavour or a make of car.

What is the difference between continuous data and discrete data?

Continuous data can take any numerical value on a scale, such as height, weight or time. Discrete data can only take particular values on a scale, and those values do not have to be whole numbers: shoe sizes are discrete but include half sizes.

Define bivariate data .

Bivariate data is data collected as pairs of values , one from each of two variables. It is collected to investigate the relationship between the two variables, for example the age of a car and the cost of its annual maintenance.

Define ordinal data .

Ordinal data is data that can be put in order . Numerical data can be ordered in the usual way. Data that is not numerical is ordinal if a rating scale can be applied to it, such as 1 to 5 running from 'disagree strongly' to 'agree strongly'.

What is the difference between primary data and secondary data?

Primary data is collected by, or specifically for, the person who is going to use it, while secondary data has been collected by somebody else. Primary data can be gathered to answer exactly the question being asked, and its accuracy and collection method are known. Secondary data is quicker, easier and cheaper to obtain, but it may be out of date and its accuracy may not be known.

What is gained by grouping a large data set into classes, and what is lost?

Grouping makes the distribution of the data clearer and any patterns easier to spot. What is lost is the exact data values , so a mean, median or mode found from grouped data can only be an estimate .

True or False? The class intervals in a grouped frequency table are allowed to have different widths.

True. Equal widths are common, and they suit data that is fairly evenly spread out. Unequal widths can be the better choice when most of the values are clustered in the middle, using narrower intervals there and wider ones at each end.

In an experiment, what is the difference between the explanatory variable and the response variable?

The explanatory (independent) variable is the one the researcher changes, or observes changes in. The response (dependent) variable is the one measured afterwards, which the researcher thinks responds to those changes. In a study of how running shoes affect 100 metre sprint times, the type of shoe is explanatory and the time taken is the response.

GCSEStatisticsEdexcelFoundationFlashcardsThe Collection of DataPlanning & Types of Data

Planning & Types of Data (Edexcel GCSE Statistics: Foundation): Flashcards

Exam code: 1ST0

1/19

0Still learning

Know0

FrontPlanning an Enquiry
What are the five stages of the statistical enquiry cycle, in order?
BackPlanning an Enquiry
In order, the five stages are:
Hypothesis & Planning
Collecting Data
Processing & Representing Data
Interpreting Results
Evaluating
BackPlanning an Enquiry
Sign up to unlock flashcards
Join for free to unlock a full flashcard set, track what you know,
and turn revision into real progress.

Was this flashcard helpful?

Cards in this collection (19)

What are the five stages of the statistical enquiry cycle, in order?
In order, the five stages are:
- Hypothesis & Planning
- Collecting Data
- Processing & Representing Data
- Interpreting Results
- Evaluating
True or False?
'Has the average age of brides increased since 2003?' is a suitable hypothesis for a statistical investigation.
False.
A hypothesis has to be a statement that data can be tested against, not a question.
A suitable version would be 'The average age of brides has increased since 2003'.
Why is the statistical enquiry process a cycle rather than a list of steps?
Because it is iterative: the stages are repeated, with improvements made each time.
Once an investigation has been evaluated you go back to the planning stage and run it again, so there is no fixed beginning or end.
Complete the statement about testing a hypothesis.
A hypothesis can only be tested through the appropriate $______$ and $______$ of data.
The completed statement is:
A hypothesis can only be tested through the appropriate collection and analysis of data.
In the statistical enquiry cycle, what is the difference between the Interpreting Results stage and the Evaluating stage?
Interpreting Results is about what the data means: you explain the statistics and diagrams in context, draw conclusions about the hypothesis, and comment on how reliable the findings are.
Evaluating is about the investigation itself: you identify weaknesses in how the data was collected or represented, and suggest improvements.
An investigation would give the best results with a sample of 5000 people, but there is only enough money for 200. Which constraint is this, and what should the plan do about it?
This is a cost constraint.
You cannot always run the best possible investigation, so the plan should aim for the best investigation that can be afforded.
In planning an investigation, what is a proactive strategy, and name one problem worth planning for.
A proactive strategy is one decided at the planning stage, ahead of a problem appearing, rather than reacting once it has already happened.
Problems worth planning for include difficulty identifying the population, people not answering some or all of the questions, and outcomes that were not expected.
What is the difference between quantitative data and qualitative data?
Quantitative data can be recorded as a number, such as a height, a length of time or a number of people.
Qualitative data cannot be recorded as a number, such as a colour, a flavour or a make of car.
What is the difference between continuous data and discrete data?
Continuous data can take any numerical value on a scale, such as height, weight or time.
Discrete data can only take particular values on a scale, and those values do not have to be whole numbers: shoe sizes are discrete but include half sizes.
Define bivariate data.
Bivariate data is data collected as pairs of values, one from each of two variables.
It is collected to investigate the relationship between the two variables, for example the age of a car and the cost of its annual maintenance.
True or False?
Heights in metres could be recorded using the two categories $h \leq 1.7$ and $h \geq 1.7$ .
False.
Categories must be non-overlapping, so that every value belongs to one category and one only.
A height of exactly 1.7 belongs to both of these categories, so $h < 1.7$ and $h \geq 1.7$ should be used instead.
Define ordinal data.
Ordinal data is data that can be put in order.
Numerical data can be ordered in the usual way.
Data that is not numerical is ordinal if a rating scale can be applied to it, such as 1 to 5 running from 'disagree strongly' to 'agree strongly'.
What is the difference between primary data and secondary data?
Primary data is collected by, or specifically for, the person who is going to use it, while secondary data has been collected by somebody else.
Primary data can be gathered to answer exactly the question being asked, and its accuracy and collection method are known.
Secondary data is quicker, easier and cheaper to obtain, but it may be out of date and its accuracy may not be known.
What is gained by grouping a large data set into classes, and what is lost?
Grouping makes the distribution of the data clearer and any patterns easier to spot.
What is lost is the exact data values, so a mean, median or mode found from grouped data can only be an estimate.
True or False?
The class intervals in a grouped frequency table are allowed to have different widths.
True.
Equal widths are common, and they suit data that is fairly evenly spread out.
Unequal widths can be the better choice when most of the values are clustered in the middle, using narrower intervals there and wider ones at each end.
Why are $0 \leq t \leq 10$ and $11 \leq t \leq 20$ unsuitable as class intervals for a continuous variable?
Because there is a gap between them, and a continuous variable can take any value inside that gap.
A value of 10.4 would have no class to go in, so intervals such as $0 \leq t < 10$ and $10 \leq t < 20$ should be used instead.
A set of times has been rounded to the nearest second. Why are $60 \leq t < 70$ and $70 \leq t < 80$ poor class intervals to use?
Because a time recorded as 70 seconds could really be anything from 69.5 to 70.5 seconds, so those readings fall on both sides of the boundary at 70.
All the values that round to the same figure must fall in the same class, so use $59.5 \leq t < 69.5$ and $69.5 \leq t < 79.5$ instead.
Complete the rule for plotting a scatter diagram.
The $______$ variable goes on the x-axis and the $______$ variable goes on the y-axis.
The completed rule is:
The explanatory (independent) variable goes on the x-axis and the response (dependent) variable goes on the y-axis.
In an experiment, what is the difference between the explanatory variable and the response variable?
The explanatory (independent) variable is the one the researcher changes, or observes changes in.
The response (dependent) variable is the one measured afterwards, which the researcher thinks responds to those changes.
In a study of how running shoes affect 100 metre sprint times, the type of shoe is explanatory and the time taken is the response.

Sign up to unlock flashcards

By signing up you agree to our Terms and Privacy Policy

Next:Population, Sampling & Collecting Data