Scribd Logo
Upload

Welcome to Scribd!

  • 3 views

    RMDS 2023 Q1 Q&Alecture Unit 19 20 PM_canvas

    Uploaded by

    z13612909240

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    RMDS 2023 Q1 Q&Alecture Unit 19 20 PM_canvas

    Uploaded by

    z13612909240
    3 views36 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    3 views36 pages

    RMDS 2023 Q1 Q&Alecture Unit 19 20 PM_canvas

    Uploaded by

    z13612909240

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 36

    Q&A LECTURE - UNIT 19, 20

    Resit Test 1 – Tomorrow


    • Remindo test: including a scientific calculator
    • Chrome books of the UT
    • 40 MC questions
    • Therm 2
    • 13:45-15:45 hrs.

    • Test 1: Unit 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 23


    Test 2 & R test – Friday 3 Nov 2023 – 13:35-
    16:45 hrs
    • Remindo tests
    • Chrome books of the UT
    • Test 2:
    • 40 MC questions
    • Unit 13, 24, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22
    • including a scientific calculator
    • R-test: similar to R practice test:

    • NH205: 65 persons: surnames start with A - G


    • NH207: 60 persons: surnames starting with H - M
    • NH209: 75 persons: surnames starting with N - Z
    What else today..
    • Unit 19 - Sampling:
    Probability vs. non-probability sampling
    “Could you explain the last question of asg unit 19? (The researcher
    adapts his plans and decides to focus on the wide variety of first year
    psychology students at the University of Twente...).

    Unit 20 – Certainty about the mean:


    Population, sample, sampling distribution (of the mean)
     assignment Q7 (start with Q5)
    Theoretical
    Research variable(s)
    Question
    I. Conceptualization
    II. Operationalization
    III. Measurement

    v1 v2
    Sampling unit1
    All Units unit2
    Data
    unit3
    unit4
    Sampling 6

    • Before sampling, you need a clear definition on


    the population of interest (target population)
     Units of Analysis in your RQ

    • A population refers to all members of a certain


    group of people/companies/countries
    Probability sampling 7

    Selected randomly from the population  Individuals have an equal or known


    chance to participate in the study.
    • Goal: your sample represents well the (target) population (external validity)
    • a sampling frame is necessary

    Sampling frame
    Types of probability sampling 8

    1. Simple random sampling (SRS)


    2. Stratified random sampling
    3. Cluster random sampling
    4. Multi-stage random sampling
    Non-probability sampling 9

    Selected non-randomly: individuals have an unequal or unknown


    chance to participate in the study.

    • No sampling frame available


    • Sample is not representative for the population
    • Goal: Inductive reasoning (explorative empirical research)
    Types of non-probability sampling 10

    Selected non-randomly: individuals have an unequal or unknown chance to


    participate in the study.

    1. Convenience
    2. Purposive
    3. Systematic

    4. Quota (purposive, with fixed final size)


    5. Snowball (social network of resp.)
    Today..
    Could you explain the last question of unit 19?
    The researcher adapts his plans and decides to focus on the wide
    variety of first year psychology students at the University Twente.
    Because of the diverse educational careers sofar, the quality of the
    psychology study might be improved by offering a more personalized
    study program in BA-1.
    The researcher wants to explore whether the present program fits to
    the diverse personal needs of the BA-1 students. He wants to cover a
    wide variety of BA-1 students by defining subgroups.
    • Which type of sampling method would you advise to researcher?
    • Describe the sampling method in more detail.
    Today..
    • Unit 19 - Sampling:
    Probability vs. non-probability sampling

    • Unit 20 – Certainty about the mean:


    Population, sample, sampling distribution (of the mean)
     assignment Q5 & Q7
    Sample distribution vs. sampling
    distribution
    Which statement is/are correct?
    A. A Sample distribution displays which values of a variable you have
    obtained after drawing a sample of a give size from a population.
    B. A Sampling distribution displays the values of a statistic (e.g. mean, SD,
    var) from repeatedly drawing samples of a give size from a population.

    1. A and B are correct


    2. Only A is correct
    3. Only B is correct
    4. A and B are not correct
    5. I don’t know 
    Q5: Average height in the
    population?
    • website
    http://onlinestatbook.com/stat_sim/sampling_dist/

    • Population: Height is normally


    distributed, ranges 0-32

    14
    Population distribution

    Sample distribution =
    distribution of height
    (after SRS): n=5
    Sampling distribution of
    the mean height of 5
    persons

    Sampling distribution of
    “none”
    → .. the sample “mean”
    → .. 25 persons
    Q5: Average height in the
    population?
    • website http://onlinestatbook.com/stat_sim/sampling_dist/

    • Population: Height is normally distributed,


    ranges 0-32

    1. Session: “animated” (one by one)


    •  3rd graph: draw 1 sample of n=2 persons
    and determine their mean heights
    •  4th graph: draw 1 sample of n=25 persons
    and determine their mean heights
    16
    website http://onlinestatbook.com/stat_sim/sampling_dist/
    Q5: Height of a population
    • website http://onlinestatbook.com/stat_sim/sampling_dist/

    • Height is normally distributed, range 0-32

    Q5a. Session: “10.000”


    •  3rd graph: drawing 10.000 samples of n=2 persons and determine
    their mean heights
    •  4th graph: drawing 10.000 sample of n=25 persons and determine
    their mean heights

    18
    Q5b:
    Compare mean and SD of both “sampling distribution of the
    (sample) mean”. Are they different?
    Q5b:
    Compare mean and SD of the sampling distribution of the
    mean

    • Means are almost similar


    • SD for n=25 < SD for n=2

    • “With a sample size of 25 you


    are more confident about the
    value of the population mean
    compared to a sample size of
    2“(the range of graph is larger)
    Q7/Q5c: What is the formula for the SD of the
    sampling distribution of the (sample) mean?

    Standard Deviation
    of the population!

    = SEM = Standard Error of the Mean


    Q5d: Compute SD of the sampling distribution of
    the (sample) mean? What is the SEM?
    Why should you memorize this SEM
    formula?

    inference
    Why should you memorize this SEM formula?
    The common situation in research …..
    • RQ: What is the average height of all UT students?
    • The distribution of height in the population is unknown
    →  and  are unknown
    • You just have one sample, randomly drawn from the
    population (SRS)
    • and s can be calculated easily.

    Standard
    Deviation
    of a samp
    le
    VARIANCE / STANDARD DEVIATION
     “Variance is the average of the squared differences from the mean”
    Why should you memorize this SEM formula?
    Information from one random sample (n > 30) can be used to say what the average height
    of UT students probably is (inference).
    ------------------------------------------------------------------------------------------------------------
    Central Limit Theorem:
    “If you draw many random samples from the population that are large enough (n > 30) and
    calculate the sample mean each time…..

    many

    …. the sampling distribution of the sample means is approximately normal, irrespective the
    shape of the population distribution.”


    Why should you memorize this SEM formula?
    Information from one random sample (n > 30) can be used to say what the average
    height of UT students probably is (inference).
    ------------------------------------------------------------------------------------------------------------
    Central Limit Theorem:
    “If you draw many random samples from the population which are sufficient large (n > 30)
    that are large enough (n > 30) and calculate the sample mean each time…..

    many

    ….the sampling distribution of the sample means is approximately normal, irrespective the
    shape of the population distribution.”

     That’s . The shape of a normal distribution is well known and very useful.
    NORMAL DISTRIBUTION

    Q7c: Empirical rule (68-95-99.7 rule)

    0.954 (or 95.4%)

    http://onlinestatbook.com/2/calculators/normal.html
    Why should you memorize this SEM
    formula?
    Central Limit Theorem:
    1. “The shape of sampling distribution is normal”.
    • - 1 SD to +1 SD: 68% of the values
    • - 2 SD to +2 SD: 95.4% of the values
    • -1.96 SD to +1.96 SD: 95.0 % of the values

    • We can use these characteristics to express our uncertainty about


    the mean of the population with only one sample!
     “95% Confidence interval of the mean”
    Why should you memorize this SEM
    formula?
    Information from one random sample (n > 30) can be used to say what the average height
    of UT students probably is (inference).
    -----------------------------------------------------------------------------------------------------------
    Central Limit Theorem:
    1. Shape of sampling distribution is normal;
    And
    2. Mean of the sampling distribution almost equals to population mean.

    → the goal of answering our RQ is close, despite we don’t known distribution of


    height in the UT population
    Why should you memorize this SEM
    formula?
    Information from one random sample (n > 30) can be used to say what the average height
    of UT students probably is (inference).
    -----------------------------------------------------------------------------------------------------------
    Central Limit Theorem:
    1. Shape of sampling distribution is normal;
    2. Mean of the sampling distribution almost equals to population mean.
    And
    3. SD of the sampling distribution (of the sample means) = SEM =

    We don’t know , but our best estimate is s.


    Why should your memorize this SEM
    formula?
    You can use information from one random sample (n > 30, ) to say what the
    average height of UT students probably is (inference).
    ----------------------------------------------------------------------------------------------------

    • 95% Confidence Interval of the mean = sample mean ± 1.96 * SEM

    S
    Why should you memorize this SEM
    formula?
    You can use information from one random sample (n > 30) to say what the average height
    of UT students probably is (inference).
    ------------------------------------------------------------------------------------------------------------

    “The average height of UT students is 1.71 cm (95 CI: [1.65, 1.77])”

    Interpret the 95% CI of the mean:


    • “95% of all sample means closest to the actual population mean are between
    1.65 and 1.77 cm”.
    • “With repeated (random) sampling, the interval 1.65 to 1.77 cm holds the actual
    population mean 95% of the times”.

    • “I am 95% confident that the interval 1.65 to 1.77 cm holds the actual population
    mean.”
    QUESTIONS?
    GOOD LUCK AT THE RESIT TEST 1! 

    You might also like