Professional Documents
Culture Documents
Research
Primary Secondary
For eg:
GTM —--------- Speaking
Change/Vary the method
CLT —---------- Speaking (whether speaking skills of learners vary
accordingly)
variable variable
Speaking depends on CLT (method)
is Dependent
Speaking: Dependent variable (DV)
CLT: Independent variable (IV)
5. Validity and reliability
- The internal validity is the extent to which the outcome is a
function of the factor you have selected.
- The external validity refers to the extent that the outcome can be
generalized to other contexts.
- Reliability can be defined as the extent to which a test produces
consistent results when administered under similar conditions.
(Hatch and Farhady, 1985, p.244)
“When we increase the reliability of our measures, we are also satisfying a
necessary condition for validity: in order for a test score to be valid, it
must be reliable.”
6. Variables: Variable_Practice
a) Independent variable: The independent variable is the major variable
which you hope to investigate. It is the variable which is selected,
manipulated and measured by the researcher.
b) Dependent variable: The dependent variable is the variable which
you observe and measure to determine the effect of the
independent variable.
c) Moderator variable: A moderator variable is a special type of
independent variable which you may select for study in order to
investigate whether it modifies the relationship between the
dependent and the major independent variables.
d) Control variable: A control variable is a variable which is held
constant in order to neutralize the potential effect it might have on
behavior.
e) Intervening variable: An intervening variable is a variable which has
not been measured or manipulated.
GTM CLT
IV CLT
MV Male/Female
InV Intelligence
CV Grade 10
7. Scales
a) Nominal scale: Name (category)
b) Ordinal scale: name + order
c) Interval scale: name + order + equal intervals
8. Literature review
“A literature review surveys scholarly articles, books and other sources
relevant to a topic for a thesis or dissertation. Its purpose is to
demonstrate that writer has insightfully and critically surveyed relevant
literature on his or her topic in order to convince an intended audience
that this topic is worth addressing”
9. Sampling
Distinctive features
The one-group x ✓ x T1 x T2
pretest posttest
Factorial designs x x ✓
- Descriptive:
a) distribution (frequencies: count up the number of items &
percentage)
frequencies: 7 nam 5 nữ
percentage:
b) central tendencies (mean: arithmetic average, mode: most popular,
& median)
12346789
mean: trung bình
mode:
median:
34 48 54 56 66 69 73 74 86 86 87 87 87 87 88 88 97 99
mean= sum (34 48 54 56 66 69 73 74 86 86 87 87 87 87 88 88 97 99)/18 =
75,89
mode= 87
median = 86
X X-M (X-M)^2
1 34 -41.89 1754.77
2 48 -27.89 777.85
3 54 -21.89 479.17
4 56 -19.89 395.61
5 66 -9.89 97.81
6 69 -6.89 47.47
7 73 -2.89 8.35
8 74 -1.89 3.57
9 86 10.11 102.21
10 86 10.11 102.21
11 87 11.11 123.43
12 87 11.11 123.43
13 87 11.11 123.43
14 87 11.11 123.43
15 88 12.11 146.65
16 88 12.11 146.65
17 97 21.11 445.63
18 99 23.11 534.07
Tổng:
Tổng / (N-1) =
SD= 18.045
Variance= SD^2= 325,63
1 7 -1 1
2 6 -2 4
3 9 1 1
4 10 2 4
tổng = 1+4+1+4=10
tổng / (N-1) = 10/3
lấy căn= 1.83
SD = 1.83
variance = SD^2 =
M: Mean
+ Chi square
a) One way: 1 variable
df = column - 1
fexp = trung bình cộng fobs = (55+26)/2 = 40,5
(55-40.5)^2/ 40.5 = 5.19
(26-40.5)^2/40.5 = 5.19
x^2= 5.19 + 5,.19 = 10,38
Chi square < critical value so the correlation is statistically insignificant.
Therefore the null hypothesis cannot be rejected.
Chi square > critical value so the correlation is statistically significant. Therefore
the null hypothesis can be rejected.
df = (row-1) x (column-1)
10A 10B Total
Total 10 12 22
x^2 = 0,74
Fexpected
fexp 10A 10B
Female 5 6
- Correlational (relationship)
The magnitude of the correlation coefficient will vary from -1 to 0 to +1.
The greater the value, the stronger the relationship between the two
variables.
Scales:
- Nominal: Phi
- Ordinal: Spearman Rho
- Interval: Pearson (bảng điểm, số liệu) (df = N - 2)
r > critical value so the correlation is statistically significant. Therefore, the null
hypothesis can be rejected.
REPORT WRITING:
the researcher ….. (aim trên đề xuống)
using SPSS/ using Pearson/…
(1)r < critical value so the correlation is statistically insignificant. Therefore, the
null hypothesis cannot be rejected.
(2)r > critical value so the correlation is statistically significant. Therefore, the
null hypothesis can be rejected.
Kết luận:
Xích ma XY = 10250
Xích ma X = 245
Xích ma Y = 330
Xích ma X^2= 9825
Xích ma Y^2=/ 18500
r = 0,04
df = N - 2 = 6
N = sample = số lượng đối tượng trong bảng = 8
X = aptitude
Y = achievement
(XY tự quy ước)
scatter plot or scattergram
When to use
- Case study: investigate a contemporary phenomenon
- Ethnography: study the culture and social interactions of a group or community
- Action research: identify and address a practical problem
Techniques of data collection
- Case study: in-depth interviews, group interviews, observational methods, using
documentary sources
- Ethnography: interview, participant observation, document
- Action research: observation, interviews, focus group, surveys
Tính Toán
a. paired samples t-test: 1 group 2 thời điểm (pre - test / post -test) (trước -
sau)
MD= 2
SD =
1 5 7 7-5 = 2 0
2 8 8 0 (0-2)^2
3 7 9 2
4 2 6 4
Report
Sig. (2-tailed) < 0.05 the difference are statistically significant, therefore the null
hypothesis can be rejected.
Sig. (2-tailed) > 0.05 the difference are statistically insignificant, therefore the
null hypothesis cannot be rejected.
Conclusion
Sig. (2-tailed) < 0.05 the difference are statistically significant, therefore the null
hypothesis can be rejected. => trình độ 2 lớp k tương đồng nhau
Sig. (2-tailed) > 0.05 the difference are statistically insignificant, therefore the
null hypothesis cannot be rejected.
PRACTICE
BT Chi square: p193/ cuốn 5
Pearson: Trang 230 cuốn 5