User Sympa

79 votes

9 answers

43k views

If A and B are correlated with C, why are A and B not necessarily correlated?

asked Dec 25, 2010 at 19:24

24 votes

1 answer

8k views

Why use ANOVA at all instead of jumping straight into post-hoc or planned comparisons tests?

asked Jun 30, 2013 at 21:13

16 votes

3 answers

4k views

Do some of you use Google Docs spreadsheet to conduct and share your statistical work with others?

asked Oct 1, 2010 at 17:21

14 votes

3 answers

26k views

How to detect when a regression model is over-fit?

asked Sep 20, 2010 at 21:35

11 votes

3 answers

797 views

How to detect which one is the better study when they give you conflicting results?

asked Sep 26, 2010 at 4:25

9 votes

1 answer

8k views

How to interpret the direction of the Harvey-Collier test and Rainbow test for linearity?

asked Feb 13, 2015 at 0:21

8 votes

3 answers

1k views

Big Data vs multiple hypothesis testing?

asked Jan 29, 2013 at 20:02

7 votes

1 answer

320 views

Can you use the paired t-test in what seems like an unpaired t-test situation?

asked Oct 3, 2013 at 22:46

6 votes

1 answer

3k views

How to calculate the specific Standard Error relevant for a specific point estimate within a linear regression?

asked Aug 15, 2013 at 23:00

6 votes

4 answers

3k views

Does the Granger Causality test in the "vars" package make sense?

asked Dec 21, 2015 at 4:33

5 votes

2 answers

31k views

How to use the LOGNORMALDIST function to generate a Cumulative Distribution Function?

asked Dec 10, 2010 at 6:17

5 votes

3 answers

2k views

Can you use heteroskedastic time series variables within a regression model?

asked Jan 4, 2011 at 16:55

4 votes

3 answers

278 views

What is a good internet based source of information on Hierarchical Modeling?

asked Sep 20, 2010 at 22:16

4 votes

1 answer

241 views

What are the reservations of Dynamic Linear Models (DLMs)?

asked Mar 8, 2016 at 21:06

4 votes

1 answer

6k views

What is the advantage of transforming variables into First Difference of the Natural Log instead of % change from one period to the next?

asked Aug 6, 2015 at 22:40

3 votes

1 answer

2k views

What are the three forms of the Park test for heteroskedasticity?

asked Dec 10, 2014 at 18:29

3 votes

2 answers

3k views

How do you compute the annual standard error of a regression model when the model itself is based on monthly observations?

asked Jan 29, 2011 at 20:30

2 votes

3 answers

4k views

How to build a regression model with just 5 datapoints with 5 or more variables?

asked Aug 8, 2012 at 16:08

2 votes

1 answer

2k views

How to estimate the deposit mix of a bank using interest rate as the independent variable?

asked Sep 27, 2012 at 15:55

2 votes

2 answers

2k views

How to calculate the combined standard error of two models?

asked Oct 1, 2012 at 21:29

2 votes

1 answer

3k views

Does heteroskedasticity matter if you have a large enough sample?

asked Apr 4, 2014 at 20:21

2 votes

1 answer

83 views

What to do if recombination of independent variables cause multicollinearity issue?

asked Oct 27, 2018 at 18:01

2 votes

1 answer

72 views

Can it be as accurate to model child-variables to estimate a parent-variable instead of modeling the parent-variable directly?

asked Aug 26, 2015 at 22:37

1 vote

2 answers

329 views

Does it make sense to purposefully run multiple regression with missing values for certain dummy variables?

asked Sep 12, 2015 at 15:20

1 vote

1 answer

1k views

ADF test for Unit Root, should you select a trend if the trend changes once?

asked Oct 24, 2015 at 19:40

1 vote

0 answers

286 views

How to do stepwise regression forward correctly?

asked Nov 15, 2015 at 1:39

1 vote

0 answers

4k views

Is it ok to have a unit root within an independent variable?

asked Mar 26, 2015 at 21:13

1 vote

2 answers

177 views

Does a Vector Autoregression Model truly avoid circular function issues?

asked Nov 3, 2019 at 18:07

1 vote

0 answers

670 views

Can a Linear-Log model be used instead of Robust Standard Errors?

asked Apr 12, 2014 at 22:01

1 vote

0 answers

524 views

How to test heteroskedasticity at the independent variable level?

asked Oct 31, 2014 at 23:00

Stack Exchange Network

36 Questions

If A and B are correlated with C, why are A and B not necessarily correlated?

Why use ANOVA at all instead of jumping straight into post-hoc or planned comparisons tests?

Do some of you use Google Docs spreadsheet to conduct and share your statistical work with others?

How to detect when a regression model is over-fit?

How to detect which one is the better study when they give you conflicting results?

How to interpret the direction of the Harvey-Collier test and Rainbow test for linearity?

Big Data vs multiple hypothesis testing?

Can you use the paired t-test in what seems like an unpaired t-test situation?

How to calculate the specific Standard Error relevant for a specific point estimate within a linear regression?

Does the Granger Causality test in the "vars" package make sense?

How to use the LOGNORMALDIST function to generate a Cumulative Distribution Function?

Can you use heteroskedastic time series variables within a regression model?

What is a good internet based source of information on Hierarchical Modeling?

What are the reservations of Dynamic Linear Models (DLMs)?

What is the advantage of transforming variables into First Difference of the Natural Log instead of % change from one period to the next?

What are the three forms of the Park test for heteroskedasticity?

How do you compute the annual standard error of a regression model when the model itself is based on monthly observations?

How to build a regression model with just 5 datapoints with 5 or more variables?

How to estimate the deposit mix of a bank using interest rate as the independent variable?

How to calculate the combined standard error of two models?

Does heteroskedasticity matter if you have a large enough sample?

What to do if recombination of independent variables cause multicollinearity issue?

Can it be as accurate to model child-variables to estimate a parent-variable instead of modeling the parent-variable directly?

Does it make sense to purposefully run multiple regression with missing values for certain dummy variables?

ADF test for Unit Root, should you select a trend if the trend changes once?

How to do stepwise regression forward correctly?

Is it ok to have a unit root within an independent variable?

Does a Vector Autoregression Model truly avoid circular function issues?

Can a Linear-Log model be used instead of Robust Standard Errors?

How to test heteroskedasticity at the independent variable level?