Indigochild1234
Badges: 4
Rep:
?
#1
Report Thread starter 1 year ago
#1
I am doing a social work degree and on a paper I am trying to use for my dissertation. The statical technique used to show significance between the results are confusing me.
They are set out like
(F-3.1, df-1235,<0.05)
-I believe f maybe an f-test to show significant or an Anova-f test but I am struggling to understand what this number means or the test.
-df I have no idea what it means
-<0.05 is p value and i can general work it out as i believe it from a t-test.
0
reply
Gregorius
Badges: 14
Rep:
?
#2
Report 1 year ago
#2
(Original post by Indigochild1234)
I am doing a social work degree and on a paper I am trying to use for my dissertation. The statical technique used to show significance between the results are confusing me.
It would be helpful if you could reproduce more of the source from which your problem comes.

They are set out like
(F-3.1, df-1235,<0.05)
There's some inconsistency here, which is why it would be good for you to reproduce more of your source. In particular, the "F-3.1" looks like it could be saying that the value of the F-statistic is 3.1 for the statistical test applied. However, the "df-1235" is puzzling. The F- distribution is characterized as being the ratio between two chi-squared random variables with degrees of freedom d1 and d2 respectively. So, the degrees of freedom specification for an F statistics should always be comprised of two numbers, not one as here.
1
reply
Indigochild1234
Badges: 4
Rep:
?
#3
Report Thread starter 1 year ago
#3
Hi, Thankyou for responding. The article I am trying to use is attached below. I have read it several times and understand the study. Mixed method approach. It is on pg 24/25 in the results that I am struggling due to the answer to the three question each has a format with the conclusion.
With each saying show a level of significance e (F = 3.83, df = 2, 121, p < 0.05). This is what I am stuck on understanding. I am trying to use it as a quantitative source.
(Original post by Gregorius)
It would be helpful if you could reproduce more of the source from which your problem comes.



There's some inconsistency here, which is why it would be good for you to reproduce more of your source. In particular, the "F-3.1" looks like it could be saying that the value of the F-statistic is 3.1 for the statistical test applied. However, the "df-1235" is puzzling. The F- distribution is characterized as being the ratio between two chi-squared random variables with degrees of freedom d1 and d2 respectively. So, the degrees of freedom specification for an F statistics should always be comprised of two numbers, not one as here.
Attached files
0
reply
Gregorius
Badges: 14
Rep:
?
#4
Report 1 year ago
#4
(Original post by Indigochild1234)
Hi, Thankyou for responding. The article I am trying to use is attached below. I have read it several times and understand the study. Mixed method approach. It is on pg 24/25 in the results that I am struggling due to the answer to the three question each has a format with the conclusion.
With each saying show a level of significance e (F = 3.83, df = 2, 121, p < 0.05). This is what I am stuck on understanding. I am trying to use it as a quantitative source.
This is a tough analysis, if you're not used to statistical methods! They're fitting a longitudinal regression model to the outcome (maternal aggression) and seeing which covariates in the regression are non-zero (at a significance level of 0.05). The covariate they're talking about in your example (F = 3.83, df = 2, 121, p < 0.05) is time - so they're trying to see if maternal aggression changed over time. The statistical test that you apply for such regression coefficients is an F-test - and in this case, the value of the F-statistic is 3.83, and the number of degrees of freedom (df1 and df2 in my earlier terminology) is the pair of values (2, 121). If you look at tables of the F-distribution, such as these here, you see that the critical value of the F distribution at the 5% level for (2,121) is about 3.1. As 3.83 > 3.1, the test is significant at the 5% level, so p < 0.05. (In fact, the actual p-value is a shade below 0.025). So they can conclude that there is evidence that maternal aggression increases over time.
0
reply
X

Quick Reply

Attached files
Write a reply...
Reply
new posts
Back
to top
Latest
My Feed

See more of what you like on
The Student Room

You can personalise what you see on TSR. Tell us a little about yourself to get started.

Personalise

Current uni students - are you thinking of dropping out of university?

Yes, I'm seriously considering dropping out (163)
14.54%
I'm not sure (51)
4.55%
No, I'm going to stick it out for now (330)
29.44%
I have already dropped out (33)
2.94%
I'm not a current university student (544)
48.53%

Watched Threads

View All